WO2024156177A1 - 空调系统及其控制方法 - Google Patents

空调系统及其控制方法 Download PDF

Info

Publication number
WO2024156177A1
WO2024156177A1 PCT/CN2023/114293 CN2023114293W WO2024156177A1 WO 2024156177 A1 WO2024156177 A1 WO 2024156177A1 CN 2023114293 W CN2023114293 W CN 2023114293W WO 2024156177 A1 WO2024156177 A1 WO 2024156177A1
Authority
WO
WIPO (PCT)
Prior art keywords
air
historical
cooling
conditioning system
temperature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/114293
Other languages
English (en)
French (fr)
Inventor
石靖峰
孟建军
张文强
阮岱玮
王锡元
张国轩
魏枫
盛凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Original Assignee
Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202310078863.XA external-priority patent/CN116007072B/zh
Priority claimed from CN202310155043.6A external-priority patent/CN118532787A/zh
Application filed by Qingdao Hisense Hitachi Air Conditioning System Co Ltd filed Critical Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Priority to EP23918178.7A priority Critical patent/EP4607101A4/en
Publication of WO2024156177A1 publication Critical patent/WO2024156177A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F5/00—Air-conditioning systems or apparatus not covered by F24F1/00 or F24F3/00, e.g. using solar heat or combined with household units such as an oven or water heater
    • F24F5/0003—Exclusively-fluid systems
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F24F2110/12—Temperature of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F24F2110/22—Humidity of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2140/00—Control inputs relating to system states

