WO2023246712A1 - 局部流量模型构建方法、装置、设备、介质和车辆 - Google Patents

局部流量模型构建方法、装置、设备、介质和车辆 Download PDF

Info

Publication number
WO2023246712A1
WO2023246712A1 PCT/CN2023/101130 CN2023101130W WO2023246712A1 WO 2023246712 A1 WO2023246712 A1 WO 2023246712A1 CN 2023101130 W CN2023101130 W CN 2023101130W WO 2023246712 A1 WO2023246712 A1 WO 2023246712A1
Authority
WO
WIPO (PCT)
Prior art keywords
coolant
model
target
heat exchange
management system
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/CN2023/101130
Other languages
English (en)
French (fr)
Inventor
张洪洋
孟莹
薛剑
马春山
刘凯峰
蒙越
宁昀鹏
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.)
Beijing Co Wheels Technology Co Ltd
Original Assignee
Beijing Co Wheels Technology 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
Application filed by Beijing Co Wheels Technology Co Ltd filed Critical Beijing Co Wheels Technology Co Ltd
Priority to US18/876,395 priority Critical patent/US20250244733A1/en
Priority to EP23826360.2A priority patent/EP4546200A4/en
Publication of WO2023246712A1 publication Critical patent/WO2023246712A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
    • F01P11/00—Component parts, details, or accessories not provided for in, or of interest apart from, groups F01P1/00 - F01P9/00
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
    • F01P7/00—Controlling of coolant flow
    • F01P7/14—Controlling of coolant flow the coolant being liquid
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00—Control of temperature
    • G05D23/19—Control of temperature characterised by the use of electric means
    • G05D23/1917—Control of temperature characterised by the use of electric means using digital means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
    • F01P2025/00—Measuring
    • F01P2025/08—Temperature
    • F01P2025/52—Heat exchanger temperature
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation

Definitions

  • the present disclosure belongs to the field of thermal management technology, and specifically relates to a local flow model construction method, device, equipment, medium and vehicle.
  • the automotive thermal management system needs to automatically adjust the cooling intensity according to driving conditions and environmental conditions to keep the corresponding components working within the optimal temperature range. Specifically, it is necessary to keep the engine operating within the corresponding optimal temperature range.
  • the temperature of the coolant in the engine When determining the temperature of the coolant in the engine, it needs to be determined based on the flow rate of the coolant. At present, when determining the flow rate of coolant, it is predicted by using the overall model of the automobile thermal management system. What is predicted is the overall flow rate of the thermal management system. However, the heat exchange components in the automobile thermal management system are intricate and complex, so each heat exchange component corresponds to There is a difference between the local flow rate of the coolant and the overall flow rate of the automobile thermal management system. If the overall flow rate of the automobile thermal management system is used to replace the local flow rate of the coolant corresponding to a certain heat exchange component in the automobile thermal management system, it is not accurate enough. of.
  • the purpose of the embodiments of the present disclosure is to provide a local flow model construction method, device, equipment, medium and vehicle, so as to quickly and accurately obtain the local flow model of the thermal management system, and thereby obtain accurate cooling water of the thermal management system.
  • the effect of local flow is to provide a local flow model construction method, device, equipment, medium and vehicle, so as to quickly and accurately obtain the local flow model of the thermal management system, and thereby obtain accurate cooling water of the thermal management system. The effect of local flow.
  • a local traffic model construction method which includes:
  • the preset model is trained to obtain a local flow model for determining the coolant at the target heat exchange component.
  • a device for building a local flow model which device includes:
  • the first building module is used to obtain the target physical model corresponding to the thermal management system based on the acquired first flow data of the thermal management system;
  • a calculation module configured to calculate the second flow rate data of the coolant at the target heat exchange component in the thermal management system based on the target physical model
  • a first determination module configured to train a preset model based on the second flow data and its corresponding target characteristic parameters for controlling the operation of the thermal management system, and obtain a value for determining the position of the coolant at the target heat exchange component. Local flow model.
  • embodiments of the present disclosure provide a local traffic model construction device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor.
  • embodiments of the present disclosure provide a computer-readable storage medium.
  • Programs or instructions are stored on the computer-readable storage medium.
  • the programs or instructions are executed by a processor, the tasks described in any embodiment of the present disclosure are implemented.
  • embodiments of the present disclosure provide a vehicle, which includes at least one of the following:
  • the local flow model building device as described in the first aspect
  • a computer-readable storage medium as described in the third aspect is described.
  • an embodiment of the present disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the local traffic model construction method described in any embodiment of the present disclosure.
  • the local flow model construction method, device, equipment, medium and vehicle obtained by the embodiments of the present disclosure obtain the target physical model corresponding to the thermal management system based on the acquired first flow data of the thermal management system; and then calculate based on the target physical model.
  • Second flow data of the coolant at the target heat exchange component in the thermal management system according to the second flow data and its corresponding target characteristic parameters for controlling the operation of the thermal management system, the preset model is trained to obtain a method for determining the location of the coolant.
  • the local flow model at the target heat exchange component can be used to accurately calculate the local flow rate of the coolant, and then the local flow rate of the coolant at the target component can be obtained based on the constructed local flow model. This calculation is simple and fast.
  • the obtained local flow rate of the coolant at the target component is accurate, which improves the accuracy and efficiency of the local flow rate of the coolant at the target component.
  • Figure 1 is a schematic diagram of the corresponding physical model of the thermal management system involved in the embodiment of the present disclosure
  • Figure 2 is a schematic flowchart of a local traffic model construction method provided by an embodiment of the present disclosure
  • Figure 3 is a schematic structural diagram of a local flow model construction device provided by an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • Figure 1 is an overall model of an automobile thermal management system.
  • the connection lines between the heat exchange components in Figure 1 can be The direction of coolant flow.
  • the flow rate of coolant it is predicted by using the overall model of the automobile thermal management system. What is predicted in this way is the overall flow rate of the thermal management system.
  • the body flow rate that is, the overall coolant flow rate in Figure 1
  • the heat exchange components in the automotive thermal management system are intricate, so the local flow rate of the coolant corresponding to each heat exchange component (for example, it can be the battery and fan in Figure 1 Is the flow rate of coolant between heat exchangers) different from the overall flow rate of the automobile thermal management system? If the overall flow rate of the automobile thermal management system is used to replace the local flow rate of the coolant corresponding to a certain heat exchange component in the automobile thermal management system , is not accurate enough.
  • embodiments of the present disclosure provide a local flow model construction method, device, equipment, medium and vehicle method.
  • the target physical model corresponding to the thermal management system is obtained.
  • the target physical model calculates the second flow data of the coolant at the target heat exchange component in the thermal management system; train the preset model based on the second flow data and its corresponding target characteristic parameters that control the operation of the thermal management system.
  • a local flow model that accurately calculates the local flow rate of the coolant can be obtained, and then the flow rate of the coolant at the target component can be obtained based on the constructed local flow model.
  • the calculation of local flow rate is simple and fast, and the obtained local flow rate of coolant at the target component is accurate, which improves the accuracy and efficiency of the local flow rate of coolant at the target component.
  • FIG. 2 is a schematic flowchart of a local traffic model construction method provided by an embodiment of the present disclosure.
  • the execution subject of the local traffic model construction method may be a server. It should be noted that the above execution subject does not constitute a limitation on the present disclosure.
  • the local traffic model construction method provided by the embodiment of the present disclosure may include steps 210 to 230.
  • Step 210 Based on the obtained first flow data of the thermal management system, obtain the target physical model corresponding to the thermal management system.
  • Step 220 Based on the target physical model, calculate the second flow rate data of the coolant at the target heat exchange component in the thermal management system.
  • Step 230 Train the preset model according to the second flow data and its corresponding target characteristic parameters for controlling the operation of the thermal management system to obtain a local flow model for determining the coolant at the target heat exchange component.
  • the target physical model corresponding to the thermal management system is obtained based on the acquired first flow data of the thermal management system; and then based on the target physical model, the cooling liquid at the target heat exchange component in the thermal management system is calculated.
  • second flow data train the preset model to obtain a local flow model for determining the coolant at the target heat exchange component, so that Obtain a local flow model that accurately calculates the local flow rate of the coolant, and then obtain the local flow rate of the coolant at the target component based on the constructed local flow model.
  • This calculation is simple and fast, and the obtained local flow rate of the coolant at the target component is obtained. Accurate, improving the accuracy and efficiency of local flow of coolant at target components.
  • the local traffic model construction method provided by the embodiment of the present disclosure is introduced in detail below.
  • Step 210 Based on the obtained first flow data of the thermal management system, obtain the target physical model corresponding to the thermal management system.
  • the first flow data can be the key flow data of the thermal management system obtained during the experiment. Specifically, it can be the overall flow data of the thermal management system, or it can be a certain part of the thermal management system in Figure 1.
  • a key heat exchange Local flow data of components for example, it can be a battery or an engine, etc.).
  • the target physical model may be a physical model corresponding to the thermal management system obtained based on the acquired first flow data of the thermal management system.
  • step 210 may specifically include:
  • the model parameters of the physical model are modified to obtain the target physical model corresponding to the thermal management system.
  • the physical model may be the overall physical model of the thermal management system as shown in FIG. 1 .
  • the model parameters of the physical model can be the water pump pressure rise of the coolant, the pressure drop of the heat exchange environment and the loss of the coolant along the pipe wall, etc. used when building the physical model.
  • an overall physical model corresponding to the thermal management system can be built, that is, the physical model in Figure 1 .
  • the correction of the model parameters of the physical model may be done manually by engineers, or it may be done automatically through other methods, which is not limited here.
  • Step 220 Based on the target physical model, calculate the second flow rate data of the coolant at the target heat exchange component in the thermal management system.
  • the target heat exchange component may be the heat exchange component where the flow rate of the coolant is to be calculated. Specifically, it can be the battery, engine or heat exchanger in Figure 1.
  • the second flow data may be flow data of the coolant at the target heat exchange component calculated based on the target physical model.
  • the flow rate of the coolant at some heat exchange components cannot be measured during the experiment, but the flow rate of the coolant at the heat exchange component is very important.
  • the overall physical model of the thermal management system target physical model
  • Traffic data second traffic data
  • the flow rate of the coolant at the engine can be calculated based on the flow rate of the coolant at the battery in Figure 1 .
  • Step 230 Train the preset model according to the second flow data and its corresponding target characteristic parameters for controlling the operation of the thermal management system to obtain a local flow model for determining the coolant at the target heat exchange component.
  • the target characteristic parameter may be a characteristic parameter that controls the operation of the thermal management system. It may also be a characteristic parameter obtained by performing preset processing on the characteristic parameter that controls the operation of the thermal management system.
  • the preset model may be a preset model. After training the preset model, a local flow model for determining the coolant at the target heat exchange component can be obtained.
  • the preset model can be a neural network model or other models that can be used to predict the local flow rate at the target heat exchange component, which is not limited here.
  • the target heat exchange component may be a heat exchange component whose local flow rate is to be predicted, for example, it may be the battery, water pump, etc. shown in Figure 1 above.
  • the local flow model may be a model used to determine the local flow rate of the coolant at the target heat exchange component.
  • the above-mentioned local flow model construction method may also include:
  • the target characteristic parameter is determined.
  • the first characteristic parameter may be a direct characteristic parameter that controls the operation of the thermal management system, such as water pump speed, temperature, valve opening, engine speed, engine torque, etc.
  • the associated characteristic parameter may be a characteristic parameter obtained by expanding the first characteristic parameter according to the corresponding relationship with the first traffic data.
  • the first characteristic parameters include water pump speed, temperature, valve opening, engine speed, and engine torque.
  • the associated characteristic parameters of the water pump speed can be obtained: the square of the speed and the square of the speed. 3rd power.
  • the associated characteristic parameters of the temperature can be obtained: the square of the temperature, the third power of the temperature, and the fourth power of the temperature.
  • the valve opening the associated characteristic parameters of the valve opening can be obtained: the square of the valve opening and the third power of the valve opening.
  • the related characteristic parameters of the engine speed and the engine torque can be obtained: the product of the engine speed and the engine torque, and the integral of the product of the engine speed and the engine torque, etc.
  • the target feature parameter may be a feature parameter based on each associated feature parameter, for example, it may be a feature parameter obtained by performing preset processing on each associated feature parameter.
  • the thermal management system by obtaining the first characteristic parameter that controls the operation of the thermal management system; and then determining at least one associated characteristic associated with the first flow data according to the corresponding relationship between the first characteristic parameter and the first flow data. Parameters; determine the target characteristic parameters according to each associated characteristic parameter, so that the target characteristic parameters can be accurately determined, and then a local flow model for determining the coolant at the target heat exchange component can be accurately constructed.
  • determining the target characteristic parameters according to each associated characteristic parameter may include:
  • Step A Input each associated feature parameter into the feature screening model in turn, and obtain the predicted traffic value corresponding to each associated feature parameter;
  • Step B For each associated feature parameter, calculate the mean square error between the predicted flow value corresponding to the associated feature parameter and the low flow value of the coolant in the thermal management system;
  • Step C Use the associated feature parameter corresponding to the smallest mean square error as the first candidate feature parameter
  • Step D Update the output of the feature screening model to the high flow value of the coolant in the thermal management system, return to steps A to C, and obtain the second candidate feature parameters;
  • Step E Use the first candidate feature parameter and the second candidate feature parameter as the target feature parameter.
  • the feature screening model can be obtained by learning each associated feature parameter and the flow value of the coolant in the thermal management system. Relationships get.
  • the feature screening model may be a generalized regression neural network (GRNN) based on joint probability distribution.
  • the input quantity of this model can be each associated characteristic parameter, and the output quantity can be the flow value of the coolant in the thermal management system.
  • Predicting the traffic value may be that after each associated feature parameter is input into the feature screening model in sequence, the feature screening model predicts the traffic value corresponding to each associated feature parameter based on each associated feature parameter.
  • the low flow value may be a flow value that is less than or equal to the first preset flow threshold.
  • the low flow value may be a lower flow value within the flow range of the coolant.
  • the first preset flow threshold here may be a preset low flow value threshold. For example, if the flow range of the coolant is between 500 and 1000, then the low flow value may be between 500 and 700.
  • the first candidate feature parameter may be a correlation feature parameter corresponding to the smallest mean square error among the predicted flow value corresponding to the calculated correlation feature parameter and the mean square error of the low flow value of the coolant in the thermal management system.
  • the high flow value may be a flow value whose flow value is greater than or equal to the second preset flow threshold.
  • the high flow rate value may be a higher flow rate value within the flow rate range of the coolant.
  • the second preset flow threshold here may be a preset high flow value threshold. For example, if the flow range of the coolant is between 500 and 1000, then the high flow value may be between 700 and 1000.
  • the second candidate feature parameter may be the associated feature parameter corresponding to the smallest mean square error among the calculated predicted flow values corresponding to each associated feature parameter and the mean square error of the high flow value of the coolant in the thermal management system.
  • the associated characteristic parameters include the product of engine speed and torque, as well as the square of the water pump speed and the cube of the water pump speed
  • all associated feature parameters are traversed, that is, the product of the engine speed and torque, and the water pump speed
  • the square and the cube of the water pump speed are respectively input into the feature screening model to obtain the predicted flow value corresponding to the product of the engine speed and torque, as well as the square of the water pump speed and the cube of the water pump speed.
  • the product is the product of the engine speed and torque
  • the predicted flow value corresponding to the product of is 550
  • the predicted flow value corresponding to the square of the water pump speed is 900
  • the predicted flow value corresponding to the cube of the water pump speed is 950.
  • the dependent variable of the feature screening model at this time (that is, the traffic standard output by the feature screening model) is 600, then calculate the mean square errors of 550, 900, and 950 and 600 respectively. By comparison, the mean square errors of 550 and 600 can be obtained If the error is the smallest, the associated characteristic parameter corresponding to 550 (the product of engine speed and torque) can be used as the first candidate characteristic parameter.
  • the first candidate feature parameter and the second candidate feature parameter are used as the target feature parameters, that is, the product of the engine speed and torque, and the square of the water pump speed are used as the final target feature parameters.
  • the first candidate characteristic parameter and the second candidate characteristic parameter may be obtained.
  • the first candidate feature parameter and the second candidate feature parameter are sorted from low to high according to their mean square error with the flow value of the coolant in the thermal management system, and then the top N feature parameters with the highest ranking are obtained as the final target feature. parameter. This ensures accuracy and avoids feature redundancy.
  • the first four feature parameters whose mean square error reduces to 0 are selected as the final target feature parameters.
  • target characteristic parameters that can be used to construct a local flow model of the coolant at the target heat exchange component are selected, so that an accurate coolant flow model can be obtained Local flow model at the target heat exchange component.
  • step 230 in order to obtain an accurate local flow model of the coolant at the target heat exchange component, may specifically include:
  • the initial local flow model with the highest accuracy is selected from each initial local flow model as the local flow model used to determine the local flow rate of the coolant at the target heat exchange component.
  • the initial local traffic model may be a model obtained by training a preset model using training samples.
  • the second flow data obtained in step 230 and its corresponding target characteristic parameters for controlling the operation of the thermal management system may be randomly divided into a training set and a test set (specifically, it may be based on 85% and 15% proportion), and then use the training samples to train the preset model to obtain at least one initial local flow model used to determine the coolant at the target heat exchange component, and then use the k test to calculate the prediction of each initial local flow model The accuracy of the local flow rate of the coolant at the target heat exchange component. Based on this accuracy, the initial local flow model with the highest accuracy is selected from each initial local flow model, and then the test set is used to compare the selected accuracy.
  • the highest initial local flow model is tested and verified, and the verification result is obtained (that is, whether the most accurate initial local flow model can accurately predict the local flow rate at the target heat exchange component). If the verification result is good, the accurate The initial local flow model with the highest accuracy is used as a local training model to determine the local flow rate of the coolant at the target heat exchange component, so that the most accurate local flow model can be obtained.
  • the obtained at least one initial local flow model for determining the coolant at the target heat exchange component conduct testing and verification using the test set, and then obtain the results of each initial local flow model. Test the results, and then use the k test to calculate the accuracy and test accuracy of the local flow rate of the coolant at the target heat exchange component predicted by each initial local flow model. Based on this accuracy and test accuracy, select the method used to determine the target heat exchanger.
  • the local training model of the local flow rate of the coolant at the component can be specifically selected based on comprehensive accuracy and test accuracy to determine the local training model for determining the local flow rate of the coolant at the target heat exchange component.
  • At least one initial local flow model for determining the cooling liquid at the target heat exchange component is obtained, and then the cooling predicted by each initial local flow model is calculated.
  • the accuracy of the local flow rate of the coolant at the target heat exchange component Based on this accuracy, the initial local flow model with the highest accuracy is selected from each initial local flow model as used to determine the local flow rate of the coolant at the target heat exchange component. local training model, so that the most accurate local traffic model can be obtained.
  • the above-mentioned local traffic model construction method may further include:
  • the outlet temperature of the coolant after heat exchange between the target heat exchange component and the coolant is obtained.
  • the target characteristic parameters that control the operation of the thermal management system can be obtained, and then the target characteristic parameters can be input into the local flow model to obtain cooling
  • the local flow rate of the liquid at the target heat exchange component Based on this local flow rate, the outlet water temperature of the coolant after the target heat exchange component transfers heat to the coolant can be obtained. In this way, the cooling of the target heat exchange component after transferring heat to the coolant can be accurately predicted.
  • the outlet water temperature of the liquid after constructing a local flow model corresponding to the target heat exchange component.