Definitions

  • the present disclosure relates to the technical field of air conditioning, and in particular to an air conditioning system and a control method thereof.
  • Air conditioning systems include central air conditioning systems and chiller systems.
  • the refrigeration process of the central air-conditioning system and the chiller system involves the compression, heat dissipation, evaporation and heat absorption of the refrigerant medium.
  • the refrigerant medium circulates in the refrigeration circuit to absorb heat from the indoor air and reduce the temperature of the indoor air, thereby realizing the refrigeration cycle.
  • an air conditioning system comprising a cooling tower, a chiller and a controller.
  • the cooling tower is configured to assist cooling water.
  • the chiller comprises a condenser.
  • the condenser and the cooling tower form a cooling water loop, and the cooling water circulates in the cooling water loop.
  • the controller is electrically connected to the cooling tower and the chiller, and is configured to: obtain the current operating condition of the cooling tower and multiple control strategies under the current operating condition; wherein the current operating condition is determined by the current outdoor dry-bulb temperature and the current outdoor relative humidity; the control strategy includes a designed cooling water temperature difference, a designed cooling water flow rate, and a first approximation degree; according to the current operating condition, the multiple control strategies, and a first energy consumption model, determine the first operating power of the cooling tower corresponding to the multiple control strategies under the current operating condition; wherein the first energy consumption model is used to characterize the relationship between the first operating power of the cooling tower and the control strategy; according to the first operating power of the cooling tower corresponding to the multiple control strategies, determine a target control strategy; wherein the target control strategy is a control strategy corresponding to the minimum first operating power of the cooling tower among the multiple control strategies; according to the minimum first operating power of the cooling tower and a second energy consumption model, determine a target operating frequency of the cooling tower; wherein the second energy consumption model
  • a control method for an air conditioning system comprising a cooling tower and a chiller.
  • the cooling tower is configured to assist cooling water.
  • the chiller comprises a condenser; the condenser and the cooling tower form a cooling water loop, and the cooling water circulates in the cooling water loop.
  • the method comprises: obtaining the current working condition of the cooling tower and a plurality of control strategies under the current working condition; wherein the current working condition is determined by the current outdoor dry-bulb temperature and the current outdoor relative humidity; the control strategy comprises a designed cooling water temperature difference, a designed cooling water flow rate and a first approximation degree; determining the first operating power of the cooling tower corresponding to the plurality of control strategies under the current working condition according to the current working condition, the plurality of control strategies and a first energy consumption model; wherein the first energy consumption model is used to characterize the relationship between the first operating power of the cooling tower and the control strategy; determining a target control strategy according to the first operating power of the cooling tower corresponding to the plurality of control strategies; wherein the target control strategy is the control strategy corresponding to the minimum first operating power of the cooling tower among the plurality of control strategies; determining a target operating frequency of the cooling tower according to the minimum first operating power of the cooling tower and a second energy consumption model; wherein the second energy consumption model is used to characterize the
  • another air conditioning system comprising at least two air conditioning devices and a controller.
  • the controller is electrically connected to the at least two air conditioning devices.
  • the controller is configured to: obtain the total predicted cooling load value of the air conditioning system at the predicted moment according to the outdoor temperature, outdoor relative humidity and total actual cooling load value of the air conditioning system at the historical moment; obtain the total energy efficiency ratio corresponding to the air conditioning system under multiple start-up modes according to the total predicted cooling load value and the operating power of each air conditioning device; wherein the multiple start-up modes include at least one air conditioning device of the at least two air conditioning devices being turned on; and obtain a target start-up mode, and use the target start-up mode as the start-up mode of the air conditioning system at the predicted moment; wherein the target start-up mode is the start-up mode corresponding to the maximum total energy efficiency ratio among the total energy efficiency ratios corresponding to the air conditioning system under the multiple start-up modes.
  • another method for controlling an air conditioning system comprising: controlling the room temperature of the air conditioning system at a historical moment according to ... outdoor temperature, outdoor relative humidity and total actual cooling load value, to obtain the total predicted cooling load value of the air-conditioning system at the predicted time; according to the total predicted cooling load value and the operating power of each air-conditioning device, to obtain the total energy efficiency ratio corresponding to the air-conditioning system under multiple start-up modes; wherein the multiple start-up modes include at least one air-conditioning device being turned on; and to obtain a target start-up mode, and use the target start-up mode as the start-up mode of the air-conditioning system at the predicted time; wherein the target start-up mode is the start-up mode corresponding to the maximum total energy efficiency ratio among the total energy efficiency ratios corresponding to the air-conditioning system under the multiple start-up modes.
  • FIG1 is a structural diagram of an air conditioning system according to some embodiments.
  • FIG2 is a structural diagram of a water chiller according to some embodiments.
  • FIG3 is a structural diagram of another water chiller according to some embodiments.
  • FIG4 is a block diagram of a controller according to some embodiments.
  • FIG5 is a flow chart of a method for controlling an air conditioning system according to some embodiments.
  • FIG6 is a block diagram of another controller according to some embodiments.
  • FIG7 is a block diagram of another air conditioning system according to some embodiments.
  • FIG8 is a block diagram of an air conditioning device according to some embodiments.
  • FIG9 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG10 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG11 is a structural diagram of a neural network for predicting cooling load values according to some embodiments.
  • FIG12 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG13 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG14 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG15 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • FIG16 is a flow chart of yet another method for controlling an air conditioning system according to some embodiments.
  • FIG. 17 is a flow chart of a method for controlling a chiller system according to some embodiments.
  • first and second are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.
  • a feature defined as “first” or “second” may explicitly or implicitly include one or more of the features.
  • plural means two or more.
  • connection and its derivative expressions may be used.
  • connection should be understood in a broad sense.
  • connection can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium.
  • At least one of A, B, and C has the same meaning as “at least one of A, B, or C” and both include the following combinations of A, B, and C: A only, B only, C only, the combination of A and B, the combination of A and C, the combination of B and C, and the combination of A, B, and C.
  • a and/or B includes the following three combinations: A only, B only, and a combination of A and B.
  • the term “if” is optionally interpreted to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.
  • the phrase “if it is determined that” or “if [the stated condition or event] is detected” is optionally interpreted to mean “upon determining that” or “in response to determining that” or “upon detecting [the stated condition or event],” depending on the context. "[stated condition or event]” or “in response to detecting [stated condition or event]”.
  • the chiller In the central air conditioning system, the chiller needs to compress and circulate the refrigerant to lower the indoor temperature. Therefore, it consumes a lot of electricity and has high energy consumption. In this case, by optimizing the power and other parameters of the chiller to reduce energy consumption, energy saving can be achieved. Usually, the energy consumption of the chiller can be reduced through regular maintenance or control and management of the chiller load.
  • the cooling tower in the central air conditioning system needs to expose hot or cold water to the air and use evaporation to reduce the temperature of the water.
  • a large amount of air volume is required to promote heat transfer between water and air. Therefore, the cooling tower requires a high-power fan, and a high-power fan consumes more electricity when running, which will increase the energy consumption of the cooling tower.
  • the power consumption of the cooling tower accounts for 12% to 15% of the total power consumption. Therefore, in the central air-conditioning system, energy-saving optimization of the cooling tower can also reduce the energy consumption of the central air-conditioning system.
  • the cooling tower can maintain a high working efficiency, thereby reducing the energy consumption of the cooling tower.
  • maintaining and cleaning the cooling tower requires manpower, time and resources, resulting in increased maintenance costs for the cooling tower.
  • the cooling tower needs to be shut down during maintenance, affecting the continuous operation of the system.
  • the operating parameters of the cooling tower can be adjusted according to the changes in seasons and ambient temperature to improve the working efficiency of the cooling tower and reduce energy consumption.
  • the above method requires adding complex control systems and monitoring equipment to the air-conditioning system, which increases the complexity and maintenance difficulty of the air-conditioning system.
  • some embodiments of the present disclosure provide an air conditioning system.
  • a first energy consumption model and a second energy consumption model can be established based on historical data and preset data of the central air conditioning system under different working conditions in the historical data.
  • the first energy consumption model multiple first operating powers of the cooling tower under the current working condition can be obtained.
  • the target operating frequency under the current working condition can be obtained, and then the cooling tower can be controlled to operate according to the target operating frequency, which can achieve the effect of reducing energy consumption.
  • the air-conditioning system is a central air-conditioning system, or other types of air-conditioning systems, which is not limited in the present disclosure.
  • the operating power of the cooling tower in the present disclosure refers to the operating power of the cooling tower fan in the cooling tower
  • the operating frequency of the cooling tower refers to the operating frequency of the cooling tower fan in the cooling tower, which will not be repeated below.
  • FIG. 1 is a structural diagram of a central air conditioning system according to some embodiments.
  • the air conditioning system 1 includes a chiller 101, and the chiller 101 is configured to cool the chilled water flowing through the chiller 101.
  • the chiller 101 includes a plurality of chillers and a condenser.
  • the condenser and the cooling tower form a cooling water loop, and the cooling water circulates in the cooling water loop.
  • FIG. 2 is a structural diagram of a water chiller according to some embodiments.
  • the chiller includes a compressor 1011, a condenser 1012, an evaporator 1013, and a throttling device 1014.
  • the compressor 1011, the condenser 1012, the evaporator 1013, and the throttling device 1014 are sequentially connected to form a refrigerant circulation loop.
  • a stop valve may be provided on the pipeline between the compressor 1011 and the condenser 1012.
  • the compressor 1011 compresses the low-temperature and low-pressure gaseous refrigerant into a high-temperature and high-pressure gaseous refrigerant and discharges it to the condenser 1012.
  • the high-temperature and high-pressure gaseous refrigerant exchanges heat with the outdoor air flow in the condenser 1012, and the refrigerant releases heat.
  • the released heat is carried by the air flow to the outdoor ambient air, and the refrigerant undergoes a phase change and condenses into a liquid or a gas-liquid two-phase refrigerant.
  • the refrigerant flows out of the condenser 1012, enters the throttling device 1014, and is cooled and reduced in pressure to become a low-temperature, low-pressure refrigerant.
  • the low-temperature, low-pressure refrigerant enters the evaporator 1013, absorbs the heat of the refrigerant in the evaporator 1013, and reduces the temperature of the refrigerant in the evaporator 1013, thereby achieving a refrigeration effect.
  • the refrigerant undergoes a phase change and evaporates into a low-temperature, low-pressure gaseous refrigerant, which flows back into the compressor 1011, thereby achieving the recycling of the refrigerant.
  • the air conditioning system 1 further includes a water separator 102.
  • the inlet end of the water separator 102 is connected to the water chiller.
  • the outlet end of the water distributor 101 is connected to the cold water user 112 , and the water distributor 102 is configured to distribute chilled water to the cold water user 112 .
  • the outlet end of the water distributor 102 is connected to a plurality of cooling devices 112 , and the water distributor 102 is configured to distribute the flow of chilled water to the plurality of cooling devices 112 so that the pressure of the multiple channels of chilled water entering the plurality of cooling devices 112 is approximately equal.
  • the air conditioning system 1 further includes a water collector 103 and a chilled water pump 104.
  • the inlet end of the water collector 103 is connected to the cooling device 112, and the outlet end of the water collector 103 is connected to the chilled water pump 104 through a chilled water pump valve.
  • the water collector 103 is configured to collect chilled water.
  • the water distributor 102 and the water collector 103 are connected to the cooling device 112 through a connecting pipe.
  • chilled water flows from the outlet of the water distributor 102 through the connecting pipe through the cooling device 112, and then enters the water collector 103 from the inlet of the water collector 103 through the pipe.
  • a first end of the chilled water pump 104 is connected to an inlet end of the chiller 101, and a second end of the chilled water pump 104 is connected to an outlet end of the water collector 103.
  • the chilled water pump 104 is configured to circulate chilled water so that the chilled water exchanges heat with indoor air to reduce the temperature of the indoor air, thereby achieving a cooling effect.
  • the chilled water pump 104 includes a chilled water pump valve, and the chilled water pump valve is configured to adjust the size of its opening to control the flow size of the chilled water in the pipeline.
  • the chiller 101, the water distributor 102, the water collector 103, and the chilled water pump 104 connected in sequence constitute a chilled water circuit.
  • the air conditioning system 1 further includes a cooling water pump 105 and a cooling tower 106.
  • a first end of the cooling water pump 105 is connected to an outlet end of the chiller 101, and a second end of the cooling water pump 105 is connected to a first end of the cooling tower 106.
  • the cooling water pump 105 is configured to circulate cooling water, so that after the chilled water takes away the heat in the room, the chilled water transfers the heat to the cooling water through the chiller 101.
  • the cooling water pump 105 is also configured to press the heated cooling water into the cooling tower 106, so that the heated cooling water exchanges heat with the atmosphere and cools down, and, after the cooling water cools down, sends the cooling water back to the condenser 1012 in the chiller to continue heat exchange.
  • the cooling water pump 105 includes a cooling water pump valve, and the cooling water pump valve is configured to adjust the size of its opening to control the flow size of the cooling water in the pipeline.
  • the chiller 101 , the cooling water pump 104 , and the cooling tower 106 connected in sequence form a cooling water loop.
  • the second end of the cooling tower 106 is connected to the inlet end of the chiller 101.
  • the cooling tower 106 is configured to promote heat exchange between cooling water and flowing air, so that the heat in the cooling water is dissipated into the flowing air to reduce the temperature of the cooling water, and to recover and circulate the cooling water.
  • the cooling tower 106 includes at least one cooling tower fan, which is configured to accelerate the flow of surrounding air to accelerate the reduction of the cooling water temperature.
  • the air conditioning system 1 may include one or more cooling towers 106, which is not limited in the present disclosure.
  • FIG. 4 is a block diagram of a controller according to some embodiments.
  • the air conditioning system 1 further comprises a first temperature sensor 107, which is disposed near the cooling tower 106 and in contact with outdoor air.
  • the first temperature sensor 107 is configured to detect an outdoor dry-bulb temperature.
  • the air conditioning system 1 further includes a second temperature sensor 108 , which is disposed at a first end of the cooling tower 106 , and is configured to detect the temperature of the cooling water when it enters the cooling tower 106 .
  • the air conditioning system 1 further includes a third temperature sensor 109 , which is disposed at the second end of the cooling tower 106 , and is configured to detect the temperature of the cooling water when it flows out of the cooling tower 106 .
  • the air conditioning system 1 further includes a humidity sensor 110 , which is disposed near the cooling tower 106 and in contact with outdoor air.
  • the humidity sensor 110 is configured to detect outdoor relative humidity.
  • the air conditioning system 1 further includes a flow meter 111 , which is disposed at the second end of the cooling tower and is configured to detect the flow rate of cooling water.
  • the air conditioning system 1 further includes a controller 40.
  • the controller 40 is electrically connected to the chiller 101, the chilled water pump 104, the cooling water pump 105, the cooling tower 106, the first temperature sensor 107, the second temperature sensor 108, the third temperature sensor 109, the humidity sensor 110, and the flow meter 111, and the controller 40 is configured to generate an operation control signal according to the instruction operation code and the timing signal, instructing the air conditioning system 1 to execute the control instruction.
  • the controller 40 can obtain the outdoor dry-bulb temperature detected by the first temperature sensor 107, the first temperature detected by the second temperature sensor 108, the second temperature detected by the third temperature sensor 109, the outdoor relative humidity detected by the humidity sensor 110, and the flow rate of cooling water detected by the flow meter 111.
  • the controller 40 is a central processing unit (CPU), a general processor, a network processor, Network processor (NP), digital signal processor (DSP), etc.
  • the controller 40 can be used to control the operation of each component in the air conditioning system 1, so that each component of the air conditioning system 1 operates to achieve each predetermined function of the air conditioning system 1.
  • Some embodiments of the present disclosure further provide a control method for an air-conditioning system.
  • the control method can be applied to the air-conditioning system described in any of the above embodiments and executed by a controller of the air-conditioning system.
  • Fig. 5 is a flow chart of a control method of a central air conditioning system according to some embodiments. The control method will be described in detail below in conjunction with Fig. 5 .
  • control method of the air conditioning system includes steps S101 to S105 .
  • step S101 the current operating condition of the cooling tower 106 and multiple control strategies under the current operating condition are obtained.
  • the current operating condition of the cooling tower 106 can be determined by the current outdoor dry bulb temperature and the current outdoor relative humidity.
  • the control strategy includes a designed cooling water temperature difference, a designed cooling water flow rate, and a first approximation degree. Under the current operating condition, multiple groups of control strategies can be obtained by combining different designed cooling water temperature differences, designed cooling water flow rates, and first approximations.
  • step S102 according to the current operating condition, the multiple control strategies and the first energy consumption model, the first operating power of the cooling tower corresponding to each control strategy under the current operating condition is determined.
  • the first energy consumption model is used to characterize the relationship between the first operating power of the cooling tower and the control strategy.
  • the current wet bulb temperature can be determined according to the current outdoor dry bulb temperature detected by the first temperature sensor and the current outdoor relative humidity detected by the humidity sensor.
  • the current wet bulb temperature, multiple sets of designed cooling water temperature differences, designed cooling water flow rates, the first approximation degree, and the rated operating power corresponding to the current working condition in the multiple sets of control strategies are substituted into the first energy consumption model for calculation to obtain the first operating power corresponding to each set of control strategies under the current working condition.
  • T wb T ⁇ arctan[0.151977(RH+8.313659) 0.50 ]+arctan(T+RH)- arctan(RH-1.676331)+0.00391838 ⁇ RH 1.5 ⁇ arctan(0.023101RH)-4.686035 (1)
  • Twb represents the current wet-bulb temperature
  • T is the current outdoor dry-bulb temperature
  • RH is the current outdoor relative humidity
  • the method for acquiring the first energy consumption model includes steps S201 to S204.
  • step S201 historical data information of the cooling tower 106 under multiple historical operating conditions within a preset time period, as well as historical operating power, historical operating frequency and rated operating power corresponding to the historical data information are obtained.
  • the historical data information under each of the historical operating conditions includes a historical wet-bulb temperature, a historical control strategy, and a preset wet-bulb temperature, a preset cooling water temperature difference, a preset cooling water flow rate, and a preset degree of approximation corresponding to the historical operating condition.
  • the historical control strategy includes the historical cooling water temperature difference, the historical cooling water flow rate, and the historical approximation degree, and the historical wet-bulb temperature is determined by the historical outdoor dry-bulb temperature and the historical outdoor relative humidity in the historical operating conditions.
  • the wet bulb temperature refers to the temperature of the surrounding air when water vapor evaporates from the target surface.
  • the historical wet bulb temperature can be calculated based on the historical outdoor dry bulb temperature and the historical outdoor relative humidity.
  • the preset duration is one year, or the preset duration can also be determined according to the needs of the tester, which is not limited in the present disclosure.
  • the historical data information under the multiple historical operating conditions includes the historical data information corresponding to a historical operating frequency less than the first preset frequency, the historical data information corresponding to a historical operating frequency greater than the second preset frequency, and the historical data information corresponding to a historical operating power greater than the first preset power and less than the second preset power, and the first data information is obtained.
  • the cooling tower 106 may malfunction during operation, resulting in abnormal data in its historical operating power or historical operating frequency. Therefore, removing the historical data information corresponding to the abnormal historical operating frequency and the abnormal historical operating power can eliminate interference factors in the historical data information, thereby helping to improve the accuracy of the first energy consumption model.
  • the first preset frequency may be 30 Hz
  • the second preset frequency may be 50 Hz
  • the first preset power may be The second preset power may be in, is the average value of the historical operating power within the preset time
  • ⁇ 1 is the average difference of the historical operating power within the preset time
  • P represents the historical operating power
  • n represents the number of first data information within a preset time period.
  • step S203 dimensionless processing is performed on the first data information to obtain second data information.
  • the historical operating power, historical wet-bulb temperature, historical cooling water temperature difference, historical approximation, and historical cooling water flow in the first data information are respectively divided by the corresponding rated operating power, preset wet-bulb temperature, preset cooling water temperature difference, preset approximation, and preset cooling water flow to obtain the second data information.
  • the value of the historical data information in the first data information is generally smaller than the value of the preset data information. Therefore, the data after dimensionless processing is not only more accurate, but also can enhance the versatility of the first data model and the second data model.
  • step S204 fitting regression processing is performed on the second data information by using the least square method to obtain the first energy consumption model.
  • performing fitting regression processing on the second data information by the least square method may be to determine an approximate function according to the curve obtained by fitting, and then obtain various coefficients of the first energy consumption model.
  • the first energy consumption model includes:
  • P represents the historical operating power
  • Pe represents the rated operating power
  • ⁇ T represents the historical cooling water temperature difference
  • ⁇ T e represents the preset cooling water temperature difference
  • T app represents the historical approximation
  • T app,e represents the preset approximation
  • T wb represents the historical wet-bulb temperature
  • T wb,e represents the preset wet-bulb temperature
  • m cw represents the historical cooling water flow
  • m cw,e represents the preset cooling water flow
  • a, b, c, d, e, r, g, h, i, j, k, l, m, n, and o represent the coefficients of the first energy consumption model.
  • step S103 a target control strategy is determined according to the first operating power of the cooling tower corresponding to each group of control strategies.
  • the target control strategy is the control strategy corresponding to the minimum first operating power in each group of control strategies. Since different control strategies correspond to different energy consumptions under the same working condition, the operating parameters of the cooling tower 106 are controlled by the control strategy corresponding to the minimum design power, which is conducive to reducing the energy consumption of the cooling tower 106 during operation and achieving energy saving.
  • step S104 a target operating frequency of the cooling tower is determined according to the first operating power and the second energy consumption model corresponding to the target control strategy.
  • the method for acquiring the second energy consumption model includes step S301.
  • step S301 the rated operating frequency corresponding to the historical operating frequency corresponding to the second data information within the preset time length is obtained, and the historical operating power, the historical operating power, the rated operating power, and the rated operating frequency corresponding to the second data information are fitted and regressed by the least squares method to obtain a second energy consumption model.
  • the second energy consumption model includes:
  • P represents the historical operating power
  • Pe represents the rated operating power
  • f represents the target operating frequency of the cooling tower
  • fe represents the rated operating frequency of the cooling tower
  • A, B, and C represent the coefficients of the second energy consumption model.
  • the various coefficients of the second energy consumption model are obtained by the controller 40 performing fitting regression processing on the historical operating power, historical operating power, rated operating power, and rated operating frequency in the second data information through the least square method.
  • the method for determining the various coefficients of the second energy consumption model is the same as the method for determining the various coefficients of the first energy consumption model, and will not be repeated here.
  • step S105 the cooling tower 106 is controlled to operate according to the target control strategy and the target operating frequency.
  • the energy consumption of the cooling tower 106 may change when the outdoor dry bulb temperature and outdoor relative humidity change, or when the cooling water temperature difference, cooling water flow rate and approach of the cooling tower change.
  • the first operating power of the cooling tower 106 corresponding to the various control strategies under the current working condition can be calculated.
  • the various first operating powers can reflect the energy consumption of the cooling tower 106 corresponding to each control strategy under the current working condition.
  • the control strategy corresponding to the minimum first operating power has the lowest energy consumption of the cooling tower 106. Therefore, the control strategy corresponding to the minimum design power can be used as the target control strategy, and the target operating power can be determined based on the minimum first operating power and the second energy consumption model.
  • controlling the operation of the cooling tower 106 (such as controlling multiple operating parameters of the cooling tower 106) according to the target control strategy and the target operating frequency is beneficial to reducing the energy consumption of the cooling tower 106 under the current operating conditions, thereby achieving energy saving.
  • the air conditioning system 1 includes four cooling towers 106.
  • the control method of the air conditioning system includes steps S1 to S8.
  • step S1 historical data information of four cooling towers within one year is obtained, and the historical data information includes historical wet-bulb temperature (e.g., historical wet-bulb temperature is determined by historical outdoor dry-bulb temperature and historical outdoor relative humidity), historical cooling water temperature difference, historical approximation, historical cooling water flow, historical operation frequency, historical operation power, and rated operation power (e.g., 7.5kw), preset cooling water temperature difference (e.g., 5°C), and preset cooling water flow (e.g., 303m3 /h) of each cooling tower under corresponding working conditions.
  • historical wet-bulb temperature e.g., historical wet-bulb temperature is determined by historical outdoor dry-bulb temperature and historical outdoor relative humidity
  • historical cooling water temperature difference e.g., historical approximation, historical cooling water flow, historical operation frequency, historical operation power, and rated operation power (e.g., 7.5kw)
  • preset cooling water temperature difference e.g., 5°C
  • the historical data information includes data information of the cooling tower 106 at each time period in a year.
  • step S2 the historical data information within the above one year is processed to obtain first data information.
  • processing the historical data information within the above one year includes: removing the historical data information with abnormalities in the historical operating frequency of the cooling tower 106, and removing the historical data information with abnormalities in the historical operating power of the cooling tower. For example, removing the historical data information corresponding to the historical operating frequency greater than 50Hz or the historical operating frequency less than 30Hz, and removing the historical data information corresponding to the historical operating power within The historical data information within the interval is removed.
  • step S3 the processed first data information is dimensionally non-dimensionalized, and then a fitting regression process is performed on the dimensionally non-dimensionalized data information by a least square method to obtain coefficients of a first energy consumption model, and further obtain the first energy consumption model.
  • the rated operating power ratio and the historical operating power ratio of the cooling tower 106 under multiple historical operating conditions are generally positively correlated.
  • the historical operating power ratio increases.
  • the rated operating power and the historical operating power of the cooling tower 106 under multiple historical operating conditions are generally positively correlated.
  • the historical operating power increases.
  • the fitting results of the first energy consumption model are shown in Table 1:
  • R 2 is the coefficient of determination, also known as goodness of fit. The closer the value of R 2 is to 1, the higher the goodness of fit of the model.
  • step S4 the historical operating power, historical operating power, rated operating power, and rated operating frequency in the second data information are fitted and regressed by the least squares method to obtain coefficients of the second energy consumption model, thereby obtaining the second energy consumption model.
  • the historical operating power ratio there is a generally positive correlation between the historical operating power ratio and the historical operating frequency ratio of the cooling tower 106 under a plurality of historical operating conditions.
  • the historical operating frequency ratio increases.
  • step S5 based on the currently detected outdoor dry-bulb temperature (such as 27°C) and the current outdoor relative humidity, the calculated wet-bulb temperature is 24°C, and by setting multiple groups of control strategies (including multiple groups of different design cooling water temperature differences, design cooling water flow rates and first approximations), multiple first operating powers of the cooling tower under the current operating conditions and different control strategies are calculated according to the first energy consumption model.
  • the currently detected outdoor dry-bulb temperature such as 27°C
  • the calculated wet-bulb temperature is 24°C
  • multiple groups of control strategies including multiple groups of different design cooling water temperature differences, design cooling water flow rates and first approximations
  • the fitting results of the second energy consumption model are shown in Table 2:
  • step S6 energy consumption is sorted according to the magnitudes of a plurality of first operating powers under different control strategies under the current working condition.
  • the total cooling energy consumption of the four cooling towers 106 is roughly negatively correlated with the number of control strategies. As the total energy consumption increases, the number of control strategies decreases.
  • a target control strategy is determined according to the above-mentioned multiple first operating powers, where the target control strategy is the control strategy corresponding to the smallest first operating power in each group of control strategies.
  • step S7 a target operating frequency corresponding to the target operating power is determined by using a second energy consumption model.
  • the target operating frequency and related data are shown in Table 3:
  • step S8 the four cooling towers 106 are controlled to operate at the target operating frequency (ie, 32 Hz).
  • cooling towers can be controlled to operate according to the same target control strategy and the same target operating frequency (eg, 32 Hz).
  • control method of the air conditioning system controls the operation of multiple cooling towers 106 (such as controlling multiple operating parameters of the cooling tower 106) through the target control strategy and the target operating frequency, which is conducive to reducing the energy consumption of the cooling tower 106 under the current working conditions, thereby achieving energy saving.
  • multiple air conditioning devices i.e., the chiller 101
  • the control method of the air conditioning system controls the operation of multiple cooling towers 106 (such as controlling multiple operating parameters of the cooling tower 106) through the target control strategy and the target operating frequency, which is conducive to reducing the energy consumption of the cooling tower 106 under the current working conditions, thereby achieving energy saving.
  • the air conditioning system 1 may be a chiller system, and the air conditioning device may also be referred to as a chiller 101.
  • Fig. 7 is a block diagram of another air conditioning system according to some embodiments.
  • the air conditioning system 1 includes a plurality of air conditioning devices and a controller 40.
  • the plurality of air conditioning devices and the controller 40 are arranged in a target room.
  • the plurality of air conditioning devices include air conditioning device 11, air conditioning device 12, ..., air conditioning device n, and the like.
  • the target room may be an office room, a residential room, or a room in a large commercial building, which is not limited in the present disclosure.
  • the controller 40 is configured to generate an operation control signal according to the instruction operation code and the timing signal, and instruct the air conditioning system 1 to execute the control instruction.
  • the controller 40 is configured to: obtain the total predicted cooling load value of the air-conditioning system 1 at the predicted time according to the outdoor temperature, outdoor relative humidity and total actual cooling load value of the air-conditioning system 1 at the historical time; obtain the total energy efficiency ratio corresponding to any start-up mode of the air-conditioning system (for example, including at least one air-conditioning device being turned on) according to the total predicted cooling load value and the operating power of each air-conditioning device; and obtain the target start-up mode, and use the target start-up mode as the start-up mode of the air-conditioning system 1 at the predicted time.
  • the target start-up mode is the start-up mode corresponding to the maximum total energy efficiency ratio among the total energy efficiency ratios corresponding to the air-conditioning system 1 under the multiple start-up modes.
  • FIG8 is a block diagram of an air conditioning device according to some embodiments.
  • the air conditioning device includes one or more of a control component 120, a sensor component 130, a communication component 140, and a power supply 150.
  • the sensor component 130, the communication component 140, and the power supply 150 are all connected to the control component 120.
  • control component 120 is configured to generate an operation control signal according to the instruction operation code and the timing signal to instruct the air conditioning device to execute the control instruction.
  • the sensor assembly 130 includes a temperature sensor and a humidity sensor.
  • the control assembly 120 is further configured to control the temperature sensor to obtain the outdoor temperature, chilled water supply temperature, cooling water return temperature at a historical moment, and control the humidity sensor to obtain the outdoor relative humidity.
  • the communication component 140 is a component for communicating with an external device or server according to various communication protocol types.
  • the communication component 140 includes a wireless communication technology (Wi-Fi) component, a Bluetooth component, a wired Ethernet component, a near field communication technology (NFC) component, and other network communication protocol chips or near field communication protocol chips, and at least one of an infrared receiver.
  • the communication component 140 is configured to communicate with other devices or communication networks (such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.).
  • RAN radio access network
  • WLAN wireless local area networks
  • the power supply 150 is configured to provide operating power support for various electrical components of the air conditioning device under the control of the control component 120.
  • the power supply 150 may include a battery and related control circuits.
  • the controller 40 is further configured to: before obtaining the total predicted cooling load value of the air-conditioning system 1 at the predicted time, establish an energy efficiency ratio prediction model corresponding to the air-conditioning system 1 according to the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of the air-conditioning system 1 at the historical time; based on the energy efficiency ratio prediction model corresponding to the air-conditioning system 1, input the chilled water supply temperature of the air-conditioning system 1, and calculate the actual energy efficiency ratio of the cooling load rate ...
  • the total predicted energy efficiency ratio of the air conditioning system is obtained by using the water temperature, cooling water return temperature, and cooling load rate; and the total actual cooling load value of the air conditioning system is obtained based on the total predicted energy efficiency ratio and operating power of the air conditioning system. In this way, the air conditioning system can be optimized and controlled to reduce the operating energy consumption of the air conditioning system.
  • the controller 40 is also configured to: after obtaining the total predicted cooling load value of the air-conditioning system 1 at the predicted time, use the total predicted energy efficiency ratio of the air-conditioning system 1 as the objective function, and use the differential evolution algorithm to determine the load rate distribution value of each air-conditioning equipment at the predicted time according to the chilled water supply temperature, the cooling water return temperature and the total predicted cooling load value.
  • differential evolution algorithm is a population-based evolutionary algorithm that can simulate the process of cooperation and competition among individuals in a population, including selection, crossover, and mutation operations.
  • the differential evolution algorithm is a mature global optimization method with high robustness and wide applicability.
  • the target load rate distribution value for each air-conditioning device can be obtained, thereby realizing the optimal control of the air-conditioning system and reducing the operating energy consumption of the air-conditioning system.
  • the controller 40 is further configured to: obtain the cooling load value allocated to each air-conditioning device according to the load rate allocation value; and obtain the optimized cooling water supply temperature value of each air-conditioning device according to the specific heat capacity of water, the chilled water flow rate and cooling water return temperature of each air-conditioning device, and the allocated cooling load value of each air-conditioning device. In this way, the air-conditioning system can be optimized and the operating energy consumption of the air-conditioning system can be reduced.
  • the method of obtaining the total predicted cooling load value of the air-conditioning system 1 at the predicted moment based on the outdoor temperature, outdoor relative humidity and total actual cooling load value of the air-conditioning system at the historical moment includes: based on the first back-propagation neural network model, inputting the outdoor temperature, outdoor relative humidity and total actual cooling load value at the first historical moment, outputting the total cooling load value at the current moment, and establishing a second back-propagation neural network model for predicting the cooling load value; and, based on the second back-propagation neural network model, inputting the outdoor temperature, outdoor relative humidity and total actual cooling load value at the second historical moment, and obtaining the output total predicted cooling load value at the predicted moment.
  • control method of the air-conditioning system provided by some embodiments of the present disclosure can obtain the total predicted cooling load value of the air-conditioning system at the next moment in advance, and actively adjust and control the water supply temperature and the opening method of the air-conditioning system a certain time in advance before the next moment arrives, thereby realizing optimized control of the air-conditioning system and reducing the operating energy consumption of the air-conditioning system.
  • the controller 40 is further configured to: after obtaining the start-up mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio as the start-up mode of the air-conditioning system at the predicted time, obtain the average cooling load value of the air-conditioning system within a preset time period before the predicted time; when the cooling load rate of the air-conditioning system is less than the preset load rate, determine whether the chilled water supply temperature value is less than the first preset temperature value; when the chilled water supply temperature value is less than or equal to the first preset temperature value, determine whether the average cooling load value is less than the preset multiple of the second cooling capacity; when the average cooling load value is greater than the preset multiple of the second cooling capacity, turn on the air-conditioning equipment corresponding to the second cooling capacity, and turn off
  • the air-conditioning device corresponding to the first cooling capacity is turned off; the second cooling capacity is less than the first cooling capacity; when the average cooling load value is less than or equal to the preset multiple of the second cooling capacity, it is determined whether the second energy
  • the controller 40 is further configured to: determine whether the chilled water supply temperature value is greater than or equal to a second preset temperature value; when the chilled water supply temperature value is greater than or equal to the second preset temperature value, determine whether the average cooling load value is less than a preset multiple of the first cooling capacity; the second preset temperature value is greater than the first preset temperature value; when the average cooling load value is greater than the preset multiple of the first cooling capacity, turn on the air-conditioning equipment corresponding to the second cooling capacity; when the average cooling load value is less than or equal to the preset multiple of the first cooling capacity, determine whether the second energy efficiency ratio is greater than or equal to the first energy efficiency ratio; when the second energy efficiency ratio is greater than or equal to the first energy efficiency ratio, turn on the air-conditioning equipment corresponding to the second energy efficiency ratio; when the second energy efficiency ratio is less than the first energy efficiency ratio, turn on the air-conditioning equipment corresponding to the first energy efficiency ratio.
  • the controller 40 needs to control the multiple air-conditioning devices to work in turn to achieve the best cooling load rate distribution among the multiple air-conditioning devices.
  • air conditioning equipment consumes a lot of energy during the start-up and stop process. Frequent start-up and stop will lead to energy waste. Therefore, when there are too many air conditioning equipment, reducing the number of air conditioning equipment will help improve energy utilization efficiency and optimize the control of the air conditioning system.
  • the controller 40 is also configured to: when the chilled water supply temperature value is greater than the first preset temperature value and less than the second preset temperature value, maintain the target opening mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio as the opening mode of the air-conditioning system at the predicted moment.
  • FIG. 9 is a flow chart of another method for controlling an air conditioning system according to some embodiments.
  • some embodiments of the present disclosure further provide another air-conditioning system control method, which includes steps S11 to S13 .
  • step S11 the total predicted cooling load value of the air-conditioning system at the predicted time is obtained according to the outdoor temperature, outdoor relative humidity and the total actual cooling load value of the air-conditioning system at the historical time.
  • the outdoor temperature is obtained by a temperature sensor
  • the outdoor relative humidity is obtained by a humidity sensor
  • the total predicted cooling load value of the air-conditioning system at the predicted time can be obtained by calculation and prediction based on a back propagation (BP) neural network model.
  • BP back propagation
  • the back propagation neural network model is the BP neural network structure.
  • the BP neural network is a multi-layer feedforward neural network trained according to the error back propagation algorithm.
  • the BP neural network model is a commonly used and effective model for modeling nonlinear, non-periodic, irregular, unstructured or semi-structured data.
  • the BP neural network model can be established in combination with data mining and has the characteristics of a time series. Predicting the cooling load value of the air-conditioning system through the BP neural network model is conducive to improving the efficiency, accuracy and reliability of the prediction.
  • step S12 the total energy efficiency ratio corresponding to the air-conditioning system in any start-up mode is obtained according to the total predicted cooling load value and the operating power of each air-conditioning device.
  • the activation method includes at least one air conditioning device being activated.
  • the air conditioning system 1 includes the air conditioning device 11, the air conditioning device 12, and the air conditioning device 13, the activation method includes: any one of the air conditioning devices 11, 12, and 13 being activated, any two of them being activated, or all of them being activated.
  • the total energy efficiency ratio of the air conditioning system in any startup mode can be obtained using formula (4):
  • COP represents the total energy efficiency ratio of the air-conditioning system
  • Qpre represents the total predicted cooling load value
  • Pi represents the operating power of the i-th air-conditioning equipment
  • Qi represents the cooling load value borne by the i-th air-conditioning equipment
  • COPi represents the energy efficiency ratio of the i-th air-conditioning equipment
  • n represents the number of air-conditioning equipment turned on.
  • step S13 a target opening mode is obtained, and the target opening mode is used as the opening mode of the air-conditioning system at the predicted time.
  • the target activation mode is an activation mode corresponding to the maximum total energy efficiency ratio among the total energy efficiency ratios corresponding to the air-conditioning system 1 under the multiple activation modes.
  • the Coefficient of Performance also known as the refrigeration performance coefficient
  • the refrigeration performance coefficient refers to the ratio of the cooling capacity of the air-conditioning system to the power consumed under certain working conditions, that is, the cooling capacity obtained by consuming unit power. Therefore, COP represents the energy utilization efficiency of the air-conditioning system.
  • the controller 40 obtains the total predicted cooling load value of the air-conditioning system at the predicted time according to the outdoor temperature, outdoor relative humidity and total actual cooling load value of the air-conditioning system at the historical time, and then obtains the corresponding total energy efficiency ratio under any start-up mode of the air-conditioning system according to the total predicted cooling load value and the operating power of each air-conditioning device. Since the larger the energy efficiency ratio, the more electric energy is saved, therefore, the target start-up mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio is used as the start-up mode of the air-conditioning system at the predicted time, so as to realize the optimized control of the air-conditioning system and reduce the operating energy consumption of the air-conditioning system.
  • FIG. 10 is a flowchart of yet another method for controlling an air conditioning system according to some embodiments.
  • step S11 includes steps S111 and S112 .
  • step S111 based on the first back propagation neural network model, the outdoor temperature, outdoor relative humidity and total actual cooling load value at the first historical moment are input, the total cooling load value at the current moment is output, and a second back propagation neural network model for predicting the cooling load value is established.
  • the back propagation neural network model is trained using multiple parameters such as the outdoor temperature, outdoor relative humidity, and total actual cooling load value at a first historical moment, as well as the total cooling load value at a current moment, thereby establishing a second back propagation neural network model for predicting cooling load values.
  • Fig. 11 is a structural diagram of a neural network for predicting cooling load values according to some embodiments.
  • the back propagation neural network model is shown in Fig. 11 .
  • the outdoor temperature one hour before the current moment, the outdoor relative humidity one hour before the current moment, the total cooling load value at the corresponding moment of the previous twenty-four hours, the total cooling load value of the previous three hours, the total cooling load value of the previous two hours, and the total cooling load value of the previous hour are used as The input layer of the BP neural network model, that is, there are six input layers in total.
  • the number of hidden layer nodes is fourteen.
  • the output layer is the training target value, and the target value is the total cooling load value of the air-conditioning system at the current moment, so that the second back propagation neural network model for predicting the cooling load value can be established through the above data training.
  • step S112 based on the second back propagation neural network model, the outdoor temperature, outdoor relative humidity and total actual cooling load value at the second historical moment are input to obtain the total predicted cooling load value at the output predicted moment.
  • the next moment after the current moment is taken as the prediction moment, and the total predicted cooling load value at the prediction moment is obtained.
  • the outdoor temperature one hour before the prediction time, the outdoor relative humidity one hour before the prediction time, the total cooling load value of the twenty-four hours before the prediction time, the total cooling load value of the three hours before the prediction time, the total cooling load value of the two hours before the prediction time, and the total cooling load value of the hour before the prediction time can be used as the input layer of the Bp neural network model, that is, the input layer has a total of six layers; the number of hidden layer nodes is fourteen layers; the output layer is the training target value, and the target value is the total predicted cooling load value of the air-conditioning system at the prediction time.
  • the relevant technology usually collects the real-time cooling load value of the air-conditioning system, and calculates the most energy-saving cooling load rate of each air-conditioning device based on the cooling load value. Then, the operating parameters of each air-conditioning device are adjusted according to the most energy-saving cooling load rate of each air-conditioning device, thereby realizing the optimal control of the air-conditioning system.
  • this load distribution method requires adjusting the water supply temperature of each air-conditioning device and the way the air-conditioning system is turned on, and the above adjustments need to last for a certain period of time to complete.
  • the process of implementing the target load distribution method calculated at the current moment may take 15 to 30 minutes to adjust the air-conditioning system to an energy-saving operating state.
  • the cooling load value may have changed.
  • control method of the air-conditioning system provided in some embodiments of the present disclosure can obtain the total predicted cooling load value of the air-conditioning system at the next moment in advance, so that the water supply temperature and the opening method of the air-conditioning system can be actively adjusted and controlled a certain time in advance before the next moment arrives, thereby realizing the optimized control of the air-conditioning system and reducing the operating energy consumption of the air-conditioning system.
  • FIG. 12 is a flowchart of yet another method for controlling an air conditioning system according to some embodiments.
  • control method of the air-conditioning system before obtaining the total predicted cooling load value of the air-conditioning system at the predicted time, the control method of the air-conditioning system further includes steps S21 to S23 .
  • step S21 an energy efficiency ratio prediction model corresponding to the air conditioning system is established according to the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of the air conditioning system at historical moments.
  • the energy efficiency ratio prediction model corresponding to the air conditioning system can be established using formula (5):
  • PLR represents the load rate of the air-conditioning system
  • Tchw,s represents the chilled water supply temperature, in °C
  • Tcw ,r represents the cooling water return temperature, in °C
  • A, B, C, D, E, F, G, H, I, and J represent the chiller model identification coefficients.
  • the chiller model identification coefficients A, B, C, D, E, F, G, H, I, J in formula (5) are obtained, thereby establishing the energy efficiency ratio prediction model corresponding to the air-conditioning system. And use a large amount of historical data to train the above energy efficiency prediction model.
  • an energy efficiency ratio prediction model corresponding to each air-conditioning device is established based on the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of each air-conditioning device at a historical moment.
  • step S22 based on the energy efficiency ratio prediction model corresponding to the air-conditioning system, the chilled water supply temperature, the cooling water return temperature, and the cooling load rate of the air-conditioning system are input to obtain the total predicted energy efficiency ratio of the air-conditioning system.
  • the above formula (5) can be used to input the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of the air-conditioning system at the predicted time, so as to obtain the total predicted energy efficiency ratio of the air-conditioning system at the predicted time.
  • the chilled water supply temperature, cooling water return temperature, and cooling load rate of each air-conditioning device are input to obtain the predicted energy efficiency ratio of each air-conditioning device, and then the total predicted energy efficiency ratio of the air-conditioning system is obtained.
  • step S23 based on the total predicted energy efficiency ratio and operating power of the air-conditioning system, the total actual cooling load value of the air-conditioning system is obtained.
  • the total actual cooling load value of the air-conditioning system is obtained.
  • the total actual cooling load value of the air conditioning system can be obtained by formula (6):
  • Q represents the actual cooling load value of the building, in kW
  • P represents the measured power of each air-conditioning system, in kW
  • the subscript i represents the i-th air-conditioning system
  • n represents the total number of air-conditioning systems.
  • an energy efficiency ratio prediction model corresponding to the air-conditioning system can be established based on the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of the air-conditioning system at historical moments, so as to obtain the total predicted energy efficiency ratio of the air-conditioning system using the energy efficiency ratio prediction model, and then obtain the total actual cooling load value of the air-conditioning system. According to the total actual cooling load value, the cooling load value of each air-conditioning system is divided, so as to achieve optimal control of the air-conditioning system and reduce the operating energy consumption of the air-conditioning system.
  • FIG. 13 is a flow chart of yet another method for controlling an air conditioning system according to some embodiments.
  • the control method of the air-conditioning system further includes steps S31 to S33 .
  • step S31 the total predicted energy efficiency ratio of the air-conditioning system is used as the objective function, and the load rate distribution value of each air-conditioning device at the predicted time is determined using a differential evolution algorithm according to the chilled water supply temperature, the cooling water return temperature and the total predicted cooling load value.
  • differential evolution algorithm is a population-based evolutionary algorithm that can simulate the process of cooperation and competition among individuals in a population, including selection, crossover, and mutation operations.
  • the differential evolution algorithm is a mature global optimization method with high robustness and wide applicability.
  • the target load rate distribution value for each air-conditioning device can be obtained, thereby realizing the optimal control of the air-conditioning system and reducing the operating energy consumption of the air-conditioning system.
  • the total actual cooling load value of the air conditioning system can be obtained using formula (7):
  • COP max represents the maximum energy efficiency ratio.
  • formula (8) can be used as a constraint condition for obtaining the target load rate distribution value corresponding to each air conditioning device:
  • Q de represents the rated cooling capacity on the nameplate of the chiller, in kW.
  • the differential evolution algorithm includes steps S311 to S316:
  • step S311 the population initialization operation is performed, including: taking each air-conditioning device in the air-conditioning system as a separate population individual, and randomly initializing a D-dimensional parameter vector with a number NP, as shown in formulas (9) and (10).
  • the population number NP is 200.
  • Xi (0) represents the i-th individual
  • j represents the j-th dimension
  • rand (0, 1) represents a random number in the interval [0, 1], and are the lower and upper bounds of the j-th dimension respectively.
  • step S312 fitness calculation is performed, including: taking the total predicted energy efficiency ratio of the air-conditioning system as the objective function, taking the objective function value as the fitness of the individual, and calculating the fitness value of each individual in the initial population.
  • step S313 the termination condition judgment is performed, including: judging whether the maximum number of iterations is reached, or whether the fitness function reaches the expected value. If so, the evolution is terminated and the best individual obtained is output as the target solution; if not, step S314 is executed.
  • step S314 a population mutation operation is performed, including: randomly selecting two different individuals in the population, scaling the vector difference of the different individuals, and then performing vector synthesis with the individual to be mutated.
  • the vector differences of different individuals can be scaled using formula (11) and then synthesized with the vector of the individual to be mutated.
  • V i (g+1) X r1 (g)+F(X r2 (g)-X r3 (g)) (11)
  • r1, r2 and r3 represent three random numbers, and the value interval of the three random numbers is [1, NP]; F represents a scaling factor, and F is a constant; g represents the gth generation.
  • step S315 a population crossover operation is performed, including: generating a random number n (eg, n is any value between 0 and 1), and then using formula (12) to complete the crossover operation.
  • CR is the crossover probability
  • crossover of populations is to generate diverse offspring vectors, enhance the diversity of the population, and promote structural differences in the population.
  • step S316 a target population selection operation is performed, including: comparing the crossover vector with the original vector, and selecting a better individual as a new individual.
  • the target population selection operation can be performed using formula (13).
  • step S32 the cooling load value allocated to each air-conditioning device is obtained according to the load rate allocation value.
  • the differential evolution algorithm can calculate that the optimal cooling load rate distribution value at the next time is that each of the two air-conditioning equipment bears 50% of the cooling load rate, that is, the cooling load values allocated to the two air-conditioning equipment are 703kw each.
  • step S33 the optimized chilled water supply temperature value of each air conditioning device is obtained according to the specific heat capacity of water, the chilled water flow rate and cooling water return temperature of each air conditioning device, and the allocated cooling load value of each air conditioning device.
  • formula (14) can be used to obtain the optimized chilled water supply temperature value of each air conditioning device:
  • c is the specific heat capacity of water, in kJ/(kg ⁇ °C); mi is the chilled water flow rate of the i-th chiller, in m3/s; tr is the return water temperature of the chilled water main, in °C; ts ,i is the chilled water supply temperature of the i-th chiller, in °C.
  • the chilled water supply temperature is related to the power consumption of the air-conditioning system. When the chilled water supply temperature is higher, the power consumption of the air-conditioning system is lower.
  • Some embodiments of the present disclosure provide a control method for an air-conditioning system, which determines the load rate distribution value of each air-conditioning device at a predicted moment through a differential evolution algorithm, and can obtain a target load rate distribution value for each air-conditioning device. Then, according to the load rate distribution value, the target cooling load value allocated to each air-conditioning device is obtained, and then the optimized chilled water supply temperature value of each air-conditioning device is obtained, and the optimized chilled water supply temperature value is set as the chilled water supply temperature value at the next moment, so that the air-conditioning system can be optimized and controlled, and the operating energy consumption of the air-conditioning system can be reduced.
  • FIG. 14 is a flowchart of yet another method for controlling an air conditioning system according to some embodiments.
  • control method of the air conditioning equipment further includes steps S801 to S805 .
  • step S801 the total energy efficiency ratio corresponding to any start-up mode of the air-conditioning system is obtained.
  • obtaining the total energy efficiency ratio corresponding to any startup mode of the air-conditioning system includes obtaining the energy efficiency ratio of a single air-conditioning device in operation, and obtaining the energy efficiency ratio of a combination of at least two air-conditioning devices in operation.
  • step S802 the start-up mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio is determined.
  • step S803 it is determined whether the air-conditioning system needs to increase or decrease air-conditioning equipment. If so, step S804 is executed; if not, step S805 is executed.
  • step S804 air-conditioning equipment in the air-conditioning system is increased or decreased.
  • the air-conditioning equipment in the air-conditioning system can be increased or decreased by increasing or decreasing the air-conditioning equipment in the air-conditioning system to reduce the frequent start and stop of the air-conditioning equipment in the air-conditioning system, thereby helping to extend the service life of the air-conditioning system.
  • step S805 the start-up mode corresponding to the maximum total energy efficiency ratio is used as the start-up mode at the next moment.
  • Fig. 15 is a flow chart of another method for controlling an air conditioning system according to some embodiments. As shown in Fig. 15, the method for reducing air conditioning equipment in the air conditioning system includes steps S41 to S46.
  • step S41 the average cooling load value of the air-conditioning system within a preset time period before the prediction time is obtained.
  • step S42 when the cooling load rate of the air-conditioning system is less than the preset load rate, it is determined whether the chilled water supply temperature value is less than or equal to the first preset temperature value.
  • the preset load rate is the lower limit of the load rate for the operation of the air-conditioning system.
  • step S43 when the chilled water supply temperature is less than or equal to the first preset temperature, it is determined whether the average cooling load is less than a preset multiple of the second cooling capacity; if so, step S44 is executed, and if not, step S46 is executed.
  • the preset multiple is set to 1.1.
  • step S44 it is determined whether the second energy efficiency ratio is greater than or equal to the first energy efficiency ratio; if so, step S46 is executed; if not, step S45 is executed.
  • the air conditioning device corresponding to the first energy efficiency ratio is the air conditioning device corresponding to the first cooling capacity
  • the air conditioning device corresponding to the second energy efficiency ratio is the air conditioning device corresponding to the second cooling capacity
  • step S45 the air conditioning device corresponding to the first energy efficiency ratio is turned on, and the air conditioning device corresponding to the second energy efficiency ratio is turned off.
  • step S46 the air conditioning device corresponding to the second energy efficiency ratio is turned on, and the air conditioning device corresponding to the first energy efficiency ratio is turned off.
  • the controller 40 needs to control the multiple air-conditioning devices to work in turn to achieve the best cooling load rate distribution among the multiple air-conditioning devices.
  • air conditioning equipment consumes a lot of energy during the start-up and stop process. Frequent start-up and stop will lead to energy waste. Therefore, when there are too many air conditioning equipment, reducing the number of air conditioning equipment will help improve energy utilization efficiency and optimize the control of the air conditioning system.
  • Fig. 16 is a flow chart of another control method of an air conditioning system according to some embodiments. As shown in Fig. 16, the method of adding an air conditioning device in the air conditioning system includes step S41, and steps S51 to S55.
  • step S41 the average cooling load value of the air-conditioning system within a preset time period before the prediction time is obtained.
  • step S51 it is determined whether the chilled water supply temperature is greater than or equal to a second preset temperature value.
  • step S52 when the chilled water supply temperature value is greater than or equal to the second preset temperature value, determine whether the average cooling load value is less than the preset multiple of the first cooling capacity; if so, execute step S53, if not, execute step S55.
  • the second preset temperature value is greater than the first preset temperature value.
  • the second preset temperature value is the first preset temperature value plus 1.5 degrees Celsius.
  • step S53 it is determined whether the second energy efficiency ratio is greater than or equal to the first energy efficiency ratio; if so, step S55 is executed; if not, step S54 is executed.
  • step S54 the air conditioning device corresponding to the first energy efficiency ratio is turned on.
  • step S55 the air conditioning device corresponding to the second energy efficiency ratio is turned on.
  • control method further includes a method for starting the air-conditioning system corresponding to maintaining the maximum total energy efficiency ratio, and the method for starting the air-conditioning system corresponding to maintaining the maximum total energy efficiency ratio includes step S61.
  • step S61 when the chilled water supply temperature is greater than the first preset temperature value and less than the second preset temperature value, the target start-up mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio is maintained as the start-up mode of the air-conditioning system at the predicted time.
  • the target opening mode of the air-conditioning system corresponding to the maximum total energy efficiency ratio in step S13 is maintained as the opening mode of the air-conditioning system at the predicted time.
  • control scheme of the air-conditioning system startup method can be implemented according to steps S41 to S46, steps S51 to S55, and step S61, thereby realizing feedforward control and energy-saving operation of the air-conditioning system.
  • FIG. 17 is a flow chart of a method for controlling a chiller system according to some embodiments.
  • the air conditioning system is a chiller system, and the chiller system includes a plurality of chillers (ie, air conditioning equipment).
  • the advance optimization control method of the chiller system will be described in detail by taking the air conditioning system as a chiller system as an example in conjunction with Fig. 17.
  • the advance optimization control method includes steps S71 to S75.
  • step S71 the total actual cooling load value is obtained.
  • step S71 is performed.
  • step S72 a Bp neural network model is established to obtain the total predicted cooling load value for the next hour.
  • step S72 may be performed according to steps S111 to S113.
  • step S73 based on the current chilled water supply temperature, cooling water return temperature, and the total predicted cooling load value for the next hour, a differential evolution algorithm is used to determine the load rate distribution value for each chiller for the next hour.
  • step S73 may be performed with reference to step S31.
  • step S74 the optimized chilled water supply temperature value of each chiller is obtained according to the load rate distribution value.
  • step S74 may be performed with reference to steps S32 to S33.
  • step S75 the number of chillers is optimized.
  • optimizing the number of chillers includes: obtaining the total energy efficiency ratio corresponding to any start-up mode of the chiller system, using the start-up mode of the chiller system corresponding to the maximum total energy efficiency ratio as the best start-up mode of the chiller system for the next hour; and sending optimization control instructions 5 minutes before the next hour.
  • step S75 chilled water may be increased or chillers in the chiller system may be decreased by executing steps S401 to S406, steps S501 to S505, and step S601.
  • steps S73 and S74 can be repeated to find the optimal load rate distribution method and reset the water supply temperature of each chiller.
  • the advance optimization control method obtains the total predicted cooling load value of the chiller system at the predicted time according to the outdoor temperature, outdoor relative humidity and total actual cooling load value of the chiller system at the historical time, and then obtains the total energy efficiency ratio corresponding to any start-up mode of the chiller system according to the total predicted cooling load value and the operating power of each chiller. Since the energy efficiency ratio is the ratio of energy conversion efficiency, the larger the energy efficiency ratio, the more electric energy is saved, so the target start-up mode of the chiller system corresponding to the maximum total energy efficiency ratio is used as the start-up mode of the chiller system at the predicted time.
  • the frequent start and stop of the chiller can be reduced, thereby increasing the service life of the chiller system, and realizing feedforward optimization control of the chiller system, thereby reducing the operating energy consumption of the chiller system.
  • the refrigeration room system includes three chillers, two of which are 500RT variable frequency centrifugal chillers, and the other is a 400RT variable frequency centrifugal chiller.
  • the control method of the air conditioning system includes steps S81 to S85.
  • step S81 the total predicted cooling load value is obtained.
  • step S81 includes steps S811 to S813.
  • step S811 according to the chilled water supply temperature, cooling water return temperature, cooling load rate and actual energy efficiency ratio of the chiller system at the historical moment, and the above formula (5), the energy efficiency ratio prediction model corresponding to the chiller system is established, and the above energy efficiency prediction model is trained using a large amount of historical data to obtain the model identification coefficients of the three chillers.
  • the model fitting results of the first chiller (500RT) include: A is -4.74375, B is 0.02529, C is -0.00001, D is -0.02952, E is -0.14628, F is 0.02047, G is 12.21102, H is -0.80367, I is -0.18150, and J is 8.11102.
  • the model fitting results for the second chiller (500RT) include: A is -9.20506, B is 0.04685, C is 0.00245, D is 0.25566, E is -0.27021, F is -0.00483, G is 20.15267, H is -0.62736, I is -0.11550, and J is 0.86570.
  • the model fitting results of the second chiller (400RT) include: A is -9.20506, B is 0.04685, C is 0.00245, D is 0.25566, E is -0.27021, F is -0.00483, G is 20.15267, H is -0.62736, I is -0.11550, and J is 0.86570.
  • step S812 based on the model identification coefficients of the above three chillers, using formula (5), the chilled water supply temperature, cooling water return temperature, and cooling load rate of each chiller are input to obtain the predicted energy efficiency ratio of each chiller.
  • step S813 the operating power of each chiller is measured, and the actual cooling load value of each chiller is calculated based on the relationship between the predicted energy efficiency ratio and the operating power of each chiller using formula (6), and finally the total actual cooling load value of the building can be determined.
  • step S82 based on the Bp neural network model, the total predicted cooling load value at the predicted time is obtained.
  • step S82 includes step S821 and step S822.
  • step S821 a target Bp neural network model is established and trained.
  • the training data sets (such as: outdoor temperature in the previous hour, outdoor relative humidity in the previous hour, total cooling load value at the corresponding time of the previous 24 hours, total cooling load value in the previous 3 hours, total cooling load value in the previous 2 hours, and total cooling load value in the previous hour) are used as the input layer of the Bp neural network model, that is, the input layer has six layers; the number of hidden layer nodes is fourteen layers; the output layer is the training target value, and the target value is the total cooling load value of the chiller system at the corresponding time, and the second back propagation neural network model for predicting the cooling load value is obtained through training.
  • the historical data of 01:00:00, 02:00:00, 03:00:0, 04:00:00, 05:00:00 on the typical meteorological day July 25, and 20:00:00, 21:00:00, 22:00:00, 23:00:0, 24:00:00 on the typical meteorological day September 30 are obtained as test data sets.
  • the second back propagation neural network model is trained.
  • the outdoor temperature in the previous hour, the outdoor relative humidity in the previous hour, the total cooling load value at the corresponding time of the previous 24 hours, the total cooling load value in the previous 3 hours, the total cooling load value in the previous 2 hours, and the total cooling load value in the previous hour are used as the input layer of the Bp neural network model, that is, the input layer has six layers; the number of hidden layer nodes is fourteen layers; the output layer is the test target value, and the target value is the total cooling load value of the chiller system at the corresponding time.
  • the total predicted cooling load value at the predicted time is obtained.
  • a prediction is made for the entire day from August 26 to August 31, and the outdoor temperature one hour before the prediction time, the outdoor relative humidity one hour before the prediction time, the total cooling load value 24 hours before the prediction time, the total cooling load value three hours before the prediction time, the total cooling load value two hours before the prediction time, and the total cooling load value one hour before the prediction time are used as the input layer of the BP neural network model, that is, the input layer has six layers in total; the number of hidden layer nodes is fourteen layers; the output layer is the training target value, and the target value is the total predicted cooling load value of the chiller system at the prediction time.
  • step S83 an optimized chiller load rate distribution method is solved based on a differential evolution algorithm.
  • the differential evolution algorithm is used to determine the load rate distribution value of each air-conditioning equipment at the prediction time according to the chilled water supply temperature, cooling water return temperature and the total predicted cooling load value.
  • the optimal load rate value of each chiller in the next hour can be calculated by using the differential evolution algorithm to solve formula (7) corresponding to the objective function and formula (8) corresponding to the constraint condition.
  • the load rate distribution ratio of the two 500RT chillers is equal, and the performance of the 500RT chiller is higher than that of the 400RT chiller, so the 500RT chiller is the main unit and the 400RT chiller is used as a cooling supplement unit.
  • step S84 the water supply temperature of the chiller is optimized.
  • the cooling load value allocated to each chiller is obtained. Then, according to the specific heat capacity of water, the chilled water flow rate and cooling water return temperature of each chiller, and the cooling load value allocated to each chiller, the above formula (9) is used to obtain the optimized chilled water supply temperature value of each chiller.
  • step S85 the control method for the number of chillers is optimized.
  • the optimization setting of the control method for the number of chillers includes: obtaining the total energy efficiency ratio corresponding to any start-up method of the chiller system according to the total predicted cooling load value and the operating power of each air-conditioning device. And taking the target start-up method of the chiller system corresponding to the maximum total energy efficiency ratio as the start-up method of the chiller system at the predicted time.
  • steps S41 to S46, steps S51 to S55, and step S61 are added to determine whether it is necessary to increase or decrease the number of chillers.
  • the energy consumption and energy efficiency of the chiller system and the original energy consumption and energy efficiency of the chiller system without adopting the control method provided by some embodiments of the present disclosure are shown in Table 4. Referring to Table 4, the use of the control method can reduce energy consumption by 6.18%, achieving energy-saving operation of the chiller system.
  • some embodiments of the present disclosure mainly introduce the present disclosure from the perspective of methods.
  • some embodiments of the present disclosure provide hardware structures and/or software modules corresponding to the execution of each function.
  • Those skilled in the art should easily realize that, in combination with the modules and algorithm steps of each example described in some embodiments of the present disclosure, some embodiments of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.
  • Some embodiments of the present disclosure may divide the controller 40 into functional modules according to the above method examples. For example, each function may be divided into functional modules, or two or more functions may be integrated into one processing module.
  • the above integrated modules may be implemented in the form of hardware or in the form of software functional modules. It is understood that in some embodiments of the present disclosure, the division of modules is schematic and is only a logical function division, and there may be other division methods in the current implementation.
  • FIG6 is a block diagram of another controller according to some embodiments.
  • the controller 40 includes a processor 401.
  • the controller 40 also includes a memory 402 and a communication interface 403 connected to the processor 401.
  • the processor 401, the memory 402 and the communication interface 403 are connected via a bus 404.
  • processor 401 can be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), etc.
  • CPU central processing unit
  • NP network processor
  • DSP digital signal processor
  • the memory 402 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, and the present disclosure is not limited to this.
  • ROM read-only memory
  • RAM random access memory
  • the communication interface 403 is configured to communicate with other devices or communication networks (such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
  • other devices or communication networks such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
  • bus 404 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • Bus 404 may be divided into an address bus, a data bus, a control bus, etc.
  • FIG6 only uses one thick line, but does not mean that there is only one bus or one type of bus.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • Chemical & Material Sciences (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