  • obtaining the outlet water temperature of the coolant after the target heat exchange component transfers heat to the coolant based on the local flow rate may specifically include:
  • the outlet temperature of the coolant after the target heat exchange component transfers heat to the coolant is obtained.
  • the first heat exchange amount may be based on the local flow rate and the specific heat of the target heat exchange component to determine the heat exchange amount between the target heat exchange component of the characteristic length and the coolant.
  • the relationship between the temperature of the target heat exchange component and the outlet temperature of the coolant may be based on the first heat exchange amount and the integration of the length of the target heat exchange component.
  • the relationship between the temperature of the target heat exchange component and the outlet temperature of the coolant may be based on the first heat exchange amount and the integration of the length of the target heat exchange component.
  • Equation (1) is the local flow rate of the coolant; C p is the constant pressure specific heat of the coolant; dT W is the temperature change of the coolant caused by the target heat exchange component of the characteristic length transferring heat to the coolant; Q is the target heat transfer due to the characteristic length After the component transfers heat to the coolant, the heat of the coolant changes due to the temperature change of the coolant (ie, the first heat change amount).
  • T B is the temperature of the target heat exchange component
  • T w is the temperature of the coolant
  • ⁇ is the heat transfer coefficient between the target heat exchange component and the coolant (the coefficient is a constant)
  • L c is the target
  • the characteristic length of the heat exchange component represents the heat exchange area corresponding to each unit length
  • x is the length of the target heat exchange component.
  • T w,out is the outlet temperature of the coolant
  • T w,in is the inlet temperature of the coolant
  • the characteristic length of the target heat exchange component is used to solve the outlet water temperature of the coolant after the target heat exchange component transfers heat to the coolant. This can avoid the local flow model constructed above to predict the outlet water temperature.
  • the temperature fluctuation problem is used to calibrate the local flow model.
  • the execution subject may be a local traffic model construction device, or a control module in the local traffic model construction device for executing the local traffic model construction method.
  • the present disclosure also provides a local flow model construction device.
  • the local traffic model construction device provided by the embodiment of the present disclosure will be described in detail below with reference to FIG. 3 .
  • Figure 3 is a schematic structural diagram of a device for building a local flow model according to an exemplary embodiment.
  • the local traffic model building device 300 may include:
  • the first building module 310 is used to obtain the target physical model corresponding to the thermal management system based on the acquired first flow data of the thermal management system;
  • the calculation module 330 is configured to calculate the second flow rate data of the coolant at the target heat exchange component in the thermal management system based on the target physical model;
  • the first determination module 330 is configured to train a preset model based on the second flow data and its corresponding target characteristic parameters for controlling the operation of the thermal management system to obtain a method for determining the position of the coolant at the target heat exchange component. local flow model.
  • the target physical model corresponding to the thermal management system is obtained through the first building module based on the acquired first flow data of the thermal management system; and then the target physical model in the thermal management system is calculated based on the calculation module.
  • the local flow model at the target heat exchange component can be used to accurately calculate the local flow rate of the coolant, and then the local flow rate of the coolant at the target component can be obtained based on the constructed local flow model. This calculation is simple and fast.
  • the obtained local flow rate of the coolant at the target component is accurate, which improves the accuracy and efficiency of the local flow rate of the coolant at the target component.
  • the above-mentioned local flow model construction device may further include:
  • a first acquisition module used to acquire the first characteristic parameters that control the operation of the thermal management system
  • a third determination module configured to determine at least one associated characteristic parameter associated with the first flow data based on the corresponding relationship between the first characteristic parameter and the first flow data;
  • the fourth determination module is used to determine the target characteristic parameters according to each of the associated characteristic parameters.
  • the fourth determination module is specifically used to:
  • Step A Input each of the associated feature parameters into the feature screening model in turn, and obtain the predicted traffic value corresponding to each of the associated feature parameters; wherein, the feature screening model is based on learning each of the associated feature parameters and heat. The relationship between the flow value of the coolant in the management system is obtained;
  • Step B For each associated characteristic parameter, calculate the mean square error between the predicted flow value corresponding to the associated characteristic parameter and the low flow value of the coolant in the thermal management system; wherein the low flow value is a flow value less than or equal to The flow value of the first preset flow threshold;
  • Step C Use the associated feature parameter corresponding to the smallest mean square error as the first candidate feature parameter
  • Step D Update the output of the feature screening model to the high flow value of the coolant in the thermal management system, and return to steps A to C to obtain the second candidate feature parameter; wherein the high flow value is The flow value is greater than or equal to the flow value of the second preset flow threshold;
  • Step E Use the first candidate feature parameter and the second candidate feature parameter as target feature parameters.
  • the second determination module 330 may be used to:
  • an initial local flow model with the highest accuracy is selected from each initial local flow model as the local flow model used to determine the local flow rate of the coolant at the target heat exchange component.
  • the above-mentioned local traffic model construction device may further include:
  • the fifth determination module is used to input the target characteristic parameters into the local flow model to obtain the local flow rate of the cooling liquid at the target heat exchange component;
  • a sixth determination module is used to obtain the outlet water temperature of the coolant after heat exchange between the target heat exchange component and the coolant based on the local flow rate.
  • the sixth determination module may be specifically used to:
  • the outlet water temperature of the coolant after the target heat exchange component transfers heat to the coolant is obtained.
  • the local traffic model construction device provided by the embodiments of the present disclosure can be used to execute the local traffic model construction method provided by the above method embodiments. Its implementation principles and technical effects are similar, and for the sake of brief introduction, they will not be described again here.
  • embodiments of the present disclosure also provide an electronic device.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. As shown in Figure 4, the electronic device may include a processor 401 and a memory 402 storing computer programs or instructions.
  • the above-mentioned processor 401 may include a central processing unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits that may be configured to implement embodiments of the present disclosure.
  • CPU central processing unit
  • ASIC Application Specific Integrated Circuit
  • Memory 402 may include bulk storage for data or instructions.
  • the memory 402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive or two or more A combination of many of the above.
  • Memory 402 may include removable or non-removable (or fixed) media, where appropriate.
  • the memory 402 may be internal or external to the integrated gateway disaster recovery device.
  • memory 402 is non-volatile solid-state memory.
  • Memory may include read-only memory (Read Only Memory image, ROM), random access memory (Random-Access Memory, RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical/tangible devices Memory storage device.
  • ROM Read Only Memory image
  • RAM random access memory
  • magnetic disk storage media devices magnetic disk storage media devices
  • optical storage media devices flash memory devices
  • electrical, optical or other physical/tangible devices Memory storage device generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or multiple processors), it is operable to perform the operations described in the local traffic model construction method provided by the above embodiment.
  • the processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any of the local traffic model construction methods in the above embodiments.
  • the electronic device may also include a communication interface 403 and a bus 410.
  • the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 and complete communication with each other.
  • the communication interface 403 is mainly used to implement communication between modules, devices, units and/or devices in the embodiments of the present disclosure.
  • Bus 410 includes hardware, software, or both, coupling components of an electronic device to one another.
  • the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) Bus, Infinite Bandwidth Interconnect, Low Pin Count (LPC) Bus, Memory Bus, Micro Channel Architecture (MCA) Bus, Peripheral Component Interconnect (PCI) Bus, PCI-Express (PCI-X) Bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of these.
  • bus 410 may include one or more buses.
  • the electronic device can execute the local traffic model building method in the embodiment of the present disclosure, thereby realizing the local traffic model building method described in FIG. 2 .
  • the embodiment of the present disclosure can provide a readable storage medium for implementation.
  • the readable storage medium stores program instructions; when the program instructions are executed by the processor, any one of the local traffic model construction methods in the above embodiments is implemented.
  • the embodiment of the present disclosure can provide a vehicle for implementation.
  • the vehicle includes the local flow model construction device, the local flow model construction device and the computer-readable storage medium in the above embodiment.
  • the functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware or a combination thereof.
  • it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, or the like.
  • ASIC application specific integrated circuit
  • elements of the disclosure are programs or code segments that are used to perform required tasks.
  • the program or code segments may be stored in a machine-readable medium or transmitted over a transmission medium or communications link via a data signal carried in a carrier wave.
  • "Machine-readable medium" may include any medium capable of storing or transmitting information.
  • machine-readable media examples include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like.
  • Code segments may be downloaded via computer networks such as the Internet, intranets, and the like.
  • Such a processor may be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It will also be understood that each block in the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can also be implemented by special purpose hardware that performs the specified functions or actions, or can be implemented by special purpose hardware and A combination of computer instructions.
  • An embodiment of the present disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the local traffic model construction method described in any embodiment of the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • Chemical & Material Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Feedback Control In General (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