提供一种空调系统，包括冷却塔、冷水机组和控制器。所述控制器被配置为：获取所述冷却塔的当前工况以及所述当前工况下的多组控制策略；所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度；根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，所述多组控制策略对应的所述冷却塔的第一运行功率；根据所述多组控制策略对应的所述冷却塔的第一运行功率，确定目标控制策略；其中，所述目标控制策略为所述多组控制策略中，与最小的所述冷却塔的第一运行功率相对应的控制策略；根据所述最小的所述冷却塔的第一运行功率和第二能耗模型，确定所述冷却塔的目标运行频率；以及控制所述冷却塔按照所述目标控制策略和所述目标运行频率运行。

Description

空调系统及其控制方法
本申请要求于2023年2月22日提交的、申请号为202310155043.6的中国专利申请的优先权，以及于2023年1月28日提交的、申请号为202310078863.X的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及空调技术领域，尤其涉及一种空调系统及其控制方法。
背景技术
随着社会经济的发展，人们的生活水平越来越高，空调系统在日常生活中的应用日益广泛。空调系统包括中央空调系统和冷水机组系统等。
中央空调系统和冷水机组系统的制冷过程涉及制冷介质的压缩、散热、蒸发和吸热等，制冷介质在制冷回路中循环流动，以吸收室内空气中的热量并降低室内空气的温度，从而实现制冷循环。
发明内容
一方面，提供一种空调系统，包括冷却塔、冷水机组和控制器。所述冷却塔被配置为协助冷却水降温。所述冷水机组包括冷凝器。所述冷凝器与所述冷却塔构成冷却水回路，所述冷却水在所述冷却水回路中循环。所述控制器与所述冷却塔和所述冷水机组电连接，所述控制器被配置为：获取所述冷却塔的当前工况以及所述当前工况下的多组控制策略；其中，所述当前工况通过当前的室外干球温度和当前的室外相对湿度确定；所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度；根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，所述多组控制策略对应的所述冷却塔的第一运行功率；其中，所述第一能耗模型用于表征所述冷却塔的第一运行功率与所述控制策略之间的关系；根据所述多组控制策略对应的所述冷却塔的第一运行功率，确定目标控制策略；其中，所述目标控制策略为所述多组控制策略中，与最小的所述冷却塔的第一运行功率相对应的控制策略；根据所述最小的所述冷却塔的第一运行功率和第二能耗模型，确定所述冷却塔的目标运行频率；其中，所述第二能耗模型用于表征所述冷却塔的第一运行功率与所述目标运行频率之间的关系；以及控制所述冷却塔按照所述目标控制策略和所述目标运行频率运行。
另一方面，提供一种空调系统的控制方法，所述空调系统包括冷却塔和冷水机组。所述冷却塔被配置为协助冷却水降温。所述冷水机组包括冷凝器；所述冷凝器与所述冷却塔构成冷却水回路，所述冷却水在所述冷却水回路中循环。所述方法包括：获取所述冷却塔的当前工况以及所述当前工况下的多组控制策略；其中，所述当前工况通过当前的室外干球温度和当前的室外相对湿度确定；所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度；根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，所述多组控制策略对应的所述冷却塔的第一运行功率；其中，所述第一能耗模型用于表征所述冷却塔的第一运行功率与所述控制策略之间的关系；根据所述多组控制策略对应的所述冷却塔的第一运行功率，确定目标控制策略；其中，所述目标控制策略为所述多组控制策略中，与最小的所述冷却塔的第一运行功率相对应的控制策略；根据所述最小的所述冷却塔的第一运行功率和第二能耗模型，确定所述冷却塔的目标运行频率；其中，所述第二能耗模型用于表征所述冷却塔的第一运行功率与所述目标运行频率之间的关系；以及控制所述冷却塔按照所述目标控制策略和所述目标运行频率运行。
又一方面，提供另一种空调系统，包括至少两个空调设备和控制器。所述控制器与所述至少两个空调设备电连接。所述控制器被配置为：根据所述空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取所述空调系统在预测时刻下的总预测冷负荷值；根据所述总预测冷负荷值和每个空调设备的运行功率，获取所述空调系统在多种开启方式下对应的总能效比；其中，所述多种开启方式包括所述至少两个空调设备中的至少一个空调设备开启；以及获取目标开启方式，将所述目标开启方式作为所述预测时刻下的所述空调系统的开启方式；其中，所述目标开启方式为所述空调系统在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
又一方面，提供另一种空调系统的控制方法，包括：根据所述空调系统在历史时刻下的室 外温度、室外相对湿度和总实际冷负荷值，获取所述空调系统在预测时刻下的总预测冷负荷值；根据所述总预测冷负荷值和每个空调设备的运行功率，获取所述空调系统在多种开启方式下对应的总能效比；其中，所述多种开启方式包括至少一个空调设备开启；以及获取目标开启方式，将所述目标开启方式作为所述预测时刻下的所述空调系统的开启方式；其中，所述目标开启方式为所述空调系统在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
附图说明
图1为根据一些实施例的一种空调系统的结构图；
图2为根据一些实施例的一种冷水主机的结构图；
图3为根据一些实施例的另一种冷水主机的结构图；
图4为根据一些实施例的一种控制器的结构图；
图5为根据一些实施例的一种空调系统的控制方法的流程图；
图6为根据一些实施例的另一种控制器的结构图；
图7为根据一些实施例的另一种空调系统的框图；
图8为根据一些实施例的一种空调设备的框图；
图9为根据一些实施例的另一种空调系统的控制方法的流程图；
图10为根据一些实施例的又一种空调系统的控制方法的流程图；
图11为根据一些实施例的一种预测冷负荷值的神经网络的结构图；
图12为根据一些实施例的又一种空调系统的控制方法的流程图；
图13为根据一些实施例的又一种空调系统的控制方法的流程图；
图14为根据一些实施例的又一种空调系统的控制方法的流程图；
图15为根据一些实施例的又一种空调系统的控制方法的流程图；
图16为根据一些实施例的又一种空调系统的控制方法的流程图；
图17为根据一些实施例的一种冷水机组系统的控制方法的流程图。
具体实施方式
下面将结合附图，对本公开一些实施例进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开所提供的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本公开保护的范围。
除非上下文另有要求，否则，在整个说明书和权利要求书中，术语“包括(comprise)”及其其他形式例如第三人称单数形式“包括(comprises)”和现在分词形式“包括(comprising)”被解释为开放、包含的意思，即为“包含，但不限于”。在说明书的描述中，术语“一个实施例(one embodiment)”、“一些实施例(some embodiments)”、“示例性实施例(exemplary embodiments)”、“示例(example)”、“特定示例(specific example)”或“一些示例(some examples)”等旨在表明与该实施例或示例相关的特定特征、结构、材料或特性包括在本公开的至少一个实施例或示例中。上述术语的示意性表示不一定是指同一实施例或示例。此外，所述的特定特征、结构、材料或特点可以以任何适当方式包括在任何一个或多个实施例或示例中。
以下，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本公开实施例的描述中，除非另有说明，“多个”的含义是两个或两个以上。
在描述一些实施例时，可能使用了“连接”及其衍伸的表达。术语“连接”应做广义理解，例如，“连接”可以是固定连接，也可以是可拆卸连接，或成一体；可以是直接相连，也可以通过中间媒介间接相连。
“A、B和C中的至少一个”与“A、B或C中的至少一个”具有相同含义，均包括以下A、B和C的组合：仅A，仅B，仅C，A和B的组合，A和C的组合，B和C的组合，及A、B和C的组合。
“A和/或B”，包括以下三种组合：仅A，仅B，及A和B的组合。
如本文中所使用，根据上下文，术语“如果”任选地被解释为意思是“当……时”或“在……时”或“响应于确定”或“响应于检测到”。类似地，根据上下文，短语“如果确定……”或“如果检测到[所陈述的条件或事件]”任选地被解释为是指“在确定……时”或“响应于确定……”或“在检测到[所 陈述的条件或事件]时”或“响应于检测到[所陈述的条件或事件]”。
本文中“适用于”或“被配置为”的使用意味着开放和包容性的语言，其不排除适用于或被配置为执行额外任务或步骤的设备。
另外，“基于”的使用意味着开放和包容性，因为“基于”一个或多个所述条件或值的过程、步骤、计算或其他动作在实践中可以基于额外条件或超出所述的值。
如本文所使用的那样，“约”、“大致”或“近似”包括所阐述的值以及处于特定值的可接受偏差范围内的平均值，其中所述可接受偏差范围如由本领域普通技术人员考虑到正在讨论的测量以及与特定量的测量相关的误差(即，测量系统的局限性)所确定。
在中央空调系统中，冷水机组需要压缩和循环制冷剂，以实现降低室内的温度，因此，需要消耗大量的电能，具有较高的能耗，在此情况下，通过优化冷水机组的功率等参数，以降低能耗，可以实现节能的效果。通常，可以通过定期维护或对冷水机组的负荷进行控制管理等方式实现降低冷水机组的能耗。
可以理解的是，中央空调系统中的冷却塔需要将热水或冷水暴露在空气中，利用蒸发的方式来降低水的温度。为了实现高效的热交换，需要大量的风量来促进水和空气之间的热传递。因此，冷却塔需要较大功率的风机，而大功率风机在运行时需要消耗较多的电能，从而会提高冷却塔的能耗。
例如，中央空调系统在全负荷工况运行的情况下，冷却塔的用电量占总用电量的12％至15％，因此，在中央空调系统中，对冷却塔进行节能优化，同样可以降低中央空调系统的能耗。
例如，可以通过定期对冷却塔进行维护与清洁，使冷却塔维持较高的工作效率，从而降低冷却塔的能耗。然而，维护和清洁冷却塔需要投入人力、时间和资源，造成冷却塔的维护成本提高。另外，在维护冷却塔时需要将冷却塔停机，影响系统的连续运行。
例如，还可以根据季节和环境温度的变化，调整冷却塔的运行参数，以提高冷却塔的工作效率，降低能耗。然而，如上方式需要在空调系统中增加复杂的控制系统和监测设备，增加空调系统的复杂性和维护难度。
基于此，本公开的一些实施例提供了一种空调系统。在该中央空调系统中，根据历史数据中中央空调系统在不同工况下的历史数据和预设数据，可以建立第一能耗模型和第二能耗模型。根据第一能耗模型可以得出冷却塔在当前工况下的多个第一运行功率，基于上述当前工况下最小的第一运行功率，根据第二能耗模型，可以得出该当前工况下的目标运行频率，进而控制冷却塔按照该目标运行频率运行，可以达到减小能耗的效果。
例如，所述空调系统为中央空调系统，或是其他种类的空调系统，本公开对此不做限定。
需要说明的是，本公开中的冷却塔的运行功率指的是冷却塔中冷却塔风机的运行功率，冷却塔的运行频率指的是冷却塔中冷却塔风机的运行频率，以下不再赘述。
图1为根据一些实施例的一种中央空调系统的结构图。
在一些实施例中，如图1所示，该空调系统1包括冷水机组101，冷水机组101被配置为对流经冷水机组101的冷冻水进行降温。例如，冷水机组101包括多个冷水主机和冷凝器。所述冷凝器与冷却塔构成冷却水回路，所述冷却水在所述冷却水回路中循环。
图2为根据一些实施例的一种冷水主机的结构图。
在一些实施例中，如图2所示，所述冷水主机包括压缩机1011、冷凝器1012、蒸发器1013以及节流装置1014。压缩机1011、冷凝器1012、蒸发器1013以及节流装置1014顺序连通形成制冷剂循环回路。
需要说明的是，所述的“顺序连通”仅用于说明各个器件之间连接的顺序关系，而各个器件之间还可以包括其他器件。例如，可以在压缩机1011与冷凝器1012之间的管路上设置截止阀等。
在空调系统1制冷时，如图3所示，压缩机1011将低温低压的气态制冷剂压缩成高温高压的气态制冷剂并排至冷凝器1012，高温高压气态制冷剂在冷凝器1012中与室外空气流换热，制冷剂释放热量，释放的热量被空气流带到室外环境空气中，制冷剂则发生相变而冷凝成液态或气液两相态的制冷剂。
接下来，制冷剂流出冷凝器1012，进入节流装置1014，并降温降压变成低温低压的制冷剂。低温低压的制冷剂进入蒸发器1013，吸收蒸发器1013内的制冷剂的热量，使蒸发器1013内的制冷剂的温度降低，实现制冷效果。制冷剂则发生相变而蒸发成低温低压的气态制冷剂，回流入压缩机1011，实现制冷剂的循环利用。
在一些实施例中，如图1所示，空调系统1还包括分水器102。分水器102的入口端与冷水机组 101的出口端连接，分水器102的出口端与用冷设备112相连，分水器102被配置为向所述用冷设备112分配冷冻水。
例如，分水器102的出口端连接多个用冷设备112，分水器102被配置为向所述多个用冷设备112分配冷冻水的流量，以使进入所述多个用冷设备112的多路冷冻水的压力大致均等。
在一些实施例中，空调系统1还包括集水器103和冷冻水泵104。集水器103的入口端与用冷设备112相连，集水器103的出口端通过冷冻水泵阀门与冷冻水泵104连接。集水器103被配置为汇集冷冻水。
在一些实施例中，分水器102和集水器103通过连接管路与用冷设备112连接。例如，冷冻水从分水器102的出口端通过连接管路流经用冷设备112，再通过管路从集水器103的入口端进入集水器103。
在一些实施例中，冷冻水泵104的第一端与冷水机组101的入口端连接，冷冻水泵104的第二端与集水器103的出口端连接。冷冻水泵104被配置为循环冷冻水，使冷冻水与室内空气进行热交换，以降低室内空气的温度，从而达到制冷的效果。
例如，冷冻水泵104包括冷冻水泵阀门，冷冻水泵阀门被配置为调整其开度的大小，以控制管路中的冷冻水的流量大小。
在一些实施例中，依次连接的冷水机组101、分水器102、集水器103、冷冻水泵104构成冷冻水回路。
在一些实施例中，空调系统1还包括冷却水泵105和冷却塔106。冷却水泵105的第一端与冷水机组101的出口端连接，冷却水泵105的第二端与冷却塔106的第一端连接。冷却水泵105被配置为循环冷却水，从而在冷冻水带走室内的热量后，使冷冻水通过冷水机组101将热量传递给冷却水。冷却水泵105还被配置为将升温后的冷却水压入冷却塔106，使升温后的冷却水与大气进行热交换并降温，以及，在冷却水降温后，将冷却水送回冷水主机中的冷凝器1012继续进行热交换。
例如，冷却水泵105包括冷却水泵阀门，冷却水泵阀门被配置为调整其开度的大小，以控制管路中冷却水的流量大小。
在一些实施例中，依次连接的冷水机组101、冷却水泵104和冷却塔106构成冷却水回路。
在一些实施例中，冷却塔106的第二端与冷水机组101的入口端相连。冷却塔106被配置为促进冷却水与流动的空气进行热交换，从而使冷却水中的热量散发至流动的空气中，以使得冷却水的温度降低，以及，回收并循环冷却水。
例如，冷却塔106包括至少一个冷却塔风机，冷却塔风机被配置为加速周围的空气流动，以加快冷却水温度的降低。需要说明的是，空调系统1可以包括一个或多个冷却塔106，本公开对此不作限定。
图4为根据一些实施例的一种控制器的结构图。
在一些实施例中，如图4所示，空调系统1还包括第一温度传感器107，第一温度传感器107设置于靠近冷却塔106的位置处，与室外空气接触。第一温度传感器107被配置为检测室外干球温度。
在一些实施例中，空调系统1还包括第二温度传感器108，第二温度传感器108设置于冷却塔106的第一端处，且第二温度传感器108被配置为检测冷却水进入冷却塔106时的温度。
在一些实施例中，空调系统1还包括第三温度传感器109，第三温度传感器109设置于冷却塔106的第二端处，且第三温度传感器109被配置为检测冷却水流出冷却塔106时的温度。
在一些实施例中，空调系统1还包括湿度传感器110，湿度传感器110设置于靠近冷却塔106的位置处，与室外空气接触，且湿度传感器110被配置为检测室外的相对湿度。
在一些实施例中，空调系统1还包括流量计111，流量计111设置于冷却塔的第二端处，且流量计111被配置为检测冷却水的流量。
在一些实施例中，如图4所示，空调系统1还包括控制器40。控制器40与冷水机组101、冷冻水泵104、冷却水泵105、冷却塔106、第一温度传感器107、第二温度传感器108、第三温度传感器109、湿度传感器110以及流量计111电连接，且控制器40被配置为根据指令操作码和时序信号，产生操作控制信号，指示空调系统1执行控制指令。
例如，控制器40可以获取第一温度传感器107检测到的室外干球温度、第二温度传感器108检测到的第一温度、第三温度传感器109检测到的第二温度、湿度传感器110检测到的室外相对湿度以及流量计111检测到的冷却水的流量。
在一些实施例中，控制器40为中央处理器(Central processing unit，CPU)、通用处理器、网络处 理器(Network processor，NP)、数字信号处理器(Digital signal processing，DSP)等。此外，控制器40可以用于控制空调系统1中各部件工作，以使得空调系统1的各个部件运行以实现空调系统1的各预定功能。
本公开的一些实施例还提供了一种空调系统的控制方法，该控制方法可应用于上述任一实施例中所述的空调系统，且由所述空调系统的控制器执行。
图5为根据一些实施例的一种中央空调系统的控制方法的流程图。下面，将结合图5，对所述控制方法进行详细地介绍。
如图5所示，所述空调系统的控制方法包括步骤S101至步骤S105。
在步骤S101，获取冷却塔106的当前工况，以及所述当前工况下的多组控制策略。
例如，通过当前的室外干球温度和当前的室外相对湿度可以确定冷却塔106的当前工况。所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度。在当前工况下，通过不同的设计冷却水温差、设计冷却水流量以及第一逼近度之间的组合，可以得到多组控制策略。
在步骤S102，根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，各组控制策略对应的冷却塔的第一运行功率。
需要说明的是，第一能耗模型用于表征冷却塔的第一运行功率与控制策略之间的关系。
例如，在当前工况下，根据第一温度传感器检测到的当前的室外干球温度、湿度传感器检测到的当前的室外相对湿度可以确定当前的湿球温度。将当前的湿球温度、和多组控制策略中的多组设计冷却水温差、设计冷却水流量、第一逼近度以及当前工况对应的额定运行功率，代入第一能耗模型中进行计算，以得到当前工况下各组控制策略对应的第一运行功率。
例如，当前的湿球温度、当前的室外干球温度以及当前的室外相对湿度之间满足如下公式：
Twb＝T·arctan[0.151977(RH+8.313659)0.50]+arctan(T+RH)-
arctan(RH-1.676331)+0.00391838·RH1.5·arctan(0.023101RH)-4.686035   (1)
在公式(1)中，Twb代表当前的湿球温度；T为当前的室外干球温度；RH为当前的室外相对湿度。
在一些实施例中，第一能耗模型的获取方法包括步骤S201至步骤S204。
在步骤S201，获取预设时长内，冷却塔106在多个历史工况下的历史数据信息，以及，与所述历史数据信息对应的历史运行功率、历史运行频率和额定运行功率。
例如，每个所述历史工况下的历史数据信息包括历史湿球温度、历史控制策略以及所述历史工况对应的预设湿球温度、预设冷却水温差、预设冷却水流量以及预设逼近度。
例如，所述历史控制策略包括历史冷却水温差、历史冷却水流量以及历史逼近度，所述历史湿球温度由所述历史工况中的历史室外干球温度和历史室外相对湿度确定。
可以理解的是，所述湿球温度是指当水蒸气从目标表面蒸发时，周围空气的温度。在所述历史工况下，根据历史室外干球温度和历史室外相对湿度，可以计算出历史湿球温度。
需要说明的是，在一些实施例中，所述预设时长为一年，或者，该预设时长还可以根据测试人员的需求确定，本公开对此不作限定。
在步骤S202，将所述多个历史工况下的所述历史数据信息中，历史运行频率小于第一预设频率对应的历史数据信息、历史运行频率大于第二预设频率对应的历史数据信息、历史运行功率大于第一预设功率且小于第二预设功率对应的历史数据信息去除，并得到第一数据信息。
可以理解的是，冷却塔106在运行过程中可能出现故障，导致其历史运行功率或历史运行频率的数据出现异常，因此，去除异常的历史运行频率和异常的历史运行功率中对应的历史数据信息，可以排除历史数据信息中的干扰因素，从而有利于提高第一能耗模型的准确性。
例如，第一预设频率可以为30Hz，第二预设频率可以为50Hz，第一预设功率可以为第二预设功率可以为其中，为预设时长内的历史运行功率的平均值，σ1为预设时长内的历史运行功率的平均差，可以通过公式(2)获得：
在公式(2)中，P代表历史运行功率；n代表预设时长内第一数据信息的个数。
σ1可以通过公式(3)获得：
在公式(3)中，代表预设时长内的历史运行功率的平均值；n代表预设时长内第一数据信息的个数；Pi代表第i个历史运行功率。
在步骤S203，对所述第一数据信息执行无量纲化处理，得到第二数据信息。
例如，用第一数据信息中的历史运行功率、历史湿球温度、历史冷却水温度差、历史逼近度、历史冷却水流量分别除以对应的额定运行功率、预设湿球温度、预设冷却水温度差、预设逼近度、预设冷却水流量，以得到第二数据信息。
可以理解的是，第一数据信息中的历史数据信息的值一般比预设数据信息的值小，因此，经过无量纲化处理后的数据不但精度更高，而且可以增强第一数据模型和第二数据模型的通用性。
在步骤S204，通过最小二乘法对所述第二数据信息执行拟合回归处理，得到所述第一能耗模型。
例如，通过最小二乘法对第二数据信息执行拟合回归处理，可以是根据拟合得到的曲线确定一个近似函数，进而得到第一能耗模型的各项系数。
在一些实施例中，第一能耗模型包括：
在第一能耗模型中，P代表历史运行功率；Pe代表额定运行功率；ΔT代表历史冷却水温差；ΔTe代表预设冷却水温差；Tapp代表历史逼近度；Tapp,e代表预设逼近度；Twb代表历史湿球温度；Twb,e代表预设湿球温度；mcw代表历史冷却水流量；mcw,e代表预设冷却水流量；a、b、c、d、e、r、g、h、i、j、k、l、m、n、o代表第一能耗模型的各项系数。
在步骤S103，根据各组控制策略对应的冷却塔的第一运行功率，确定目标控制策略。
例如，目标控制策略为各组控制策略中，对应最小的第一运行功率的控制策略。由于在同一工况下，不同的控制策略对应不同的能耗，因此以最小的设计功率对应的控制策略对冷却塔106的运行参数进行控制，有利于降低冷却塔106运行时的能耗，达到节能的效果。
在步骤S104，根据目标控制策略对应的第一运行功率和第二能耗模型，确定冷却塔的目标运行频率。
在一些实施例中，第二能耗模型的获取方法包括步骤S301。
在步骤S301，获取所述预设时长内的所述第二数据信息对应的历史运行频率对应的额定运行频率，并通过最小二乘法对第二数据信息对应的所述历史运行功率、所述历史运行功率、所述额定运行功率，以及所述额定运行频率执行拟合回归处理，得到第二能耗模型。