本公开提供了一种局部流量模型构建方法，包括：基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型；基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据；根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。

Description

局部流量模型构建方法、装置、设备、介质和车辆 技术领域
本公开属于热管理技术领域，具体涉及一种局部流量模型构建方法、装置、设备、介质和车辆。
背景技术
汽车热管理系统需根据行车工况和环境条件，自动调节冷却强度以保持相应的部件在最佳的温度范围内工作，具体的是保持发动机在相应的最佳温度范围内工作。
在确定发动机中的冷却液的温度时，需要根据冷却液的流量来进行确定。目前在确定冷却液的流量时是利用汽车热管理系统的整体模型来预测的，如此预测的为热管理系统的整体流量，但汽车热管理系统内各换热部件错综复杂，故各换热部件对应的冷却液的局部流量与汽车热管理系统的整体流量是存在差异的，若用汽车热管理系统的整体流量代替汽车热管理系统中某一换热部件对应的冷却液的局部流量，是不够精确的。
发明内容
本公开实施例的目的是提供一种局部流量模型构建方法、装置、设备、介质和车辆，以实现快速精确的得到热管理系统的局部流量模型，进而可得到精确的热管理系统的冷却水的局部流量的效果。
第一方面，提供了一种局部流量模型构建方法，该方法包括：
基于获取的热管理系统的第一流量数据，得到所述热管理系统对应的目标物理模型；
基于所述目标物理模型，计算所述热管理系统中目标换热部件处冷却液的第二流量数据；
根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
第二方面，提供了一种局部流量模型构建装置，该装置包括：
第一构建模块，用于基于获取的热管理系统的第一流量数据，得到所述热管理系统对应的目标物理模型；
计算模块，用于基于所述目标物理模型，计算所述热管理系统中目标换热部件处冷却液的第二流量数据；
第一确定模块，用于根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
第三方面，本公开实施例提供了一种局部流量模型构建设备，该设备包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现本公开任一实施例所述的局部流量模型构建方法的步骤。
第四方面，本公开实施例提供了一种计算机可读存储介质，所述计算机可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现本公开任一实施例所述的局部流量模 型构建方法的步骤。
第五方面，本公开实施例提供了一种车辆，所述车辆包括以下至少一种：
如第一方面所述的局部流量模型构建装置；
如第二方面所述的局部流量模型构建设备；
如第三方面所述的计算机可读存储介质。
第六方面，本公开实施例提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现本公开任一实施例所述的局部流量模型构建方法。
本公开实施例提供的局部流量模型构建方法、装置、设备、介质和车辆，通过基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型；然后基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据；根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型，如此可得到精确计算冷却液的局部流量的局部流量模型，进而可基于构建的该局部流量模型得到冷却液在目标部件处的局部流量，如此计算简单快速，且得到的冷却液在目标部件处的局部流量精确，提升了冷却液在目标部件处的局部流量的精确性和高效性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是本公开实施例涉及的热管理系统对应的物理模型示意图；
图2是本公开实施例提供的一种局部流量模型构建方法的流程示意图；
图3是本公开实施例提供的一种局部流量模型构建装置的结构示意图；
图4是本公开实施例提供的一种电子设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不是全部的实施例。
在现有技术中，如图1为汽车热管理系统的整体模型，在图1中各换热部件(例如图1中的电池、风扇换热器和发动机等)之间的连接线可以是了冷却液的流动方向。目前在确定冷却液的流量时是利用汽车热管理系统的整体模型来预测的，如此预测的为热管理系统的整 体流量(即为图1中的整体冷却液的流量)，但汽车热管理系统内各换热部件错综复杂，故各换热部件对应的冷却液的局部流量(例如可以是图1中电池与风扇换热器之间的冷却液的流量)与汽车热管理系统的整体流量是否差异的，若用汽车热管理系统的整体流量代替汽车热管理系统中某一换热部件对应的冷却液的局部流量，是不够精确的。
为了解决上述问题，本公开实施例提供了一种局部流量模型构建方法、装置、设备、介质和车辆方法，通过基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型；然后基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据；根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型，如此可得到精确计算冷却液的局部流量的局部流量模型，进而可基于构建的该局部流量模型得到冷却液在目标部件处的局部流量，如此计算简单快速，且得到的冷却液在目标部件处的局部流量精确，提升了冷却液在目标部件处的局部流量的精确性和高效性。
下面结合附图，通过具体的实施例及其应用场景对本公开实施例提供的局部流量模型构建方法进行详细地说明。
图2是本公开实施例所提供的一种局部流量模型构建方法的流程示意图，该局部流量模型构建方法的执行主体可以为服务器，需要说明的是，上述执行主体并不构成对本公开的限定。
如图2所示，本公开实施例提供的局部流量模型构建方法可以包括步骤210-步骤230。
步骤210、基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型。
步骤220、基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据。
步骤230、根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
在本公开的实施例中，通过基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型；然后基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据；根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型，如此可得到精确计算冷却液的局部流量的局部流量模型，进而可基于构建的该局部流量模型得到冷却液在目标部件处的局部流量，如此计算简单快速，且得到的冷却液在目标部件处的局部流量精确，提升了冷却液在目标部件处的局部流量的精确性和高效性。
下面详细介绍本公开实施例提供的局部流量模型构建方法。
步骤210、基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型。
其中，第一流量数据可以是在实验的过程中，获取的热管理系统的关键的流量数据，具体的可以是热管理系统的整体流量数据，也可以是图1中的热管理系统中的某一关键的换热 部件(例如可以是电池或者发动机等)的局部流量数据。
目标物理模型可以是根据获取的热管理系统的第一流量数据，所得到的与热管理系统对应的物理模型。
在本公开的一些实施例中，为了精确得到目标物理模型，步骤210具体可以包括：
基于获取的热管理系统的第一流量数据，构建热管理系统对应的物理模型；
基于第一流量数据，对物理模型的模型参数进行修正，得到热管理系统对应的目标物理模型。
其中，物理模型可以是上述如图1所示的热管理系统的整体的物理模型。
物理模型的模型参数可以是构建物理模型时所用到的冷却液的水泵压升、换热环境的压降和冷却液的沿程管壁的损耗等。
在本公开的一些实施例中，通过获取的热管理系统的第一流量数据，可搭建出热管理系统对应的整体的物理模型，即图1中的物理模型。
在本公开的一些实施例中，如何构建出热管理系统对应的整体的物理模型属于现有技术，在此不再赘述。
由于知道热管理系统的物理模型在某一对应的流量数据的情况下，其模型参数是怎样的，故可根据第一流量数据，对物理模型的模型参数进行修正，得到热管理系统对应的目标物理模型。
在本公开的一些实施例中，对物理模型的模型参数进行修正可以是工程师手动修正，也可以是通过其他方式进行自动修正，在此不做限定。
步骤220、基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据。
其中，目标换热部件可以是要计算的此处的冷却液的流量的换热部件。具体的可以是图1中电池、发动机或换热器等。
第二流量数据可以是基于目标物理模型计算出的目标换热部件处冷却液的流量数据。
在本公开的一些实施例中，由于在实验过程中，有些换热部件处的冷却液的流量无法测量得到，但该换热部件的处的冷却液的流量是很重要的。且热管理系统的整体的物理模型(目标物理模型)可以简单计算出该换热部件的处的冷却液的流量，故可以根据目标物理模型计算出热管理系统中目标换热部件处冷却液的流量数据(第二流量数据)。例如可以是根据图1中的电池处冷却液的流量，计算出发动机处冷却液的流量。
步骤230、根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
其中，目标特征参数可以是控制热管理系统运行的特征参数。还可以是对控制热管理系统运行的特征参数进行预设的处理后所得到的特征参数。
预设模型可以是预先设置的模型，对该预设模型进行训练后，可得到用于确定冷却液在目标换热部件处的局部流量模型。该预设模型可以是神经网络模型，还可以是其他可用于预测目标换热部件处的局部流量的模型，这里不做限定。
目标换热部件可以是要预测局部流量的换热部件，例如可以是上述图1中电池、水泵等。
局部流量模型可以是用于确定冷却液在目标换热部件处的局部流量的模型。
在本公开的一些实施例中，为了进一步精确构建用于确定冷却液在目标换热部件处的局部流量模型，在步骤230之前，上述所涉及的局部流量模型构建方法还可以包括：
获取控制热管理系统运行的第一特征参数；
根据第一特征参数与第一流量数据之间的对应关系，确定与第一流量数据关联的至少一个关联特征参数；