在一些实施例中，第二能耗模型包括：
在第二能耗模型中，P代表历史运行功率；Pe代表额定运行功率；f代表冷却塔的目标运行频率；fe代表冷却塔的额定运行频率；A、B、C代表第二能耗模型的各项系数。
可以理解的是，第二能耗模型的各项系数由控制器40通过最小二乘法对第二数据信息中的历史运行功率、历史运行功率、额定运行功率，以及额定运行频率执行拟合回归处理得到。第二能耗模型的各项系数的确定方法与第一能耗模型的各项系数的确定方法相同，此处不再赘述。
在步骤S105，控制冷却塔106按照所述目标控制策略和所述目标运行频率运行。
可以理解的是，在本公开的一些实施例提供的所述空调系统的控制方法中，由于冷却塔106的能耗 与工况和控制策略有关，因此，在室外干球温度和室外相对湿度发生变化，或者，在冷却塔的冷却水温差、冷却水流量和逼近度发生变化时，冷却塔的能耗可能会发生改变。
在此情况下，根据第一能耗模型，可以计算得出当前工况下，多种控制策略对应的冷却塔106的第一运行功率。上述多种第一运行功率可以反映出，当前工况下，每种控制策略对应的冷却塔106的能耗的大小。
可以理解的是，在多种控制策略中，最小的第一运行功率对应的控制策略对应的冷却塔106的能耗最小，因此，可以将最小的设计功率对应的控制策略作为目标控制策略，并根据最小的第一运行功率和第二能耗模型，确定目标运行功率。
这样，按照目标控制策略和目标运行频率对冷却塔106的运行进行控制(如对冷却塔106的多个运行参数进行控制)，有利于降低冷却塔106在当前工况下的能耗，从而达到节能的效果。
以下，将结合一个更加详细的示例，对本公开的空调系统的控制方法，进行进一步地详细说明。
在一些实施例中，空调系统1包括四台冷却塔106。所述空调系统的控制方法包括步骤S1至步骤S8。
在步骤S1，获取四台冷却塔在一年内的历史数据信息，所述历史数据信息包括历史湿球温度(如，历史湿球温度通过历史室外干球温度和历史室外相对湿度确定)历史冷却水温度差、历史逼近度、历史冷却水流量、历史运行频率、历史运行功率，以及，对应工况下的每个冷却塔的额定运行功率(如7.5kw)、预设冷却水温度差(如5℃)、预设冷却水流量(如303m3/h)。
需要说明的是，所述历史数据信息包括冷却塔106在一年内的各时段的数据信息。
在步骤S2，对上述一年内的历史数据信息进行处理，以得到第一数据信息。
例如，对上述一年内的历史数据信息进行处理包括：对冷却塔106的历史运行频率中，出现异常的历史数据信息进行除去，以及，对冷却塔的历史运行功率，出现异常的历史数据信息进行去除。例如，将对应于历史运行频率大于50Hz或历史运行频率小于30Hz的历史数据信息进行去除，将对应于历史运行功率位于区间内的历史数据信息进行去除。
在步骤S3，对经过处理后的第一数据信息进行无量纲化处理后，通过最小二乘法对无量纲化处理后的数据信息进行拟合回归处理，以得到第一能耗模型的系数，进而得到第一能耗模型。
例如，冷却塔106在多个历史工况下的额定运行功率比与历史运行功率比之间大致呈正相关。当额定运行功率比增大时，历史运行功率比也增大。冷却塔106在多个历史工况下的额定运行功率和历史运行功率之间大致呈正相关。当额定运行功率增大时，历史运行功率也增大。
在一些实施例中，第一能耗模型的拟合结果如表1所示：
表1
在表1中，R2为判定系数，又叫拟合优度，R2的值越接近1，模型的拟合优度越高。
在步骤S4，通过最小二乘法对第二数据信息中的历史运行功率、历史运行功率、额定运行功率，以及额定运行频率进行拟合回归处理，得到第二能耗模型的系数，从而得到第二能耗模型。
例如，冷却塔106在多个历史工况下的历史运行功率比和历史运行频率比之间大致呈正相关。当历史运行功率比增大时，历史运行频率比也增大。
在步骤S5，根据当前检测到的室外干球温度(如27℃)和当前的室外相对湿度，计算得到的湿球温度为24℃，通过设定多组控制策略(包括多组不同的设计冷却水温差、设计冷却水流量和第一逼近度)，根据第一能耗模型计算出冷却塔在当前工况下、不同控制策略下的冷却塔的多个第一运行功率。
在一些实施例中，第二能耗模型的拟合结果如表2所示：
表2
在步骤S6，根据当前工况下，不同控制策略下的多个第一运行功率的大小进行能耗排序。
例如，四台冷却塔106的制冷总能耗与控制策略数量之间大致呈负相关。当四台冷却塔106的制冷 总能耗增大时，控制策略数量随之降低。
根据上述多个第一运行功率，确定目标控制策略，目标控制策略为各组控制策略中，对应最小的第一运行功率的控制策略。
在步骤S7，通过第二能耗模型，确定目标运行功率对应的目标运行频率。
在一些实施例中，目标运行频率及相关数据如表3所示：
表3
在步骤S8，控制四个冷却塔106按照目标运行频率(即32Hz)运行。
例如，如表3所示，可以控制四台冷却塔按照相同的目标控制策略和相同的目标运行频率(如32Hz)运行。
可以理解的是，上述的一些实施例提供的空调系统的控制方法，通过目标控制策略和目标运行频率对多个冷却塔106的运行进行控制(如对冷却塔106的多个运行参数进行控制)，有利于降低冷却塔106在当前工况下的能耗，从而达到节能的效果。然而，对于空调系统1中的多个空调设备(即冷水机组101)之间的负荷率分配是否合理、多个空调设备对应的开启方式是否合理，空调系统能耗是否最低等问题，则无法进行有效的判断。
基于此，本公开的一些实施例提供了另一种空调系统1。例如，空调系统1可以是冷水机组系统，空调设备也可以称为冷水机组101。
图7为根据一些实施例的另一种空调系统的框图。如图7所示，空调系统1包括多个空调设备和控制器40。多个空调设备和控制器40设置在目标房间中。
例如，多个空调设备包括空调设备11、空调设备12、……空调设备n等。
在一些实施例中，目标房间可以是办公房间，住宅房间，大型商业建筑房间，本公开对此不作限定。
在一些实施例中，控制器40被配置为根据指令操作码和时序信号，产生操作控制信号，指示空调系统1执行控制指令。
例如，控制器40被配置为：根据空调系统1在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取空调系统1在预测时刻下的总预测冷负荷值；根据总预测冷负荷值和每个空调设备的运行功率，获取空调系统任一开启方式(例如，包括至少一个空调设备开启)下对应的总能效比；以及获取目标开启方式，将目标开启方式作为预测时刻下的空调系统1的开启方式。例如，所述目标开启方式为空调系统1在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
图8为根据一些实施例的一种空调设备的框图。如图8所示，空调设备包括控制组件120、传感器组件130、通信组件140和供电电源150中的一种或者多种。传感器组件130、通信组件140、供电电源150均与控制组件120连接。
在一些实施例中，控制组件120被配置为根据指令操作码和时序信号，产生操作控制信号，指示空调设备执行控制指令。
在一些实施例中，传感器组件130包括温度传感器和湿度传感器。控制组件120还被配置为控制温度传感器获取历史时刻下的室外温度、冷冻水供水温度、冷却水回水温度，以及控制湿度传感器获取室外相对湿度。
在一些实施例中，通信组件140是用于根据各种通信协议类型与外部设备或服务器进行通信的组件。例如，通信组件140包括无线通信技术(Wi-Fi)组件，蓝牙组件，有线以太网组件和近距离无线通信技术(Near field communication，NFC)组件等其他网络通信协议芯片或近场通信协议芯片，以及红外接收器中的至少一种。通信组件140被配置为与其他设备或通信网络通信(如以太网，无线接入网(Radio access network，RAN)，无线局域网(Wireless local area networks，WLAN)等)。
在一些实施例中，供电电源150被配置为在控制组件120的控制下，为空调设备的各电器元件提供运行电力支持。供电电源150可以包括电池及相关控制电路。
在一些实施例中，控制器40还被配置为：在获取空调系统1在预测时刻下的总预测冷负荷值之前，根据在历史时刻下空调系统1的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立空调系统1对应的能效比预测模型；基于空调系统1对应的能效比预测模型，输入空调系统1的冷冻水供 水温度、冷却水回水温度、冷负荷率，以获取空调系统的总预测能效比；以及，基于空调系统的总预测能效比和运行功率，获取空调系统的总实际冷负荷值。这样，可以实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，控制器40还被配置为：在获取空调系统1在预测时刻下的总预测冷负荷值之后，以空调系统1的总预测能效比为目标函数，根据冷冻水供水温度、冷却水回水温度以及总预测冷负荷值，利用差分进化算法，确定预测时刻下的每个空调设备的负荷率分配值。
需要说明的是，差分进化算法是一种基于群体的进化算法，它可以模拟种群中个体的合作与竞争的过程，包括选择、交叉、变异操作。差分进化算法一种成熟的，且具有高鲁棒性和广泛适用性的全局优化方法。
可以理解的是，通过差分进化算法确定预测时刻下的每个空调设备的负荷率分配值，可以获取针对每个空调设备的目标负荷率分配值，从而实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，控制器40还被配置为：根据负荷率分配值，获取每个空调设备分配的冷负荷值；以及，根据水的比热容、每个空调设备的冷冻水流量和冷却水回水温度、每个空调设备的分配的冷负荷值，获取每个空调设备优化后的冷冻水供水温度值。这样，可以实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，所述根据空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取空调系统1在预测时刻下的总预测冷负荷值，包括：基于第一反向传播神经网络模型，输入第一历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，输出当前时刻下的总冷负荷值，并建立用于预测冷负荷值的第二反向传播神经网络模型；以及，基于第二反向传播神经网络模型，输入第二历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取输出的预测时刻下的总预测冷负荷值。
如此，本公开的一些实施例提供的空调系统的控制方法，可以提前获取下一时刻的空调系统的总预测冷负荷值，并在下一时刻到来之前，提前一定的时间主动地调节和控制空调系统的供水温度以及开启方式，从而实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，控制器40还被配置为：在获取最大总能效比对应的空调系统的开启方式，作为预测时刻下的空调系统的开启方式之后，获取空调系统在预测时刻前的预设时长内的平均冷负荷值；在空调系统的冷负荷率小于预设负荷率的情况下，判断冷冻水供水温度值是否小于第一预设温度值；在冷冻水供水温度值小于或者等于第一预设温度值的情况下，判断平均冷负荷值是否小于第二制冷量的预设倍数；在平均冷负荷值大于第二制冷量的预设倍数的情况下，开启第二制冷量对应的空调设备，关闭第一制冷量对应的空调设备；第二制冷量小于第一制冷量；在平均冷负荷值小于或者等于第二制冷量的预设倍数的情况下，判断第二能效比是否大于或者等于第一能效比；第一能效比对应的空调设备为第一制冷量对应的空调设备，第二能效比对应的空调设备为第二制冷量对应的空调设备；当第二能效比大于或者等于第一能效比时，开启第二能效比对应的空调设备，关闭第一能效比对应的空调设备；当第二能效比小于第一能效比时，开启第一能效比对应的空调设备，关闭第二能效比对应的空调设备。这样，可以实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，控制器40还被配置为：判断冷冻水供水温度值是否大于或者等于第二预设温度值；在冷冻水供水温度值大于或者等于第二预设温度值的情况下，判断平均冷负荷值是否小于第一制冷量的预设倍数；第二预设温度值大于第一预设温度值；在平均冷负荷值大于第一制冷量的预设倍数的情况下，开启第二制冷量对应的空调设备；在平均冷负荷值小于或者等于第一制冷量的预设倍数的情况下，判断第二能效比是否大于或者等于第一能效比；当第二能效比大于或者等于第一能效比时，开启第二能效比对应的空调设备；当第二能效比小于第一能效比时，开启第一能效比对应的空调设备。
可以理解的是，当空调系统中配置的空调设备过多时，多个空调设备无需同时工作，在此情况下，控制器40需要控制多个空调设备轮流工作，以实现多个空调设备之间的最佳冷负荷率分配。
然而，空调设备在启动和停止的过程中需要消耗较多的能量，频繁地启停会导致能耗的浪费，因此，当空调设备过多时，通过减少空调设备的数量，有利于提高能源的利用效率，优化空调系统的控制。
在一些实施例中，控制器40还被配置为：在冷冻水供水温度值大于第一预设温度值且小于第二预设温度值的情况下，保持最大总能效比对应的空调系统的目标开启方式，作为预测时刻下的空调系统的开启方式。
图9为根据一些实施例的另一种空调系统的控制方法的流程图。
基于上述的另一种空调系统1，如图9所示，本公开的一些实施例还提供了另一种空调系统的控制方法，该方法包括步骤S11至S13。
在步骤S11，根据空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取空调系统在预测时刻下的总预测冷负荷值。
在一些实施例中，所述室外温度由温度传感器获取，所述室外相对湿度由湿度传感器获取。
在一些实施例中，空调系统在预测时刻下的总预测冷负荷值可以基于反向传播(Back Propagation，BP)神经网络模型进行计算和预测来获得。
可以理解的是，反向传播神经网络模型即为BP神经网络结构，BP神经网络是一种按照误差逆向传播算法训练的多层前馈神经网络。BP神经网络模型是一种针对非线性、非周期、无规律、无结构性或半结构性数据建模较常用、效果显著的模型。BP神经网络模型可以结合数据挖掘建立，且具有时间序列的特征。通过BP神经网络模型对空调系统的冷负荷值进行预测，有利于提高预测的效率、准确性和可靠性。
在步骤S12，根据总预测冷负荷值和每个空调设备的运行功率，获取空调系统在任一开启方式下对应的总能效比。
需要说明的是，所述开启方式包括至少一个空调设备开启。例如，在空调系统1包括空调设备11、空调设备12和空调设备13的情况下，所述开启方式包括：空调设备11、空调设备12和空调设备13中的任一者开启、任两者开启或全部开启。
在一些实施例中，可以利用公式(4)，获取空调系在统任一开启方式下对应的总能效比：
在公式(4)中，COP表示空调系统的总能效比，Qpre表示总预测冷负荷值，Pi为第i台空调设备的运行功率，Qi表示第i台空调设备所承担的冷负荷值，COPi表示第i台空调设备的能效比，n为所开启的空调设备的台数。
在步骤S13，获取目标开启方式，将目标开启方式作为预测时刻下的空调系统的开启方式。
需要说明的是，所述目标开启方式为空调系统1在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
可以理解的是，在空调系统中，能效比(Coefficient of Performance，COP)又称制冷性能系数，是指在一定的工况下，空调系统的制冷量与所消耗的功率之比，即消耗单位功率所获得的制冷量。因此，COP表示了空调系统对能源的利用效率。空调系统的COP越大，表示空调系统对能源的利用效率越高，空调系统的性能就越好，反之就越差。因此，将最大总能效比对应的空调系统的目标开启方式作为预测时刻下的空调系统的开启方式。从而实现空调系统的优化控制，降低空调系统的运行能耗。
在以上实施例中，控制器40根据空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取空调系统在预测时刻下的总预测冷负荷值，再根据总预测冷负荷值和每个空调设备的运行功率，获取空调系统任一开启方式下对应的总能效比。由于能效比越大，节省的电能就越多，因此，将最大总能效比对应的空调系统的目标开启方式作为预测时刻下的空调系统的开启方式，从而可以实现空调系统的优化控制，降低空调系统的运行能耗。
图10为根据一些实施例的又一种空调系统的控制方法的流程图。
在一些实施例中，如图10所示，步骤S11包括步骤S111和S112。
在步骤S111，基于第一反向传播神经网络模型，输入第一历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，输出当前时刻下的总冷负荷值，并建立用于预测冷负荷值的第二反向传播神经网络模型。
在一些实施例中，通过多个参数如第一历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，以及当前时刻下的总冷负荷值，对反向传播神经网络模型进行训练，从而建立用于预测冷负荷值的第二反向传播神经网络模型。
图11为根据一些实施例的一种预测冷负荷值的神经网络的结构图。反向传播神经网络模型如图11所示。
例如，参见图11，将当前时刻的前一小时的室外温度、前一小时的室外相对湿度、前二十四小时对应时刻的总冷负荷值、前三小时的总冷负荷值、前二小时的总冷负荷值以及前一小时的总冷负荷值作为 Bp神经网络模型的输入层，即，共六层输入层。隐含层节点数为十四层。输出层为训练目标值，目标值为当前时刻下的空调系统的总冷负荷值，从而可以通过上述数据训练建立用于预测冷负荷值的第二反向传播神经网络模型。
在步骤S112，基于第二反向传播神经网络模型，输入第二历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，以获取输出的预测时刻下的总预测冷负荷值。
在一些实施例中，基于建立的第二反向传播神经网络模型，以当前时刻的下一时刻为预测时刻，获取预测时刻下的总预测冷负荷值。
例如，可以将预测时刻的前一小时的室外温度、预测时刻的前一小时的室外相对湿度、预测时刻的前二十四小时的总冷负荷值、预测时刻的前三小时的总冷负荷值、预测时刻的前二小时的总冷负荷值、预测时刻的前一小时的总冷负荷值作为Bp神经网络模型的输入层，即，输入层共六层；隐含层节点数为十四层；输出层为训练目标值，目标值为预测时刻下的空调系统的总预测冷负荷值。
需要说明的是，相关技术通常是通过采集空调系统的实时的冷负荷值，并根据该冷负荷值计算得到每个空调设备最节能的冷负荷率，然后，根据每个空调设备最节能的冷负荷率对每个空调设备的运行参数进行调整，从而实现空调系统的优化控制。
然而，实现该负荷分配方式需要调节每个空调设备的供水温度，以及空调系统的开启方式，以上调节需要持续一定的时间才能完成。例如，实现当前时刻计算得到的目标负荷分配方式的过程，可能需要耗时15分钟至30分钟，以使空调系统被调节至节能运行状态。然而，在15分钟至30分钟后，冷负荷值可能已经发生改变。
基于此，本公开的一些实施例提供的空调系统的控制方法，可以提前获取下一时刻的空调系统的总预测冷负荷值，从而可以在下一时刻到来之前，提前一定的时间主动地调节和控制空调系统的供水温度以及开启方式，从而实现空调系统的优化控制，降低空调系统的运行能耗。
图12为根据一些实施例的又一种空调系统的控制方法的流程图。
在一些实施例中，如图12所示，在获取空调系统在预测时刻下的总预测冷负荷值之前，所述空调系统的控制方法还包括步骤S21至S23。
在步骤S21，根据空调系统在历史时刻下的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立空调系统对应的能效比预测模型。
在一些实施例中，可以利用公式(5)，建立空调系统对应的能效比预测模型：
在公式(5)中，PLR表示空调系统的负荷率；Tchw,s表示冷冻水供水温度，单位为℃；Tcw,r表示冷却水回水温度，单位为℃；A，B，C，D，E，F，G，H，I，J表示冷水机组模型辨识系数。
通过输入历史时刻下空调系统的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，获得公式(5)中的冷水机组模型辨识系数A，B，C，D，E，F，G，H，I，J，从而建立空调系统对应的能效比预测模型。并利用大量历史数据，训练上述能效预测模型。
在一些实施例中，根据每个空调设备在历史时刻下的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立每个空调设备对应的能效比预测模型。
在步骤S22，基于空调系统对应的能效比预测模型，输入空调系统的冷冻水供水温度、冷却水回水温度、冷负荷率，以获取空调系统的总预测能效比。
在一些实施例中，可以利用上述公式(5)，输入空调系统在预测时刻下的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，从而获取空调系统在预测时刻下的总预测能效比。
在一些实施例中，基于每个空调设备对应的能效比预测模型，输入所述每个空调设备的冷冻水供水温度、冷却水回水温度、冷负荷率，获取所述每个空调设备的预测能效比，进而获取所述空调系统的总预测能效比。
在步骤S23，基于空调系统的总预测能效比和运行功率，获取空调系统的总实际冷负荷值。
在一些实施例中，基于每个空调设备对应的所述预测能效比和对应的运行功率，获取空调系统的总实际冷负荷值。
例如，通过公式(6)，可以获得空调系统的总实际冷负荷值：
在公式(6)中，Q表示建筑真实冷负荷值，单位为kW；P表示每个空调系统的实测功率，单位为kW；下标i表示第i台空调系统；n表示空调系统的总数。
可以理解的是，在上述的一些实施例中，可以根据在历史时刻下空调系统的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立空调系统对应的能效比预测模型，从而利用该能效比预测模型获取空调系统的总预测能效比，进而获取空调系统的总实际冷负荷值。根据总实际冷负荷值，对每个空调系统的冷负荷值进行划分，从而可以实现空调系统的优化控制，降低空调系统的运行能耗。
图13为根据一些实施例的又一种空调系统的控制方法的流程图。
在一些实施例中，如图13所示，在获取空调系统在预测时刻下的总预测冷负荷值之后，所述空调系统的控制方法还包括步骤S31至步骤S33。
在步骤S31，以空调系统的总预测能效比为目标函数，根据冷冻水供水温度、冷却水回水温度以及总预测冷负荷值，利用差分进化算法，确定预测时刻下的每个空调设备的负荷率分配值。
需要说明的是，差分进化算法是一种基于群体的进化算法，它可以模拟种群中个体的合作与竞争的过程，包括选择、交叉、变异操作。差分进化算法一种成熟的，且具有高鲁棒性和广泛适用性的全局优化方法。
可以理解的是，通过差分进化算法确定预测时刻下的每个空调设备的负荷率分配值，可以获取针对每个空调设备的目标负荷率分配值，从而实现空调系统的优化控制，降低空调系统的运行能耗。
在一些实施例中，可以利用公式(7)，获取空调系统的总实际冷负荷值：
在公式(7)中，COPmax表示最大能效比。
在一些实施例中，可以以公式(8)作为获取每个空调设备对应的目标负荷率分配值约束条件：
在公式(8)中，Qde表示冷冻水机组铭牌上的额定制冷量，单位为kW。
由公式(8)可知，每个空调设备所分配的冷负荷值的总和等于所述多个空调设备的总冷负荷值。
在一些实施例中，所述差分进化算法包括步骤S311至步骤S316：
在步骤S311，执行初始化种群操作，包括：将空调系统中的每个空调设备作为一个单独的种群个体，随机初始化数目为NP的D维参数向量，其公式见(9)和(10)。例如，种群数NP取200。