根据各关联特征参数，确定目标特征参数。
其中，第一特征参数可以是控制热管理系统运行的直接特征参数，例如可以是水泵转速、温度、阀门开度、发动机转速和发动机扭矩等。
关联特征参数可以是根据与第一流量数据的对应关系，对第一特征参数进行扩展后得到的特征参数。
在一个示例中，第一特征参数有水泵转速、温度、阀门开度、发动机转速和发动机扭矩，对上述第一特征参数分别进行扩展，可得到水泵转速的关联特征参数：转速的平方和转速的3次方。对温度进行扩展，可得到温度的关联特征参数：温度的平方、温度的3次方和温度的4次方。对阀门开度进行扩展，可得到阀门开度的关联特征参数：阀门开度的平方和阀门开度的3次方。对发动机转速和发动机扭矩进行扩展，可得到发动机转速和发动机扭矩的关联特征参数：发动机转速和发动机扭矩的乘积，以及发动机转速和发动机扭矩的乘积的积分等。
目标特征参数可以是基于各关联特征参数的特征参数，例如可以是对各关联特征参数进行预设处理，得到的特征参数。
在本公开的实施例中，通过获取控制热管理系统运行的第一特征参数；然后根据第一特征参数与第一流量数据之间的对应关系，确定与第一流量数据关联的至少一个关联特征参数；根据各关联特征参数，确定目标特征参数，如此可精确确定目标特征参数，进而精确构建出用于确定冷却液在目标换热部件处的局部流量模型。
在本公开的一些实施例中，为了精确得到目标特征参数，所述根据各关联特征参数，确定目标特征参数，可以包括：
步骤A、将各关联特征参数分别依次输入到特征筛选模型中，分别得到与各关联特征参数对应的预测流量值；
步骤B、针对每个关联特征参数，计算关联特征参数对应的预测流量值与热管理系统中冷却液的低流量值的均方误差；
步骤C、将最小的均方误差对应的关联特征参数，作为第一候选特征参数；
步骤D、将所特征筛选模型的输出更新为热管理系统中冷却液的高流量值，返回执行步骤A至C，得到第二候选特征参数；
步骤E、将第一候选特征参数和第二候选特征参数，作为目标特征参数。
其中，特征筛选模型可以是通过学习各关联特征参数和热管理系统中冷却液的流量值的 关系得到。
在本公开的一些实施例中，特征筛选模型可以是基于联合概率分布的广义回归神经网络(generalized regression neural network，GRNN)。该模型的输入量可以是各关联特征参数，输出量可以是热管理系统中冷却液的流量值。
预测流量值可以是将各关联特征参数分别依次输入到特征筛选模型中后，特征筛选模型基于各关联特征参数，预测出的与各关联特征参数对应的流量值。
低流量值可以是流量值小于或等于第一预设流量阈值的流量值。该低流量值可以是在冷却液的流量范围内的一个较低的流量值。
这里的第一预设流量阈值可以是预先设置的低流量值的阈值，例如冷却液的流量范围为500-1000之间，则低流量值可以是500-700之间。
第一候选特征参数可以是计算出的关联特征参数对应的预测流量值与热管理系统中冷却液的低流量值的均方误差中最小的均方误差对应的关联特征参数。
高流量值可以是流量值大于或等于第二预设流量阈值的流量值。该高流量值可以是在冷却液的流量范围内的一个较高的流量值。
这里的第二预设流量阈值可以是预先设置的高流量值的阈值，例如冷却液的流量范围为500-1000之间，则高流量值可以是700-1000之间。
第二候选特征参数可以是计算出的各关联特征参数对应的预测流量值与热管理系统中冷却液的高流量值的均方误差中最小的均方误差对应的关联特征参数。
在一个示例中，若关联特征参数有发动机转速和扭矩的乘积，以及水泵转速的平方和水泵转速的3次方，则遍历所有的关联特征参数，即将发动机转速和扭矩的乘积，以及水泵转速的平方和水泵转速的3次方分别输入到特征筛选模型中，分别得到与发动机转速和扭矩的乘积，以及水泵转速的平方和水泵转速的3次方对应的预测流量值，若与发动机转速和扭矩的乘积对应的预测流量值为550，与水泵转速的平方对应的预测流量值为900，与水泵转速的3次方对应的预测流量值为950。若特征筛选模型此时的因变量(即该特征筛选模型的输出的流量标准)为600，则分别计算550、900和950与600的均方误差，通过比较，可得到550与600的均方误差最小，则可将550对应的关联特征参数(发动机转速和扭矩的乘积)作为第一候选特征参数。
继续上述示例，将特征筛选模型此时的输出替换为高流量值，例如可以是850。然后继续将发动机转速和扭矩的乘积，以及水泵转速的平方和水泵转速的3次方分别输入到特征筛选模型中，分别得到与发动机转速和扭矩的乘积，以及水泵转速的平方和水泵转速的3次方对应的预测流量值，若与发动机转速和扭矩的乘积对应的预测流量值为550，与水泵转速的平方对应的预测流量值为900，与水泵转速的3次方对应的预测流量值为950。则分别计算550、900和950与850的均方误差，通过比较，可得到900与850的均方误差最小，则可将900对应的关联特征参数(水泵转速的平方)作为第二候选特征参数。
然后将第一候选特征参数和第二候选特征参数作为目标特征参数，即将发动机转速和扭矩的乘积，以及水泵转速的平方作为最终的目标特征参数。
在本公开的一些实施例中，为了避免构建冷却液在目标换热部件处的局部流量模型的目标特征参数的冗余，可以在得到第一候选特征参数和第二候选特征参数后，将第一候选特征参数和第二候选特征参数按照其与热管理系统中冷却液的流量值的均方误差，由低到高进行排序，然后获取排序靠前的前N个特征参数作为最终的目标特征参数。如此即可保证精度，还可避免特征冗余。在一个示例中，选取均方误差降低至0的前4个特征参数作为最终的目标特征参数。
在本公开的实施例中，通过将各关联特征参数利用特征筛选模型进行筛选，选取出可用于构建冷却液在目标换热部件处的局部流量模型的目标特征参数，如此可得到精确的冷却液在目标换热部件处的局部流量模型。
在本公开的一些实施例中，为了得到精确的冷却液在目标换热部件处的局部流量模型，步骤230具体可以包括：
基于第二流量数据及其对应的控制热管理系统运行的目标特征参数，构建训练样本；
基于训练样本对预设模型进行训练，得到至少一个用于确定冷却液在目标换热部件处的初始局部流量模型；
获取各初始局部流量模型在计算冷却液在目标换热部件处的局部流量时的精确度；
基于精确度，从各初始局部流量模型中选取出精确度最高的初始局部流量模型，作为用于确定目标换热部件处冷却液局部流量的局部流量模型。
其中，初始局部流量模型可以是利用训练样本对预设模型进行训练后，所得到的模型。
在本公开的一些实施例中，可以是将步骤230获取的第二流量数据及其对应的控制热管理系统运行的目标特征参数随机划分为训练集和测试集(具体的可以是按照85％和15％的比例进行划分)，然后利用训练样本对预设模型进行训练，得到至少一个用于确定冷却液在目标换热部件处的初始局部流量模型，然后利用k检验计算各初始局部流量模型预测出的冷却液在目标换热部件处的局部流量的精确度，根据该精确度，从各初始局部流量模型中选取出精确度最高的初始局部流量模型，然后利用测试集对选取出的精确度最高的初始局部流量模型进行测试验证，得到验证结果(即该精确度最高的初始局部流量模型是否可以精确预测出目标换热部件处的局部流量)，若该验证结果良好，则可将该精确度最高的初始局部流量模型作为用于确定目标换热部件处冷却液局部流量的局部训练模型，如此可得到最为精确的局部流量模型。
在本公开的一些实施例中，还可以是将得到的至少一个用于确定冷却液在目标换热部件处的初始局部流量模型，分别利用测试集进行测试验证，然后得到各初始局部流量模型的测试结果，然后利用k检验计算各初始局部流量模型预测出的冷却液在目标换热部件处的局部流量的精确度和测试精度，基于该精确度和测试精度来选取出用于确定目标换热部件处冷却液局部流量的局部训练模型，具体的可以是综合精确度和测试精度来选取用于确定目标换热部件处冷却液局部流量的局部训练模型。
在本公开的实施例中，通过利用训练样本对预设模型进行训练，得到至少一个用于确定冷却液在目标换热部件处的初始局部流量模型，然后计算各初始局部流量模型预测出的冷却 液在目标换热部件处的局部流量的精确度，根据该精确度，从各初始局部流量模型中选取出精确度最高的初始局部流量模型，作为用于确定目标换热部件处冷却液局部流量的局部训练模型，如此可得到最为精确的局部流量模型。
在本公开的一些实施例中，在步骤230之后，上述所涉及的局部流量模型构建方法还可以包括：
将目标特征参数输入至局部流量模型中，得到冷却液在目标换热部件处的局部流量；
基于局部流量，得到目标换热部件与冷却液热交换后冷却液的出水温度。
在本公开的实施例中，在构建出目标换热部件对应的局部流量模型之后，可获取到控制热管理系统运行的目标特征参数，然后将该目标特征参数输入到局部流量模型中，得到冷却液在目标换热部件处的局部流量，根据该局部流量，可得到目标换热部件传热给冷却液后冷却液的出水温度，如此可精确预测出目标换热部件传热给冷却液后冷却液的出水温度。
在本公开的一些实施例中，所述基于局部流量，得到目标换热部件传热给冷却液后冷却液的出水温度，具体可以包括：
基于局部流量，以及目标换热部件的比热，确定特征长度的目标换热部件给冷却液传热后冷却液的第一热量变化量；
基于第一热量变化量，对目标换热部件的长度进行积分，得到目标换热部件的温度与冷却液的出口温度的关系式；
基于关系式，得到目标换热部件传热给冷却液后冷却液的出水温度。
其中，第一换热量可以是基于局部流量，以及目标换热部件的比热，确定特征长度的目标换热部件与冷却液的换热量。
目标换热部件的温度与冷却液的出口温度的关系式可以是基于第一换热量，对目标换热部件的长度进行积分后所得到的目标换热部件的温度与冷却液的出口温度之间的关系式。
在本公开的一些实施例中，在稳态条件下，目标换热部件给冷却液传热后导致冷却液的温度变化，由于该温度变化导致的冷却液热量(即第一热量变化量)变化如下公式(1)所示：
在公式(1)中，为冷却液的局部流量；Cp为冷却液的定压比热；dTW为特征长度的目标换热部件给冷却液传热后导致冷却液的温度变化；Q为由于特征长度的目标换热部件给冷却液传热后导致冷却液的温度变化导致的冷却液热量变化(即第一热量变化量)。
然后如下的公式(2)所示的目标换热部件与冷却液的换热关系式，将公式(1)和公式(2)进行联立，然后对目标换热部件的长度进行积分，得到如公式(3)所示的目标换热部件的温度与冷却液的出口温度的关系式。
Q＝α*dA*(TB-Tw)＝α*Lc*dx*(TB-Tw)      (2)
在公式(2)中TB为目标换热部件的温度；Tw为冷却液的温度；α为目标换热部件与冷却液之间的换热系数(该系数为常数)；Lc为目标换热部件的特征长度，表示每单位长度对应的换热面积；x为目标换热部件的长度。
在公式(3)中，Tw，out为冷却液的出水温度，Tw,in为冷却液的入水温度。
如此可基于公式(3)得到目标换热部件传热给冷却液后冷却液的出水温度。
在本公开的实施例中，通过利用目标换热部件的特征长度来进行求解目标换热部件传热给冷却液后冷却液的出水温度，如此可避免上述构建的局部流量模型在预测出水温度时的温度波动问题，以用于校准局部流量模型。
需要说明的是，本公开实施例提供的局部流量模型构建方法，执行主体可以为局部流量模型构建装置，或者该局部流量模型构建装置中的用于执行局部流量模型构建方法的控制模块。
基于与上述的局部流量模型构建方法相同的发明构思，本公开还提供了一种局部流量模型构建装置。下面结合图3对本公开实施例提供的局部流量模型构建装置进行详细说明。
图3是根据一示例性实施例示出的一种局部流量模型构建装置的结构示意图。
如图3所示，该局部流量模型构建装置300可以包括：
第一构建模块310，用于基于获取的热管理系统的第一流量数据，得到所述热管理系统对应的目标物理模型；
计算模块330，用于基于所述目标物理模型，计算所述热管理系统中目标换热部件处冷却液的第二流量数据；
第一确定模块330，用于根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
在本公开的实施例中，通过第一构建模块基于获取的热管理系统的第一流量数据，得到热管理系统对应的目标物理模型；然后基于计算模块基于目标物理模型，计算热管理系统中目标换热部件处冷却液的第二流量数据；基于第一确定模块根据第二流量数据及其对应的控制热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型，如此可得到精确计算冷却液的局部流量的局部流量模型，进而可基于构建的该局部流量模型得到冷却液在目标部件处的局部流量，如此计算简单快速，且得到的冷却液在目标部件处的局部流量精确，提升了冷却液在目标部件处的局部流量的精确性和高效性。
在本公开的一些实施例中，为了进一步精确构建用于确定冷却液在目标换热部件处的局部流量模型，上述所涉及的局部流量模型构建装置还可以包括：
第一获取模块，用于获取控制所述热管理系统运行的第一特征参数；
第三确定模块，用于根据所述第一特征参数与所述第一流量数据之间的对应关系，确定与所述第一流量数据关联的至少一个关联特征参数；
第四确定模块，用于根据各所述关联特征参数，确定目标特征参数。
在本公开的一些实施例中，为了精确得到目标特征参数，所述第四确定模块具体用于：
步骤A、将各所述关联特征参数分别依次输入到特征筛选模型中，分别得到与各所述关联特征参数对应的预测流量值；其中，所述特征筛选模型是通过学习各关联特征参数和热管理系统中冷却液的流量值的关系得到；
步骤B、针对每个关联特征参数，计算所述关联特征参数对应的预测流量值与热管理系统中冷却液的低流量值的均方误差；其中，所述低流量值为流量值小于或等于第一预设流量阈值的流量值；
步骤C、将最小的均方误差对应的关联特征参数，作为第一候选特征参数；
步骤D、将所述特征筛选模型的输出更新为所述热管理系统中所述冷却液的高流量值，返回执行步骤A至C，得到第二候选特征参数；其中，所述高流量值为流量值大于或等于第二预设流量阈值的流量值；
步骤E、将所述第一候选特征参数和所述第二候选特征参数，作为目标特征参数。
在本公开的一些实施例中，为了得到精确的冷却液在目标换热部件处的局部流量模型，第二确定模块330具体可以用于：
根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，构建训练样本；
基于所述训练样本对预设模型进行训练，得到至少一个用于确定冷却液在目标换热部件处的初始局部流量模型；
获取各初始局部流量模型在计算所述冷却液在目标换热部件处的局部流量时的精确度；
基于所述精确度，从各初始局部流量模型中选取出精确度最高的初始局部流量模型，作为用于确定目标换热部件处冷却液局部流量的局部流量模型。
在本公开的一些实施例中，上述所涉及的局部流量模型构建装置还可以包括：
第五确定模块，用于将所述目标特征参数输入至所述局部流量模型中，得到所述冷却液在所述目标换热部件处的局部流量；
第六确定模块，用于基于所述局部流量，得到所述目标换热部件与所述冷却液热交换后所述冷却液的出水温度。
在本公开的一些实施例中，第六确定模块具体可以用于：
基于所述局部流量，以及所述目标换热部件的比热，确定特征长度的所述目标换热部件传热给冷却液后所述冷却液的第一热量变化量；
基于所述第一热量变化量，对所述目标换热部件的长度进行积分，得到所述目标换热部件的温度与所述冷却液的出口温度的关系式；
基于所述关系式，得到所述目标换热部件传热给所述冷却液后所述冷却液的出水温度。
本公开实施例提供的局部流量模型构建装置，可以用于执行上述各方法实施例提供的局部流量模型构建方法，其实现原理和技术效果类似，为简介起见，在此不再赘述。
基于同一发明构思，本公开实施例还提供了一种电子设备。
图4是本公开实施例提供的一种电子设备的结构示意图。如图4所示，电子设备可以包括处理器401以及存储有计算机程序或指令的存储器402。
具体地，上述处理器401可以包括中央处理器(CPU)，或者特定集成电路(Application Specific Integrated Circuit，ASIC)，或者可以被配置成实施本公开实施例的一个或多个集成电路。
存储器402可以包括用于数据或指令的大容量存储器。举例来说而非限制，存储器402可包括硬盘驱动器(Hard Disk Drive，HDD)、软盘驱动器、闪存、光盘、磁光盘、磁带或通用串行总线(Universal Serial Bus，USB)驱动器或者两个或更多个以上这些的组合。在合适的情况下，存储器402可包括可移除或不可移除(或固定)的介质。在合适的情况下，存储器402可在综合网关容灾设备的内部或外部。在特定实施例中，存储器402是非易失性固态存储器。存储器可包括只读存储器(Read Only Memory image，ROM)、随机存取存储器(Random-Access Memory，RAM)、磁盘存储介质设备、光存储介质设备、闪存设备、电气、光学或其他物理/有形的存储器存储设备。因此，通常，存储器包括一个或多个编码有包括计算机可执行指令的软件的有形(非暂态)计算机可读存储介质(例如，存储器设备)，并且当该软件被执行(例如，由一个或多个处理器)时，其可操作来执行上述实施例提供的局部流量模型构建方法所描述的操作。
处理器401通过读取并执行存储器402中存储的计算机程序指令，以实现上述实施例中的任意一种局部流量模型构建方法。
在一个示例中，电子设备还可包括通信接口403和总线410。其中，如图4所示，处理器401、存储器402、通信接口403通过总线410连接并完成相互间的通信。
通信接口403，主要用于实现本公开实施例中各模块、设备、单元和/或设备之间的通信。
总线410包括硬件、软件或两者，将电子设备的部件彼此耦接在一起。举例来说而非限制，总线可包括加速图形端口(AGP)或其他图形总线、增强工业标准架构(EISA)总线、前端总线(FSB)、超传输(HT)互连、工业标准架构(ISA)总线、无限带宽互连、低引脚数(LPC)总线、存储器总线、微信道架构(MCA)总线、外围组件互连(PCI)总线、PCI-Express(PCI-X)总线、串行高级技术附件(SATA)总线、视频电子标准协会局部(VLB)总线或其他合适的总线或者两个或更多个以上这些的组合。在合适的情况下，总线410可包括一个或多个总线。尽管本公开实施例描述和示出了特定的总线，但本公开考虑任何合适的总线或互连。
该电子设备可以执行本公开实施例中的局部流量模型构建方法，从而实现图2描述的局部流量模型构建方法。
另外，结合上述实施例中的局部流量模型构建方法，本公开实施例可提供一种可读存储介质来实现。该可读存储介质上存储有程序指令；该程序指令被处理器执行时实现上述实施例中的任意一种局部流量模型构建方法。
另外，结合上述实施例中的局部流量模型构建方法，本公开实施例可提供一种车辆来实现。该车辆包括上述实施例中的局部流量模型构建装置、局部流量模型构建设备和计算机可读存储介质。
需要明确的是，本公开并不局限于上文所描述并在图中示出的特定配置和处理。为了简 明起见，这里省略了对已知方法的详细描述。在上述实施例中，描述和示出了若干具体的步骤作为示例。但是，本公开的方法过程并不限于所描述和示出的具体步骤，本领域的技术人员可以在领会本公开的精神后，作出各种改变、修改和添加，或者改变步骤之间的顺序。
以上所述的结构框图中所示的功能块可以实现为硬件、软件、固件或者它们的组合。当以硬件方式实现时，其可以例如是电子电路、专用集成电路(ASIC)、适当的固件、插件、功能卡等等。当以软件方式实现时，本公开的元素是被用于执行所需任务的程序或者代码段。程序或者代码段可以存储在机器可读介质中，或者通过载波中携带的数据信号在传输介质或者通信链路上传送。“机器可读介质”可以包括能够存储或传输信息的任何介质。机器可读介质的例子包括电子电路、半导体存储器设备、ROM、闪存、可擦除ROM(EROM)、软盘、CD-ROM、光盘、硬盘、光纤介质、射频(RF)链路，等等。代码段可以经由诸如因特网、内联网等的计算机网络被下载。
还需要说明的是，本公开中提及的示例性实施例，基于一系列的步骤或者装置描述一些方法或系统。但是，本公开不局限于上述步骤的顺序，也就是说，可以按照实施例中提及的顺序执行步骤，也可以不同于实施例中的顺序，或者若干步骤同时执行。
上面参考根据本公开的实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各方面。应当理解，流程图和/或框图中的每个方框以及流程图和/或框图中各方框的组合可以由计算机程序指令实现。这些计算机程序指令可被提供给通用计算机、专用计算机、或其它可编程数据处理装置的处理器，以产生一种机器，使得经由计算机或其它可编程数据处理装置的处理器执行的这些指令使能对流程图和/或框图的一个或多个方框中指定的功能/动作的实现。这种处理器可以是但不限于是通用处理器、专用处理器、特殊应用处理器或者现场可编程逻辑电路。还可理解，框图和/或流程图中的每个方框以及框图和/或流程图中的方框的组合，也可以由执行指定的功能或动作的专用硬件来实现，或可由专用硬件和计算机指令的组合来实现。
本公开实施例提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现本公开任一实施例所述的局部流量模型构建方法。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述，仅为本公开的具体实施方式，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、模块和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。应理解，本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本公开的保护范围之内。

Claims (11)

  1. 一种局部流量模型构建方法，包括：
    基于获取的热管理系统的第一流量数据，得到所述热管理系统对应的目标物理模型；
    基于所述目标物理模型，计算所述热管理系统中目标换热部件处冷却液的第二流量数据；
    根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
  2. 根据权利要求1所述的方法，其中，在所述根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型之前，所述方法还包括：
    获取控制所述热管理系统运行的第一特征参数；
    根据所述第一特征参数与所述第一流量数据之间的对应关系，确定与所述第一流量数据关联的至少一个关联特征参数；
    根据各所述关联特征参数，确定目标特征参数。
  3. 根据权利要求2所述的方法，其中，所述根据各所述关联特征参数，确定目标特征参数，包括：
    步骤A、将各所述关联特征参数分别依次输入到特征筛选模型中，分别得到与各所述关联特征参数对应的预测流量值；其中，所述特征筛选模型是通过学习各关联特征参数和热管理系统中冷却液的流量值的关系得到；
    步骤B、针对每个关联特征参数，计算所述关联特征参数对应的预测流量值与热管理系统中冷却液的低流量值的均方误差；其中，所述低流量值为流量值小于或等于第一预设流量阈值的流量值；
    步骤C、将最小的均方误差对应的关联特征参数，作为第一候选特征参数；
    步骤D、将所述特征筛选模型的输出更新为所述热管理系统中所述冷却液的高流量值，返回执行步骤A至C，得到第二候选特征参数；其中，所述高流量值为流量值大于或等于第二预设流量阈值的流量值；
    步骤E、将所述第一候选特征参数和所述第二候选特征参数，作为目标特征参数。
  4. 根据权利要求1-3任一项所述的方法，其中，所述根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型，包括：
    根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，构建训练样本；
    基于所述训练样本对预设模型进行训练，得到至少一个用于确定冷却液在目标换热部件处的初始局部流量模型；
    获取各初始局部流量模型在计算所述冷却液在目标换热部件处的局部流量时的精确度；
    基于所述精确度，从各初始局部流量模型中选取出精确度最高的初始局部流量模型，作为用于确定目标换热部件处冷却液局部流量的局部流量模型。
  5. 根据权利要求4所述的方法，其中，在所述得到用于确定目标换热部件处冷却液的局部流量的局部流量模型之后，所述方法还包括：
    将所述目标特征参数输入至所述局部流量模型中，得到所述冷却液在所述目标换热部件处的局部流量；
    基于所述局部流量，得到所述目标换热部件与所述冷却液热交换后所述冷却液的出水温度。
  6. 根据权利要求5所述的方法，其中，所述基于所述局部流量，得到所述目标换热部件与所述冷却液热交换后所述冷却液的出水温度，包括：
    基于所述局部流量，以及所述目标换热部件的比热，确定特征长度的所述目标换热部件传热给冷却液后所述冷却液的第一热量变化量；
    基于第一热量变化量，对所述目标换热部件的长度进行积分，得到所述目标换热部件的温度与所述冷却液的出口温度的关系式；
    基于所述关系式，得到所述目标换热部件传热给所述冷却液后所述冷却液的出水温度。
  7. 一种局部流量模型构建装置，装置包括：
    第一构建模块，用于基于获取的热管理系统的第一流量数据，得到所述热管理系统对应的目标物理模型；
    计算模块，用于基于所述目标物理模型，计算所述热管理系统中目标换热部件处冷却液的第二流量数据；
    第一确定模块，用于根据所述第二流量数据及其对应的控制所述热管理系统运行的目标特征参数，对预设模型进行训练，得到用于确定冷却液在目标换热部件处的局部流量模型。
  8. 一种局部流量模型构建设备，包括：处理器以及存储有计算机程序指令的存储器；所述处理器执行所述计算机程序指令时实现如权利要求1-6中任意一项所述的局部流量模型构建方法。
  9. 一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现如权利要求1-6中任意一项所述的局部流量模型构建方法。
  10. 一种车辆，包括以下至少一种：
    如权利要求7所述的局部流量模型构建装置；
    如权利要求8所述的局部流量模型构建设备；
    如权利要求9所述的计算机可读存储介质。
  11. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1至6中任一项所述的局部流量模型构建方法。
PCT/CN2023/101130 2022-06-22 2023-06-19 局部流量模型构建方法、装置、设备、介质和车辆 Ceased WO2023246712A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/876,395 US20250244733A1 (en) 2022-06-22 2023-06-19 Method for constructing local flow model, apparatus and device, and medium
EP23826360.2A EP4546200A4 (en) 2022-06-22 2023-06-19 METHOD, APPARATUS AND DEVICE FOR CONSTRUCTING LOCAL FLOW MODELS, SUPPORT AND VEHICLE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210713385.0 2022-06-22
CN202210713385.0A CN117313254A (zh) 2022-06-22 2022-06-22 局部流量模型构建方法、装置、设备、介质和车辆

Publications (1)

Publication Number Publication Date
WO2023246712A1 true WO2023246712A1 (zh) 2023-12-28

Family

ID=89235855

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/101130 Ceased WO2023246712A1 (zh) 2022-06-22 2023-06-19 局部流量模型构建方法、装置、设备、介质和车辆

Country Status (4)

Country Link
US (1) US20250244733A1 (zh)
EP (1) EP4546200A4 (zh)
CN (1) CN117313254A (zh)
WO (1) WO2023246712A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119227595A (zh) * 2024-12-03 2024-12-31 国网浙江省电力有限公司杭州供电公司 液流传导的循环式热管理方法和系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117631710A (zh) * 2022-08-10 2024-03-01 北京罗克维尔斯科技有限公司 电机系统的温度控制方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016007320A1 (de) * 2016-06-16 2017-12-21 Daimler Ag Verfahren zum Ermitteln wenigstens einer Temperatur eines Kühlmittels für ein Kraftfahrzeug
US20180004864A1 (en) * 2016-06-29 2018-01-04 International Business Machines Corporation Hybrid modeling for a device under test associated with a two-phase cooling system
CN111814261A (zh) * 2020-07-29 2020-10-23 潍柴动力股份有限公司 整车冷却特性数据确定方法、装置、设备及可存储介质
CN114154689A (zh) * 2021-11-18 2022-03-08 中南大学 一种冷水主机单机能耗预测方法、系统及存储介质
CN114239133A (zh) * 2021-11-26 2022-03-25 中汽研（常州）汽车工程研究院有限公司 混合动力汽车热管理系统一维联合仿真建模方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112459890A (zh) * 2019-09-06 2021-03-09 深圳臻宇新能源动力科技有限公司 热管理系统及基于神经网络的热管理方法和装置
CN114282456A (zh) * 2021-12-23 2022-04-05 苏州同元软控信息技术有限公司 换热器参数虚拟验证优化方法以及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016007320A1 (de) * 2016-06-16 2017-12-21 Daimler Ag Verfahren zum Ermitteln wenigstens einer Temperatur eines Kühlmittels für ein Kraftfahrzeug
US20180004864A1 (en) * 2016-06-29 2018-01-04 International Business Machines Corporation Hybrid modeling for a device under test associated with a two-phase cooling system
CN111814261A (zh) * 2020-07-29 2020-10-23 潍柴动力股份有限公司 整车冷却特性数据确定方法、装置、设备及可存储介质
CN114154689A (zh) * 2021-11-18 2022-03-08 中南大学 一种冷水主机单机能耗预测方法、系统及存储介质
CN114239133A (zh) * 2021-11-26 2022-03-25 中汽研（常州）汽车工程研究院有限公司 混合动力汽车热管理系统一维联合仿真建模方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4546200A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119227595A (zh) * 2024-12-03 2024-12-31 国网浙江省电力有限公司杭州供电公司 液流传导的循环式热管理方法和系统

Also Published As

Publication number Publication date
EP4546200A4 (en) 2025-11-19
CN117313254A (zh) 2023-12-29
US20250244733A1 (en) 2025-07-31
EP4546200A1 (en) 2025-04-30

Similar Documents

Publication Publication Date Title
WO2023246712A1 (zh) 局部流量模型构建方法、装置、设备、介质和车辆
CN111125909B (zh) 一种一维汽车热管理模型的自动化标定方法
WO2020133721A1 (zh) 一种基于非参数贝叶斯框架的信号交叉口状态估计方法
WO2023246897A1 (zh) 热管理系统建模方法、装置、设备、介质和车辆
CN113158589B (zh) 一种电池管理系统的仿真模型校准方法以及装置
EP4542014A1 (en) Temperature prediction method and apparatus for engine cooling system, device, medium, and vehicle
CN114743076B (zh) 一种自动驾驶图像处理评价方法、相关设备、介质及产品
CN116774052A (zh) 动力电池温度预测方法、装置、车辆及存储介质
CN112566170A (zh) 网络质量评估方法、装置、服务器及存储介质
CN115234371A (zh) 车辆发动机热管理诊断方法、装置、设备及存储介质
CN117391220A (zh) 一种模型构建方法、装置、设备及计算机存储介质
CN116502131B (zh) 基于迁移学习的轴承故障诊断模型训练方法及装置
WO2024174873A1 (zh) 热管理系统中部件温度预测方法及相关设备
CN118885772B (zh) 基于物理信息神经网络模型的故障检测方法、装置、设备及介质
WO2023246647A1 (zh) 发动机冷却系统温度预测方法、装置、设备、介质和车辆
CN117436196A (zh) 汽车磨损度预估方法、装置、电子设备及存储介质
CN114638159A (zh) 确定耐蚀性的方法、装置、设备及计算机存储介质
CN120803079B (zh) 冷却液流量匹配方法、系统及其应用
CN119714581B (zh) 换热介质的温度确定方法、装置、电子设备、存储介质及车辆
CN119449867B (zh) 重型车远程监控NOx排放数据诊断方法及装置
CN115307271B (zh) 空调器及其故障的确定方法、空调装置及可读存储介质
CN116429968B (zh) 基于样本迁移的烟气含氧量预测方法、装置和电子设备
CN118821575A (zh) 失效模式的预测方法、装置、设备及计算机存储介质
CN118798297A (zh) 模型训练方法、装置、设备及计算机存储介质
CN119514079A (zh) 气路模型的建立方法、装置、设备及存储介质

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: 23826360

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18876395

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2023826360

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2023826360

Country of ref document: EP

Effective date: 20250122

WWP Wipo information: published in national office

Ref document number: 2023826360

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 18876395

Country of ref document: US