在公式(9)和公式(10)中：Xi(0)表示第i个个体；j表示第j维；rand(0,1)表示在区间[0,1]中的随机数，和分别为第j维的下界和上界。
在步骤S312，执行适应度计算，包括：以空调系统的总预测能效比为目标函数，将目标函数值作为个体的适应度，计算初始种群中每个个体的适应度值。
在步骤S313，执行终止条件判断，包括：判断是否达到最大迭代次数，或者，适应度函数是否达到预期值，若是，则终止进化，将得到的最佳个体作为目标解输出；若否，则执行步骤S314。
在步骤S314，执行种群变异操作，包括：随机地选取种群中的两个不同的个体，将不同的个体的向量差缩放后与待变异个体进行向量合成。
例如，可以利用公式(11)将不同的个体的向量差缩放后与待变异个体进行向量合成。
Vi(g+1)＝Xr1(g)+F(Xr2(g)-Xr3(g))      (11)
在公式(11)中，r1，r2和r3表示三个随机数，该三个随机数的取值区间为[1,NP]；F表示缩放因子，且F为常数；g表示第g代。
在步骤S315，执行种群交叉操作，包括：产生一个随机数n(如，n为0至1之间的任一值)，然后利用公式(12)完成交叉操作。
在公式(12)中，CR为交叉概率。
可以理解的是，种群的交叉是为了产生多样性的子代向量，增强种群的多样性，促使种群产生结构化差异。
在步骤S316，执行目标种群选择操作，包括：将交叉向量与原向量作对比，选择其中的较优的个体作为新的个体。
例如，可以通过公式(13)执行所述目标种群选择操作。
在步骤S32，根据负荷率分配值，获取每个空调设备分配的冷负荷值。
例如，在预测时刻为下一时刻，且预测时刻的预测冷负荷值为1406Kw的情况下，若共有两个额定冷负荷值均为1406kw的空调设备，则差分进化算法可以计算出，下一时刻的最佳冷负荷率分配值为两个空调设备各承担50％的冷负荷率，即，所述两个空调设备分配的冷负荷值各为703kw。
在步骤S33，根据水的比热容、每个空调设备的冷冻水流量和冷却水回水温度、每个空调设备的分配的冷负荷值，获取每个空调设备优化后的冷冻水供水温度值。
在一些实施例中，可以利用公式(14)，获取每个空调设备优化后的冷冻水供水温度值：
在公式(14)中，c为水的比热容，单位为kJ/(kg·℃)；mi为第i台冷机的冷冻水流量，单位为m3/s；tr为冷冻水总管的回水温度，单位为℃；ts,i为第i台冷机的冷冻水供水温度，单位为℃。
可以理解的是，冷冻水供水温度与空调系统的功耗相关，当冷冻水供水温度越大时，空调系统的功耗越小。
本公开的一些实施例提供的空调系统的控制方法，通过差分进化算法确定预测时刻下的每个空调设备的负荷率分配值，可以获取针对每个空调设备的目标负荷率分配值。进而根据负荷率分配值，获取每个空调设备分配的目标冷负荷值，再获取每个空调设备优化后的冷冻水供水温度值，将优化后的冷冻水供水温度值设置为下一时刻的冷冻水供水温度值，从而可以实现空调系统的优化控制，降低空调系统的运行能耗。
图14为根据一些实施例的又一种空调系统的控制方法的流程图。
在一些实施例中，如图14所示，空调设备的控制方法还包括步骤S801至步骤S805。
在步骤S801，获取空调系统任一开启方式下对应的总能效比。
例如，获取空调系统任一开启方式下对应的总能效比包括获取单个空调设备运行的能效比，以及获取至少两个空调设备组合运行的能效比。
在步骤S802，确定最大总能效比对应的空调系统的开启方式。
在步骤S803，判断空调系统是否需要增加或减少空调设备，若是，则执行步骤S804，若否，则执行步骤S805。
在步骤S804，增加或减少空调系统中的空调设备。
例如，可以通过增加空调系统中的空调设备的方法或减少空调系统中的空调设备的方法来增加或减少空调系统中的空调设备，以降低空调系统中空调设备的频繁启停，从而有利于延长空调系统的使用寿命。
在步骤S805，将最大总能效比对应的开启方式作为下一时刻的开启方式。
图15为根据一些实施例的又一种空调系统的控制方法的流程图。如图15所示，所述减少空调系统中的空调设备的方法包括步骤S41至步骤S46。
在步骤S41，获取空调系统在预测时刻前的预设时长内的平均冷负荷值。
在步骤S42，在空调系统的冷负荷率小于预设负荷率的情况下，判断冷冻水供水温度值是否小于或等于第一预设温度值。
例如，预设负荷率为空调系统运行的负荷率下限。
在步骤S43，在冷冻水供水温度值小于或者等于第一预设温度值的情况下，判断平均冷负荷值是否小于第二制冷量的预设倍数；若是，则执行步骤S44，若否，则执行步骤S46。
例如，所述预设倍数设置为1.1。
在步骤S44，判断第二能效比是否大于或者等于第一能效比；若是，则执行步骤S46，若否，则执行步骤S45。
需要说明的是，第二制冷量小于第一制冷量。所述第一能效比对应的空调设备为所述第一制冷量对应的空调设备，所述第二能效比对应的空调设备为所述第二制冷量对应的空调设备。
在步骤S45，开启第一能效比对应的空调设备，关闭第二能效比对应的空调设备。
在步骤S46，开启第二能效比对应的空调设备，关闭第一能效比对应的空调设备。
可以理解的是，当空调系统中配置的空调设备过多时，多个空调设备无需同时工作，在此情况下，控制器40需要控制多个空调设备轮流工作，以实现多个空调设备之间的最佳冷负荷率分配。
然而，空调设备在启动和停止的过程中需要消耗较多的能量，频繁地启停会导致能耗的浪费，因此，当空调设备过多时，通过减少空调设备的数量，有利于提高能源的利用效率，优化空调系统的控制。
图16为根据一些实施例的又一种空调系统的控制方法的流程图。如图16所示，所述增加空调系统中的空调设备的方法包括步骤S41，以及步骤S51至步骤S55。
在步骤S41，获取空调系统在预测时刻前的预设时长内的平均冷负荷值。
在步骤S51，判断冷冻水供水温度值是否大于或者等于第二预设温度值。
在步骤S52，在冷冻水供水温度值大于或者等于第二预设温度值的情况下，判断平均冷负荷值是否小于第一制冷量的预设倍数；若是，则执行步骤S53，若否，则执行步骤S55。
需要说明的是，第二预设温度值大于第一预设温度值。例如，第二预设温度值为第一预设温度值加1.5摄氏度。
在步骤S53，判断第二能效比是否大于或者等于第一能效比；若是，则执行步骤S55，若否，则执行步骤S54。
在步骤S54，开启第一能效比对应的空调设备。
在步骤S55，开启第二能效比对应的空调设备。
可以理解的是，当空调系统中配置的空调设备过少时，为实现用户的需求(如将室内温度降低至20℃)，这些空调设备可能在高负荷条件下运行，高负荷地运行会导致空调设备的能效比下降。因此，通过增加适当数量的空调设备，可以提高空调系统的稳定性和能效比，且可以避免空调系统过度负荷运行。
在一些实施例中，所述控制方法还包括保持最大总能效比对应的空调系统的开启方法，所述保持最大总能效比对应的空调系统的开启方法包括步骤S61。
在步骤S61，在冷冻水供水温度值大于第一预设温度值且小于第二预设温度值的情况下，保持最大总能效比对应的所述空调系统的目标开启方式，作为预测时刻下的空调系统的开启方式。
例如，在冷冻水供水温度值大于第一预设温度值，且小于第一预设温度值加1.5摄氏度的情况下，保持步骤S13中最大总能效比对应的所述空调系统的目标开启方式，作为预测时刻下的空调系统的开启方式。
在一些实施例中，在空调系统运行的下一小时前的5分钟，可以按照步骤S41至步骤S46，步骤S51至步骤S55，以及步骤S61实现空调系统开启方法的控制方案，从而实现空调系统的前馈控制以及节能运行。
可以理解的是，通过判断是否需要增加空调设备或者减少空调设备，并执行相关控制步骤，可以避免空调系统中空调设备的频繁启停，从而增加空调系统的使用寿命，并且实现空调系统的优化控制，降低空调系统的运行能耗。
图17为根据一些实施例的一种冷水机组系统的控制方法的流程图。
在一些实施例中，空调系统为冷水机组系统，所述冷水机组系统包括多个冷水机组(即空调设备)。
以下，将结合图17，以空调系统为冷水机组系统为例，对冷水机组系统的提前优化控制方法进行详细介绍。所述提前优化控制方法包括步骤S71至步骤S75。
在步骤S71，获取总实际冷负荷值。
例如，通过建立冷水机组系统对应的能效比预测模型，以及实测每个冷水机组的运行功率，获取当前时刻的总实际冷负荷值。例如，参照步骤S21至步骤S23执行步骤S71。
在步骤S72，建立Bp神经网络模型，获取下一小时的总预测冷负荷值。
例如，步骤S72可以按照步骤S111至步骤S113执行。
在步骤S73，根据当前时刻下的冷冻水供水温度、冷却水回水温度，以及下一小时的总预测冷负荷值，利用差分进化算法，确定下一小时的每个冷水机组的负荷率分配值。
例如，步骤S73可以参照步骤S31执行。
在步骤S74，根据所述负荷率分配值，获取每个冷水机组优化后的冷冻水供水温度值。
例如，步骤S74可以参照步骤S32至步骤S33执行。
在步骤S75，对冷水机组的台数件进行优化设定。
例如，对冷水机组的台数件进行优化设定包括：获取冷水机组系统任一开启方式下对应的总能效比，将最大总能效比对应的冷水机组系统的开启方式作为下一小时的最佳的冷水机组系统的开启方式；以及在下一小时前的5分钟发送优化控制指令。
例如，在步骤S75中，可以通过执行步骤S401至步骤S406，步骤S501至步骤S505，以及步骤S601，来增加冷水或者减少冷水机组系统中的冷水机组。
这样，基于最佳的冷水机组运行台数和负荷率分配，逐时调整冷水机组运行台数，重设各台冷水机组的供水设定温度，可以保障冷水机组系统运行的安全性和稳定性。当冷水机组系统中的冷水机组增加或减少时，可以重复步骤S73和步骤S74，以寻找最佳的负荷率分配方式，重设各台冷水机组的供水温度。
可以理解的是，所述提前优化控制方法，根据冷水机组系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取冷水机组系统在预测时刻下的总预测冷负荷值，再根据总预测冷负荷值和每个冷水机组的运行功率，获取冷水机组系统任一开启方式下对应的总能效比。由于能效比是能源转换效率之比，能效比越大，节省的电能就越多，因此将最大总能效比对应的冷水机组系统的目标开启方式作为预测时刻下的冷水机组系统的开启方式。
因此，通过增加是否需要进行增加冷水机组或者减少冷水机组的判断，可以降低冷水机组的频繁启停，从而增加冷水机组系统的使用寿命，并且实现冷水机组系统的前馈优化控制，降低冷水机组系统的运行能耗。
以下，以某酒店建筑的制冷机房系统(即空调系统)为例，对空调系统的控制方法进行详细地介绍。
制冷机房系统包括三个冷水机组，其中的两个冷水机组为500RT的变频离心式冷水机组，另外的一个冷水机组为400RT的变频离心式冷水机组。所述空调系统的控制方法包括步骤S81至步骤S85。
在步骤S81，获取总预测冷负荷值。
例如，步骤S81包括步骤S811至步骤S813。
在步骤S811，根据在历史时刻下冷水机组系统的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，和上述公式(5)，建立冷水机组系统对应的能效比预测模型，并利用大量历史数据，训练上述能效预测模型，以得到三个冷水机组的模型辨识系数。第一个冷水机组(500RT)的模型拟合结果包括：A为-4.74375，B为0.02529，C为-0.00001，D为-0.02952，E为-0.14628，F为0.02047，G为12.21102，H为-0.80367，I为-0.18150，J为8.11102。第二个冷水机组(500RT)的模型拟合结果包括：A为-9.20506，B为0.04685，C为0.00245，D为0.25566，E为-0.27021，F为-0.00483，G为20.15267，H为-0.62736，I为-0.11550，J为0.86570。第二个冷水机组(400RT)的模型拟合结果包括：A为-9.20506，B为0.04685，C为0.00245，D为0.25566，E为-0.27021，F为-0.00483，G为20.15267，H为-0.62736，I为-0.11550，J为0.86570。在步骤S812，基于上述三个冷水机组的模型辨识系数，利用公式(5)，输入每个冷水机组的冷冻水供水温度、冷却水回水温度、冷负荷率，获取每个冷水机组的预测能效比。
在步骤S813，实测每个冷水机组的运行功率，利用公式(6)，根据每个冷水机组的预测能效比与运行功率的关系计算得出每个冷水机组的实际冷负荷值，最终可以确定建筑的总实际冷负荷值。
在步骤S82，基于Bp神经网络模型，获取预测时刻下的总预测冷负荷值。
例如，步骤S82包括步骤S821和步骤S822。
在步骤S821，建立并训练目标Bp神经网络模型。
例如，获取气象典型日5月2日的01:00:00、02:00:00、03:00:0、04:00:00、05:00:00，以及气象典 型日7月24日的20:00:00、21:00:00、22:00:00、23:00:0、24:00:00对应时刻的历史数据作为训练数据集。将该训练数据集(如，包括：前1小时的室外温度、前1小时的室外相对湿度、前24小时对应时刻的总冷负荷值、前3小时的总冷负荷值、前2小时的总冷负荷值以及前1小时的总冷负荷值)作为Bp神经网络模型的输入层，即，输入层共有六层；隐含层节点数为十四层；输出层为训练目标值，目标值为对应时刻下的冷水机组系统的总冷负荷值，训练得到用于预测冷负荷值的第二反向传播神经网络模型。基于上述第二反向传播神经网络模型，获取气象典型日7月25日的01:00:00、02:00:00、03:00:0、04:00:00、05:00:00，以及气象典型日9月30日的20:00:00、21:00:00、22:00:00、23:00:0、24:00:00对应时刻的历史数据作为测试数据集。对第二反向传播神经网络模型进行训练。将前1小时的室外温度、前1小时的室外相对湿度、前24小时对应时刻的总冷负荷值、前3小时的总冷负荷值、前2小时的总冷负荷值以及前1小时的总冷负荷值作为Bp神经网络模型的输入层，即，输入层共有六层；隐含层节点数为十四层；输出层为测试目标值，目标值为对应时刻下的冷水机组系统的总冷负荷值。在步骤S822，获取预测时刻下的总预测冷负荷值。
例如，对8月26日至8月31日全天时刻进行预测，将预测时刻下的前1小时的室外温度、前1小时的室外相对湿度、预测时刻的前24时刻的总冷负荷值、预测时刻前3小时的总冷负荷值、预测时刻前2小时的总冷负荷值、预测时刻前1小时的总冷负荷值作为Bp神经网络模型的输入层，即，输入层共六层；隐含层节点数为十四层；输出层为训练目标值，目标值为预测时刻下的冷水机组系统的总预测冷负荷值。
在步骤S83，基于差分进化算法求解优化的冷水机组负荷率分配方式。
例如，以冷水机组系统的总预测能效比为目标函数，根据冷冻水供水温度、冷却水回水温度以及总预测冷负荷值，利用差分进化算法，确定预测时刻下的每个空调设备的负荷率分配值。
例如，可以通过对以冷水机组系统的总预测能效比为目标函数对应的公式(7)，以及约束条件对应的公式(8)，采用差分进化算法求解计算得出下一小时的每个冷水机组的优化负荷率值。
在一些实施例中，两个500RT的冷机负荷率分配比例相等，而500RT的冷水机组性能比400RT冷水机组性能更高，因此500RT冷水机组为主机，400RT冷水机组作为冷量补充的机组。
在步骤S84，对冷水机组供水温度进行优化设定。
例如，根据负荷率分配值，获取每个冷水机组分配的冷负荷值。再根据水的比热容、每个冷水机组的冷冻水流量和冷却水回水温度、每个冷水机组的分配的冷负荷值，利用上述公式(9)，获取每个冷水机组优化后的冷冻水供水温度值。
在步骤S85，对冷水机组的台数的控制方式进行优化设定。
例如，对冷水机组的台数的控制方式进行优化设定包括：根据总预测冷负荷值和每个空调设备的运行功率，获取冷水机组系统任一开启方式下对应的总能效比。并将最大总能效比对应的冷水机组系统的目标开启方式，作为预测时刻下的冷水机组系统的开启方式。
在一些实施例中，为避免冷水机组的频繁启停，增加了步骤S41至步骤S46，步骤S51至步骤S55、以及步骤S61，以判断是否需要进行增加冷水机组或者减少冷水机组。
8月26日至8月31日采用本公开的一些实施例提供的控制方法后，冷水机组系统的能耗、能效情况以及未采用本公开的一些实施例提供的控制方法的冷水机组系统的原始能耗、能效情况如下表4所示。参见表4，采用该控制方法，可以使能耗降低6.18％，实现了冷水机组系统的节能运行。
表4
可以理解的是，上述的一些实施例主要从方法的角度对本公开进行介绍。为实现上述功能，本公开的一些实施例提供执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本公开的一些实施例描述的各示例的模块及算法步骤，本公开的一些实施例能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本公开的范围。
本公开的一些实施例可以根据上述方法示例对控制器40进行功能模块上的划分。例如，可以将应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。可以理解的是，本公开的一些实施例中，对模块的划分是示意性的，仅仅为一种逻辑功能划分，当前实现时可以有另外的划分方式。
图6为根据一些实施例的另一种控制器的结构图。如图6所示，控制器40包括处理器401。在一些实施例中，控制器40还包括与处理器401连接的存储器402和通信接口403。处理器401、存储器402和通信接口403通过总线404连接。
在一些实施例中，处理器401可以是中央处理器(Central processing unit，CPU)，通用处理器网络处理器(Network processor，NP)、数字信号处理器(Digital signal processing，DSP)等。
在一些实施例中，存储器402可以是只读存储器(Read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备、随机存取存储器(Random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，本公开对此不做限定。
在一些实施例中，通信接口403被配置为与其他设备或通信网络通信(如以太网，无线接入网(Radio access network，RAN)，无线局域网(Wireless local area networks，WLAN)等。
在一些实施例中，总线404可以是外设部件互连标准(Peripheral component interconnect，PCI)总线或扩展工业标准结构(Extended industry standard architecture，EISA)总线等。总线404可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
本领域的技术人员将会理解，本发明的公开范围不限于上述具体实施例，并且可以在不脱离本公开的精神的情况下对实施例的某些要素进行修改和替换。本公开的范围受所附权利要求的限制。

Claims (20)

  1. 一种空调系统，包括：
    冷却塔，被配置为协助冷却水降温；
    冷水机组，包括冷凝器；所述冷凝器与所述冷却塔构成冷却水回路，所述冷却水在所述冷却水回路中循环；
    控制器，与所述冷却塔和所述冷水机组电连接，所述控制器被配置为：
    获取所述冷却塔的当前工况以及所述当前工况下的多组控制策略；其中，所述当前工况通过当前的室外干球温度和当前的室外相对湿度确定；所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度；
    根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，所述多组控制策略对应的所述冷却塔的第一运行功率；其中，所述第一能耗模型用于表征所述冷却塔的第一运行功率与所述控制策略之间的关系；
    根据所述多组控制策略对应的所述冷却塔的第一运行功率，确定目标控制策略；其中，所述目标控制策略为所述多组控制策略中，与最小的所述冷却塔的第一运行功率相对应的控制策略；
    根据所述最小的所述冷却塔的第一运行功率和第二能耗模型，确定所述冷却塔的目标运行频率；其中，所述第二能耗模型用于表征所述冷却塔的第一运行功率与所述目标运行频率之间的关系；以及
    控制所述冷却塔按照所述目标控制策略和所述目标运行频率运行。
  2. 根据权利要求1所述的空调系统，还包括：
    第一温度传感器，被配置为检测所述室外干球温度；
    湿度传感器，被配置为检测室外相对湿度；
    第二温度传感器，被配置为检测第一温度；所述第一温度为所述冷却水进入所述冷却塔时的温度；
    第三温度传感器，被配置为检测第二温度；所述第二温度为所述冷却水流出所述冷却塔时的温度；以及
    流量计，被配置为检测所述冷却水的流量；
    其中，所述第一温度传感器、所述湿度传感器、所述第二温度传感器、所述第三温度传感器以及所述流量计与所述控制器电连接；
    所述控制器还被配置为：
    获取所述冷却塔在预设时长内的多个历史工况下的历史数据信息，以及，与所述历史数据信息对应的历史运行功率、历史运行频率和额定运行功率；其中，所述历史工况下的所述历史数据信息包括历史湿球温度、历史控制策略以及所述历史工况对应的预设湿球温度、预设冷却水温差、预设冷却水流量以及预设逼近度；所述历史控制策略包括历史冷却水温差、历史冷却水流量以及历史逼近度，所述历史湿球温度由所述历史工况中的历史室外干球温度和历史室外相对湿度确定；
    将所述多个历史工况下的所述历史数据信息中，所述历史运行频率小于第一预设频率对应的历史数据信息、所述历史运行频率大于第二预设频率对应的历史数据信息、所述历史运行功率大于第一预设功率且小于第二预设功率对应的历史数据信息去除，并得到第一数据信息；
    对所述第一数据信息执行无量纲化处理，并得到第二数据信息；以及
    通过最小二乘法对所述第二数据信息执行拟合回归处理，并得到所述第一能耗模型。
  3. 根据权利要求1或2所述的空调系统，其中，所述第一能耗模型包括：

    其中，P代表历史运行功率；Pe代表额定运行功率；ΔT代表历史冷却水温差；ΔTe代表预设冷却水温差；Tapp代表历史逼近度；Tapp,e代表预设逼近度；Twb代表历史湿球温度；Twb,e代表预设湿球温度；mcw代表历史冷却水流量；mcw,e代表预设冷却水流量；a、b、c、d、e、r、g、h、i、r、k、l、m、n、o代表所述第一能耗模型的各项系数。
  4. 根据权利要求1至3中任一项所述的空调系统，其中，所述控制器还被配置为：
    获取预设时长内的第二数据信息对应的所述冷却塔的历史运行频率和额定运行频率；以及
    通过最小二乘法对所述第二数据信息对应的所述冷却塔的历史运行功率、所述历史运行频率、额定运行功率，以及所述额定运行频率执行拟合回归处理，得到所述第二能耗模型。
  5. 根据权利要求4所述的空调系统，其中，所述第二能耗模型包括：
    其中，P代表所述历史运行功率；Pe代表所述额定运行功率；f代表所述目标运行频率；fe代表所述额定运行频率；A、B、C代表所述第二能耗模型的各项系数。
  6. 一种空调系统的控制方法，其中，所述空调系统包括：
    冷却塔，被配置为协助冷却水降温；
    冷水机组，包括冷凝器；所述冷凝器与所述冷却塔构成冷却水回路，所述冷却水在所述冷却水回路中循环；
    所述方法包括：
    获取所述冷却塔的当前工况以及所述当前工况下的多组控制策略；其中，所述当前工况通过当前的室外干球温度和当前的室外相对湿度确定；所述控制策略包括设计冷却水温差、设计冷却水流量以及第一逼近度；
    根据所述当前工况、所述多组控制策略以及第一能耗模型，确定当前工况下，所述多组控制策略对应的所述冷却塔的第一运行功率；其中，所述第一能耗模型用于表征所述冷却塔的第一运行功率与所述控制策略之间的关系；
    根据所述多组控制策略对应的所述冷却塔的第一运行功率，确定目标控制策略；其中，所述目标控制策略为所述多组控制策略中，与最小的所述冷却塔的第一运行功率相对应的控制策略；
    根据所述最小的所述冷却塔的第一运行功率和第二能耗模型，确定所述冷却塔的目标运行频率；其中，所述第二能耗模型用于表征所述冷却塔的第一运行功率与所述目标运行频率之间的关系；以及
    控制所述冷却塔按照所述目标控制策略和所述目标运行频率运行。
  7. 根据权利要求6所述的空调系统的控制方法，其中，所述空调系统还包括：
    第一温度传感器，被配置为检测所述室外干球温度；
    湿度传感器，被配置为检测室外相对湿度；
    第二温度传感器，被配置为检测第一温度；所述第一温度为所述冷却水进入所述冷却塔时的温度；
    第三温度传感器，被配置为检测第二温度；所述第二温度为所述冷却水流出所述冷却塔时的温度；以及
    流量计，被配置为检测所述冷却水的流量；
    所述方法还包括：
    获取预设时长内的所述冷却塔在多个历史工况下的历史数据信息，以及，与所述历史数据信息对应的历史运行功率、历史运行频率和额定运行功率；其中，所述历史工况下的所述历史数据信息包括历史湿球温度、历史控制策略以及所述历史工况对应的预设湿球温度、预设冷却水温差、预设冷却水流量以及预设逼近度；所述历史控制策略包括历史冷却水温差、历史冷却水流量以及历史逼近度，所述历史湿球温度由所述历史工况中的历史室外干球温度和历史室外相对湿度确定；
    将所述多个历史工况下的所述历史数据信息中，所述历史运行频率小于第一预设频率对应的历史数据信息、所述历史运行频率大于第二预设频率对应的历史数据信息、所述历史运行功率大于第一预设功率且小于第二预设功率对应的历史数据信息去除，得到第一数据信息；
    对所述第一数据信息执行无量纲化处理，得到第二数据信息；以及
    通过最小二乘法对所述第二数据信息执行拟合回归处理，得到所述第一能耗模型。
  8. 根据权利要求6或7所述的空调系统的控制方法，其中，所述第一能耗模型包括：
    其中，P代表历史运行功率；Pe代表额定运行功率；ΔT代表历史冷却水温差；ΔTe代表预设冷却水温差；Tapp代表历史逼近度；Tapp,e代表预设逼近度；Twb代表历史湿球温度；Twb,e代表预设湿球温度；mcw代表历史冷却水流量；mcw,e代表预设冷却水流量；a、b、c、d、e、r、g、h、i、r、k、l、m、n、o代表所述第一能耗模型的各项系数。
  9. 根据权利要求6至8中任一项所述的空调系统的控制方法，其中，所述方法还包括：
    获取预设时长内的第二数据信息对应的所述冷却塔的历史运行频率和额定运行频率；以及
    通过最小二乘法对所述第二数据信息对应的所述冷却塔的历史运行功率、所述历史运行频率、额定运行功率，以及所述额定运行频率执行拟合回归处理，得到所述第二能耗模型。
  10. 根据权利要求9所述的空调系统的控制方法，其中，所述第二能耗模型包括：
    其中，P代表所述历史运行功率；Pe代表所述额定运行功率；f代表所述目标运行频率；fe代表所述额定运行频率；A、B、C代表所述第二能耗模型的各项系数。
  11. 一种空调系统，包括：
    至少两个空调设备；和
    控制器，与所述至少两个空调设备电连接；所述控制器被配置为：
    根据所述空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取所述空调系统在预测时刻下的总预测冷负荷值；
    根据所述总预测冷负荷值和每个空调设备的运行功率，获取所述空调系统在多种开启方式下对应的总能效比；其中，所述多种开启方式包括所述至少两个空调设备中的至少一个空调设备开启；以及
    获取目标开启方式，将所述目标开启方式作为所述预测时刻下的所述空调系统的开启方式；其中，所述目标开启方式为所述空调系统在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
  12. 根据权利要求11所述的空调系统，其中，所述控制器还被配置为：
    在所述获取所述空调系统在所述预测时刻下的所述总预测冷负荷值之前，根据在所述历史时刻下的所述空调系统的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立所述空调系统对应的能效比预测模型；
    基于所述能效比预测模型，输入所述空调系统的所述冷冻水供水温度、所述冷却水回水温度以及所述冷负荷率，获得所述空调系统的总预测能效比；以及
    基于所述空调系统的所述总预测能效比和运行功率，获得所述空调系统的总实际冷负荷值。
  13. 根据权利要求12所述的空调系统，其中，所述控制器，所述控制器还被配置为：
    在所述获取所述空调系统在所述预测时刻下的所述总预测冷负荷值之后，以所述空调系统的所述总预测能效比为目标函数，根据冷冻水供水温度、冷却水回水温度以及所述总预测冷负荷值，利用差分进化算法，确定所述预测时刻下的每个空调设备的负荷率分配值。
  14. 根据权利要求13所述的空调系统，其中，所述控制器还被配置为：
    根据所述负荷率分配值，获得每个空调设备分配的冷负荷值；
    根据水的比热容、每个空调设备的冷冻水流量和冷却水回水温度、每个空调设备分配的冷负荷值，获得所述每个空调设备优化后的冷冻水供水温度值。
  15. 根据权利要求11至14中任一项所述的空调系统，其中，所述根据所述空调系统在历史时刻下的所述室外温度、所述室外相对湿度和所述总实际冷负荷值，获得所述空调系统在所述预测时刻下的所述总预测冷负荷值，包括：
    基于第一反向传播神经网络模型，输入第一历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，输出当前时刻下的总冷负荷值，并建立用于预测冷负荷值的第二反向传播神经网络模型；以及
    基于所述第二反向传播神经网络模型，输入第二历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获得输出的所述预测时刻下的所述总预测冷负荷值。
  16. 根据权利要求11至15中任一项所述的空调系统，其中，所述控制器还被配置为：
    在获取所述目标开启方式，并将所述目标开启方式作为所述预测时刻下的所述空调系统的开启方式后，获得所述空调系统在所述预测时刻前的预设时长内的平均冷负荷值；
    在所述空调系统的冷负荷率小于预设负荷率的情况下，判断所述冷冻水供水温度值是否小于或等于第一预设温度值；
    在所述冷冻水供水温度值小于或等于所述第一预设温度值的情况下，判断所述平均冷负荷值是否小于第二制冷量的预设倍数；
    在所述平均冷负荷值大于所述第二制冷量的预设倍数的情况下，开启所述第二制冷量对应的空调设备，关闭第一制冷量对应的空调设备；其中，所述第二制冷量小于所述第一制冷量；
    在所述平均冷负荷值小于或等于所述第二制冷量的预设倍数的情况下，判断第二能效比是否大于或等于第一能效比；其中，所述第一能效比对应的空调设备为所述第一制冷量对应的空调设备，所述第二能效比对应的空调设备为所述第二制冷量对应的空调设备；
    在所述第二能效比大于或者等于所述第一能效比的情况下，开启所述第二能效比对应的空调设备，关闭所述第一能效比对应的空调设备；以及
    在所述第二能效比小于所述第一能效比的情况下，开启所述第一能效比对应的空调设备，并关闭所述第二能效比对应的空调设备。
  17. 根据权利要求16所述的空调系统，其中，所述控制器还被配置为：
    判断所述冷冻水供水温度值是否大于或者等于第二预设温度值；
    在所述冷冻水供水温度值大于或者等于所述第二预设温度值的情况下，判断所述平均冷负荷值是否小于所述第一制冷量的预设倍数；其中，所述第二预设温度值大于所述第一预设温度值；
    在所述平均冷负荷值大于所述第一制冷量的预设倍数的情况下，开启所述第二制冷量对应的空调设备；
    在所述平均冷负荷值小于或者等于所述第一制冷量的预设倍数的情况下，判断所述第二能效比是否大于或者等于所述第一能效比；
    在所述第二能效比大于或者等于所述第一能效比的情况下，开启所述第二能效比对应的空调设备；以及
    在所述第二能效比小于所述第一能效比的情况下，开启所述第一能效比对应的空调设备。
  18. 根据权利要求17所述的空调系统，其中，所述控制器还被配置为：
    在所述冷冻水供水温度值大于所述第一预设温度值且小于所述第二预设温度值的情况下，保持所述目标开启方式，作为所述预测时刻下的所述空调系统的开启方式。
  19. 一种空调系统的控制方法，包括：
    根据所述空调系统在历史时刻下的室外温度、室外相对湿度和总实际冷负荷值，获取所述空调系统在预测时刻下的总预测冷负荷值；
    根据所述总预测冷负荷值和每个空调设备的运行功率，获取所述空调系统在多种开启方式下对应的总能效比；其中，所述多种开启方式包括至少一个空调设备开启；以及
    获取目标开启方式，将所述目标开启方式作为所述预测时刻下的所述空调系统的开启方式；其中，所述目标开启方式为所述空调系统在所述多种开启方式下对应的总能效比中，对应于最大的总能效比的开启方式。
  20. 根据权利要求19所述的控制方法，还包括：
    在所述获取所述空调系统在所述预测时刻下的所述总预测冷负荷值之前，根据在所述历史时刻下的所述空调系统的冷冻水供水温度、冷却水回水温度、冷负荷率以及实际能效比，建立所述空调系统对应的能效比预测模型；
    基于所述能效比预测模型，输入所述空调系统的所述冷冻水供水温度、所述冷却水回水温度以及所述冷负荷率，获得所述空调系统的总预测能效比；以及
    基于所述空调系统的所述总预测能效比和运行功率，获得所述空调系统的总实际冷负荷值。
PCT/CN2023/114293 2023-01-28 2023-08-22 空调系统及其控制方法 Ceased WO2024156177A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP23918178.7A EP4607101A4 (en) 2023-01-28 2023-08-22 AIR CONDITIONING SYSTEM AND ITS CONTROL METHOD

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202310078863.XA CN116007072B (zh) 2023-01-28 2023-01-28 一种中央空调系统及其控制方法
CN202310078863.X 2023-01-28
CN202310155043.6A CN118532787A (zh) 2023-02-22 2023-02-22 一种空调系统及其控制方法
CN202310155043.6 2023-02-22

Publications (1)

Publication Number Publication Date
WO2024156177A1 true WO2024156177A1 (zh) 2024-08-02

Family

ID=91969904

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/114293 Ceased WO2024156177A1 (zh) 2023-01-28 2023-08-22 空调系统及其控制方法

Country Status (2)

Country Link
EP (1) EP4607101A4 (zh)
WO (1) WO2024156177A1 (zh)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118822040A (zh) * 2024-08-23 2024-10-22 重庆智拓能源科技有限公司 一种空调制冷机房运行系统cop预测方法
CN119022413A (zh) * 2024-09-13 2024-11-26 广东工业大学 一种冷水机组负荷分配方法和装置
CN119123579A (zh) * 2024-11-12 2024-12-13 杭州华电华源环境工程有限公司 一种基于分层多目标优化的冰蓄冷控制方法及系统
CN119146474A (zh) * 2024-09-06 2024-12-17 北京市市政工程设计研究总院有限公司 确定多能耦合供热系统的能源组合形式的方法和装置
CN119436515A (zh) * 2024-12-13 2025-02-14 珠海格力电器股份有限公司 多模块空调器机组的控制方法及装置、多模块空调器机组
CN119713515A (zh) * 2024-09-24 2025-03-28 辽宁睿智聚合科技有限公司 面向建筑负荷预测的中央空调系统优化控制方法
CN119847310A (zh) * 2025-03-19 2025-04-18 国家工业信息安全发展研究中心 一种数据中心节能系统及方法
CN120176228A (zh) * 2025-05-21 2025-06-20 西安四腾环境科技有限公司 一种智能化的医院洁净室送风调节方法和系统
CN120273927A (zh) * 2025-04-17 2025-07-08 科瑞特空调集团有限公司 一体式数字化风机的节能控制系统
CN120488861A (zh) * 2025-07-08 2025-08-15 南京群顶科技股份有限公司 冷站冷却塔最佳台数频率动态调节方法及系统
CN120578087A (zh) * 2025-06-05 2025-09-02 远大能源利用管理有限公司 一种中央空调机房系统能效实时仿真及优化方法
CN120627328A (zh) * 2025-08-13 2025-09-12 同济大学 一种面向工厂动力站房冷源系统的智能优化控制方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040011066A1 (en) * 2002-07-19 2004-01-22 Hitachi Plant Engineering & Construction Co., Ltd. Air conditioning plant and control method thereof
CN104534627A (zh) * 2015-01-14 2015-04-22 江苏联宏自动化系统工程有限公司 中央空调冷却水系统综合能效控制方法
CN111723456A (zh) * 2020-05-08 2020-09-29 华南理工大学 一种基于nsga-ⅱ算法的中央空调系统能效优化方法
CN116007072A (zh) * 2023-01-28 2023-04-25 青岛海信日立空调系统有限公司 一种中央空调系统及其控制方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5244420B2 (ja) * 2008-02-28 2013-07-24 三菱重工業株式会社 ターボ冷凍機および熱源システムならびにこれらの制御方法
CN102705957B (zh) * 2012-06-07 2014-06-11 华南理工大学 办公建筑中央空调逐时冷负荷在线预测方法及系统
SG11201810279QA (en) * 2016-06-29 2018-12-28 Kirkham Group Pte Ltd Large scale machine learning-based chiller plants modeling, optimization and diagnosis
CN110332647B (zh) * 2019-07-11 2021-02-02 四川聚智精创轨道交通科技有限公司 地铁地下车站空调系统负荷预测方法及空调系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040011066A1 (en) * 2002-07-19 2004-01-22 Hitachi Plant Engineering & Construction Co., Ltd. Air conditioning plant and control method thereof
CN104534627A (zh) * 2015-01-14 2015-04-22 江苏联宏自动化系统工程有限公司 中央空调冷却水系统综合能效控制方法
CN111723456A (zh) * 2020-05-08 2020-09-29 华南理工大学 一种基于nsga-ⅱ算法的中央空调系统能效优化方法
CN116007072A (zh) * 2023-01-28 2023-04-25 青岛海信日立空调系统有限公司 一种中央空调系统及其控制方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4607101A4

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118822040B (zh) * 2024-08-23 2025-02-18 重庆智拓能源科技有限公司 一种空调制冷机房运行系统cop预测方法
CN118822040A (zh) * 2024-08-23 2024-10-22 重庆智拓能源科技有限公司 一种空调制冷机房运行系统cop预测方法
CN119146474A (zh) * 2024-09-06 2024-12-17 北京市市政工程设计研究总院有限公司 确定多能耦合供热系统的能源组合形式的方法和装置
CN119022413A (zh) * 2024-09-13 2024-11-26 广东工业大学 一种冷水机组负荷分配方法和装置
CN119713515A (zh) * 2024-09-24 2025-03-28 辽宁睿智聚合科技有限公司 面向建筑负荷预测的中央空调系统优化控制方法
CN119123579A (zh) * 2024-11-12 2024-12-13 杭州华电华源环境工程有限公司 一种基于分层多目标优化的冰蓄冷控制方法及系统
CN119436515A (zh) * 2024-12-13 2025-02-14 珠海格力电器股份有限公司 多模块空调器机组的控制方法及装置、多模块空调器机组
CN119847310A (zh) * 2025-03-19 2025-04-18 国家工业信息安全发展研究中心 一种数据中心节能系统及方法
CN120273927A (zh) * 2025-04-17 2025-07-08 科瑞特空调集团有限公司 一体式数字化风机的节能控制系统
CN120273927B (zh) * 2025-04-17 2025-10-03 科瑞特空调集团有限公司 一体式数字化风机的节能控制系统
CN120176228A (zh) * 2025-05-21 2025-06-20 西安四腾环境科技有限公司 一种智能化的医院洁净室送风调节方法和系统
CN120578087A (zh) * 2025-06-05 2025-09-02 远大能源利用管理有限公司 一种中央空调机房系统能效实时仿真及优化方法
CN120488861A (zh) * 2025-07-08 2025-08-15 南京群顶科技股份有限公司 冷站冷却塔最佳台数频率动态调节方法及系统
CN120627328A (zh) * 2025-08-13 2025-09-12 同济大学 一种面向工厂动力站房冷源系统的智能优化控制方法

Also Published As

Publication number Publication date
EP4607101A1 (en) 2025-08-27
EP4607101A4 (en) 2026-01-21

Similar Documents

Publication Publication Date Title
WO2024156177A1 (zh) 空调系统及其控制方法
CN104134100B (zh) 一种基于云计算的节能管理系统
US7567888B2 (en) Method for evaluating and optimizing performance of chiller system
CN102455093B (zh) 制冷系统能效控制方法
CN111207485B (zh) 一种防冻结控制方法、装置、存储介质及水多联系统
CN110895016A (zh) 一种基于模糊自适应的中央空调系统节能群控方法
CN116558049A (zh) 一种基于中央空调负荷动态预测的系统及优化控制方法
WO2011106918A1 (zh) 基于云计算的电子信息系统机房能源管理控制系统及方法
CN101655272A (zh) 一种网络中央空调节能控制管理系统及其方法
CN111678247A (zh) 空调设备的运行控制方法、空调设备和计算机存储介质
WO2014019250A1 (zh) 一种优化多联机空调系统中压缩机运行控制的方法及装置
CN112460762B (zh) 一种中央空调负荷群参与电力系统调峰的控制策略
CN115875809A (zh) 机房换热设备的节能方法、装置及计算机可读存储介质
CN109612170B (zh) 一种利用宽温热泵实现的低温环境供热系统以及使用方法
CN113739371A (zh) 一种基于云端协同的中央空调系统及其控制方法
CN113887079A (zh) 考虑新能源发电不确定性的空气源热泵控制方法及系统
TW201027014A (en) Method for managing air conditioning power consumption
CN114206071A (zh) 基于双曲线冷却塔的数据中心冷却系统
CN217109938U (zh) 一种空调能效分析与调适系统
CN200975766Y (zh) 区域集中供冷冷量调节系统
CN118548644B (zh) 一种集中供液液冷储能电站及其控制方法
CN116007078A (zh) 一种制冷系统的运行参数获取方法、装置及设备
CN119983507A (zh) 冷却水系统控制方法、空调冷却水系统和及高效制冷机房
CN115468282B (zh) 一种冷水机系统及其控制方法
CN119451038A (zh) 微模块数据中心空调群控方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23918178

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023918178

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023918178

Country of ref document: EP

Effective date: 20250523

WWP Wipo information: published in national office

Ref document number: 2023918178

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE