WO2024201718A1 - Dispositif de pompe à vide - Google Patents

Dispositif de pompe à vide Download PDF

Info

Publication number
WO2024201718A1
WO2024201718A1 PCT/JP2023/012529 JP2023012529W WO2024201718A1 WO 2024201718 A1 WO2024201718 A1 WO 2024201718A1 JP 2023012529 W JP2023012529 W JP 2023012529W WO 2024201718 A1 WO2024201718 A1 WO 2024201718A1
Authority
WO
WIPO (PCT)
Prior art keywords
registration
model
unit
discrimination
discrimination model
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/JP2023/012529
Other languages
English (en)
Japanese (ja)
Inventor
敏幸 松本
新井　晃
平 大久保
翔平 臼田
佳月 井出
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.)
Kashiyama Industries Ltd
Original Assignee
Kashiyama Industries 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 Kashiyama Industries Ltd filed Critical Kashiyama Industries Ltd
Priority to PCT/JP2023/012529 priority Critical patent/WO2024201718A1/fr
Priority to JP2025509340A priority patent/JPWO2024201718A1/ja
Publication of WO2024201718A1 publication Critical patent/WO2024201718A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
    • F04B37/00—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00
    • F04B37/10—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00 for special use
    • F04B37/14—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00 for special use to obtain high vacuum
    • F04B37/16—Means for nullifying unswept space
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
    • F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
    • F04B49/10—Other safety measures

Definitions

  • vacuum pumps are increasingly being used in applications where a sudden shutdown during use could cause major damage, such as at semiconductor device manufacturing sites. For this reason, vacuum pumps used in such applications are required to be equipped with a predictive maintenance system that constantly monitors the operating status and predicts and maintains any abnormalities that might cause a sudden shutdown.
  • a discrimination model is prepared as an indicator of whether the vacuum pump is normal or not, and the discrimination model is used to discriminate abnormalities from operating parameters (hereinafter referred to as "operating parameters") that represent the operating state of the vacuum pump and are obtained from the vacuum pump during operation (for example, Patent Document 1).
  • Patent Document 1 discloses a diagnostic device that predicts and diagnoses abnormalities in rotating machines such as pump motors using a normal model as a discrimination model.
  • the normal model used in this diagnostic device is generated based on values obtained from the motor current of a motor that is operating normally (paragraph 0037 of Patent Document 1).
  • Vacuum pumps are operated in a variety of installation environments and conditions, and the thresholds at which operational parameters detected from an operating vacuum pump can be determined to be normal vary depending on the installation environment and condition. For this reason, when performing predictive maintenance on vacuum pumps, it is preferable to use a discrimination model that corresponds to the installation environment and installation conditions, and a discrimination model must be generated each time the installation environment or installation conditions change. However, in conventional predictive maintenance systems installed in vacuum pumps, it was not easy to generate and register discrimination models.
  • the main objective of the present invention is to propose a vacuum pump device that allows for easy generation and registration of a discrimination model.
  • the vacuum pump apparatus of the present invention comprises a collection unit that collects operating parameters representing the operating state of the vacuum pump, a model generation unit that generates a discrimination model used to determine whether the operating state is normal or not based on collected data of the operating parameters collected by the collection unit, a model registration unit in which the discrimination model is registered, a registration control unit that controls the collection operation of the operating parameters by the collection unit, the generation operation of the discrimination model by the model generation unit, and the registration operation of the discrimination model in the model registration unit, and an input unit that instructs the registration control unit to perform at least one of the registration operations of new registration, additional registration, and update registration of the discrimination model.
  • the registration control unit of the vacuum pump is provided with a registration function that performs at least a registration operation instructed by a command among a new registration function, an additional registration function, and an update registration function of the discrimination model.
  • the new registration function is a function that is activated upon receiving a command for new registration, and causes the collection unit to collect operation parameters, the model generation unit to generate a new discrimination model based on the collected operation parameters, and the generated discrimination model to be newly registered in the model registration unit.
  • the additional registration function is a function that is activated upon receiving a command for additional registration, and causes the collection unit to collect operation parameters, the model generation unit to generate a new discrimination model based on the collected operation parameters, and the generated discrimination model to be additionally registered in the model registration unit in addition to the already registered discrimination model registered in the model registration unit.
  • the update registration function is a function that is activated upon receiving a command for update registration, and causes the collection unit to collect operation parameters, the model generation unit to generate a new discrimination model based on the collected operation parameters, and the generated discrimination model to be registered in the model registration unit in place of the already registered discrimination model registered in the model registration unit.
  • the discrimination model generated by the model generation unit is a normal model generated using the MT method (Mahalanobis-Taguchi system) from a group of multidimensional information including several different operating parameters that indicate the normal operating state of the vacuum pump.
  • the collected data used to generate the discrimination model is a series of data detected at a predetermined sampling period over a predetermined time.
  • the input unit includes one or more operating members that are operated to input the command.
  • the discrimination model includes a first discrimination model and a second discrimination model for discriminating whether a first operating state and a second operating state of the vacuum pump are normal or not.
  • the model registration unit has a first registration area for registering the first discrimination model and a second registration area for registering the second discrimination model, and that the input unit has an operation member for specifying a registration area that inputs a command to the registration control unit to specify whether the registration operation instructed by the command is to be performed on the first registration area or the second registration area.
  • the input unit is configured to instruct the registration control unit to perform the registration operation of each of the multiple discrimination models, including the first discrimination model and the second discrimination model, as a series of registration operations while automatically switching between the discrimination models to be generated and registered by determining the operating state of the vacuum pump based on at least one of the operating parameters.
  • the present invention provides a vacuum pump device that allows for easy generation and registration of a discrimination model.
  • FIG. 1 is a block diagram showing a configuration of a vacuum pump device according to a first embodiment
  • FIG. 2 is an explanatory diagram of the MT method used in the first embodiment.
  • 4 is a graph showing an operation status of the dry vacuum pump of the first embodiment.
  • FIG. 4 is a diagram illustrating a difference in unit space depending on an operating state in the first embodiment.
  • 1 is a block diagram showing a configuration of a predictive maintenance system according to a first embodiment.
  • FIG. 4 is a flowchart mainly showing the processing performed in the predictive maintenance system for the vacuum pump apparatus of the first embodiment.
  • FIG. 11 is a block diagram showing a configuration of a vacuum pump device according to a second embodiment.
  • 10 is a flowchart mainly showing the processing performed in a predictive maintenance system for a vacuum pump apparatus according to a second embodiment.
  • 9 is a flowchart showing each process in a discrimination model registration step in FIG. 8 .
  • FIG. 1 is a block diagram showing the configuration of a vacuum pump device 1 of the first embodiment.
  • the vacuum pump device 1 includes a two-stage dry vacuum pump 3 arranged inside a device case 2 as a vacuum pump.
  • the dry vacuum pump 3 is configured with two stages, a front-stage mechanical booster pump 4 (hereinafter simply referred to as a "booster pump 4") and a rear-stage screw-type vacuum pump 5 (hereinafter referred to as a "back pump 5").
  • the intake port 6 of the dry vacuum pump 3 extends from the booster pump 4 and opens upward on the top surface of the device case 2.
  • the exhaust port 7 of the dry vacuum pump 3 extends from the back pump 5 and opens laterally on the side surface of the device case 2.
  • the booster pump 4 and the back pump 5 are connected by an internal pipe.
  • the dry vacuum pump 3 sucks in air from the intake port 6, passes it through the booster pump 4 and the back pump 5 in this order, and exhausts it from the exhaust port 7, thereby performing vacuum drawing inside a container connected to the intake port 6 side.
  • the vacuum pump device 1 is also provided with detection elements 10 such as measuring devices or detection sensors, and each detection element detects operating parameters representing the operating state of the dry vacuum pump 3 from various viewpoints.
  • the vacuum pump device 1 is provided with vibration detection elements 10a, 10b and current detection elements 10c, 10d to detect the vibration and current of the booster pump 4 and the back pump 5, respectively.
  • the vacuum pump device 1 is also provided with a temperature detection element 10e (thermocouple 10e) to detect the temperature of the back pump 5.
  • the vacuum pump device 1 is also provided with a back pressure detection element 10f in the exhaust path of the back pump 5 to detect the back pressure of the dry vacuum pump 3.
  • the vacuum pump device 1 is equipped with an operation control system 20 that controls the operation of the dry vacuum pump 3, and a predictive maintenance system 30 that determines whether the operating condition of the dry vacuum pump 3 is normal or not.
  • the operation control system 20 is electrically connected to the booster pump 4 and the back pump 5.
  • the operation control system 20 receives operation commands from the user's operation panel 21 or the like and maintenance commands from the predictive maintenance system 30 described below, and controls operations such as drive/stop for the booster pump 4 and the back pump 5 according to the contents of the operation commands and maintenance commands.
  • the predictive maintenance system 30 constantly monitors the operating state of the dry vacuum pump 3, grasps the operating state of the dry vacuum pump 3, and determines the timing of maintenance and the occurrence of abnormalities, etc., and notifies the user of the results and reflects them in the control of the operation control system 20.
  • the predictive maintenance system 30 Before describing the predictive maintenance system 30 in detail, an overview of the predictive maintenance system 30 in the vacuum pump device 1 according to the first embodiment will first be described.
  • FIG. 2 is an explanatory diagram of the MT method used in the first embodiment.
  • FIG. 3 is a graph showing the operating status of the dry vacuum pump 3 in the first embodiment.
  • FIG. 4 is a diagram explaining the difference in unit space depending on the operating state in the first embodiment.
  • the predictive maintenance system 30 in the vacuum pump device 1 attempts to determine whether the operating state of the dry vacuum pump 3 is normal or not from different operating parameters (multidimensional measurement values) detected by at least two types of detection elements 10 (10a to 10f).
  • the MT method (Mahalanobis-Taguchi system) using quality engineering and statistical techniques is used to determine whether the operating state of the dry vacuum pump 3 is normal or not using an index called the Mahalanobis distance (hereinafter referred to as the "MD value").
  • a ruler is created that integrates the multidimensional information of a homogeneous group for the purpose (in the first embodiment, the operating parameters of the dry vacuum pump 3 during normal operation).
  • the range in which the homogeneous group for the purpose (the group of operating information of the dry vacuum pump 3 during normal operation) is distributed is called the unit space.
  • this ruler is used to determine how far each individual object (in the first embodiment, the data of the dry vacuum pump 3 during abnormal operation) that does not belong to this homogeneous group is from the center of the unit space (called the "Mahalanobis distance (MD value)" and to determine whether it is normal or not.
  • a normal model generated by using the MT method (Mahalanobis-Taguchi system) from a group of multidimensional information including several different operating parameters that indicate the normal operating state of the dry vacuum pump 3 is used as a discrimination model.
  • the MD value in the unit space of this discrimination model is then calculated, and whether it is normal or not is determined based on the idea that the larger the MD value, the greater the degree of abnormality. For example, whether or not the exponentially weighted moving average (EWMA) of the calculated MD value exceeds a threshold value is used to determine whether or not the value is normal.
  • EWMA exponentially weighted moving average
  • the dry vacuum pump 3 When the dry vacuum pump 3 draws a vacuum inside a container connected to the intake port 6, as shown in FIG. 3, it operates by repeating different operating states, such as an idle operating state in which the motor speed is not increased and a process operating state in which the motor speed is periodically increased (and other operating states in some cases). Since the pump behavior differs in each operating state, the predictive maintenance system 30 considers it difficult to determine whether the pump is normal or not using only one discrimination model, and determines whether the pump is normal or not using multiple discrimination models.
  • different operating states such as an idle operating state in which the motor speed is not increased and a process operating state in which the motor speed is periodically increased (and other operating states in some cases). Since the pump behavior differs in each operating state, the predictive maintenance system 30 considers it difficult to determine whether the pump is normal or not using only one discrimination model, and determines whether the pump is normal or not using multiple discrimination models.
  • the vacuum pump device 1 determines whether the pump is normal or not using a first discrimination model and a second discrimination model for determining whether the different first operating state (e.g., an idle operating state) and second operating state (e.g., a process operating state) of the dry vacuum pump 3 are normal or not.
  • the predictive maintenance system 30 will be described in detail below.
  • FIG. 5 is a block diagram showing the configuration of the predictive maintenance system 30 in the vacuum pump device 1 of embodiment 1.
  • the predictive maintenance system 30 includes a collection unit 31, a model generation unit 32, a model registration unit 33, a registration control unit 34, an input unit 35, and a discrimination unit 36.
  • the collection unit 31 is electrically connected to the detection element 10 and collects operating parameters that represent the operating state of the dry vacuum pump 3 detected by the detection element 10 for use in generating a discrimination model.
  • the collected data collected by the collection unit 31 and used in generating a discrimination model is a series of data detected at a predetermined sampling period over a predetermined time.
  • the collection unit 31 collects the vibration and current of the booster pump 4, the vibration and current of the back pump 5, and operating parameters related to the temperature and back pressure of the back pump 5 as a series of continuous collected data every second for one hour for use in generating a discrimination model.
  • the collection unit 31 collects operating parameters that represent the operating state of the dry vacuum pump 3 detected by the detection element 10 when determining whether the operation of the dry vacuum pump 3 is normal or not. For example, the collection unit 31 collects the vibration and current of the booster pump 4, the vibration and current of the back pump 5, and the operating parameters related to the temperature and back pressure of the back pump 5 as a series of operating status data in 60-second units every second so that the discrimination unit 36 described below can determine whether the dry vacuum pump 3 is operating normally every 60 seconds.
  • the model generating unit 32 generates a discrimination model used to determine whether the operating state of the dry vacuum pump 3 is normal or not based on the collected data of the operating parameters collected by the collecting unit 31. As described above, in the first embodiment, it is determined whether the dry vacuum pump 3 operating in the different first operating state (idle operating state) and second operating state (process operating state) is normal or not. For this reason, the model generating unit 32 can generate at least a first discrimination model and a second discrimination model corresponding to each operating state. Also, as described above, the dry vacuum pump 3 is composed of a booster pump 4 and a back pump 5, and it is determined whether each pump is normal or not.
  • the model generating unit 32 can generate a first discrimination model for the booster pump 4 and a second discrimination model for the booster pump 4, as well as a first discrimination model for the back pump 5 and a second discrimination model for the back pump 5, corresponding to each pump.
  • the discrimination model generated by the model generation unit 32 is a normal model generated using the MT method (Mahalanobis-Taguchi system) from a group of multidimensional information including several different operating parameters that indicate the normal operating state of the dry vacuum pump 3 (for example, the operating parameters of vibration, current, temperature, and back pressure in the discrimination model for the back pump 5 of embodiment 1, and the operating parameters of vibration and current in the discrimination model for the booster pump 4 of embodiment 1).
  • MT method Mohalanobis-Taguchi system
  • the model registration unit 33 is a memory having a registration area for registering data such as so-called memory elements or storage media, and a discrimination model is registered in the registration area.
  • a first discrimination model and a second discrimination model for discriminating whether a first operating state (e.g., an idle operating state) and a second operating state (e.g., a process operating state) that differ for each of the booster pump 4 and the back pump 5 are normal or not are used to determine whether they are normal or not.
  • the model registration unit 33 has a first registration area for registering the first discrimination model and a second registration area for registering the second discrimination model for each of the booster pump 4 and the back pump 5.
  • the registration control unit 34 controls the operation of collecting operating parameters by the collection unit 31, the operation of generating a discrimination model by the model generation unit 32, and the operation of registering a discrimination model in the model registration unit 33.
  • the registration control unit 34 has a registration function that performs registration operations instructed by commands from the input unit 35 described below, such as a new discrimination model registration function, an additional registration function, and an update registration function.
  • the new registration function in the registration control unit 34 is activated when a command for new registration is received, and causes the collection unit 31 to collect operating parameters, the model generation unit 32 to generate a new discrimination model based on the collected operating parameters, and the model registration unit 33 to newly register the generated discrimination model.
  • the additional registration function in the registration control unit 34 is activated when an additional registration command is received, and causes the collection unit 31 to collect operating parameters, the model generation unit 32 to generate a new discrimination model based on the collected operating parameters, and the model registration unit 33 to additionally register the generated discrimination model in addition to the discrimination models already registered in the model registration unit 33.
  • the update registration function in the registration control unit 34 is activated when an update registration command is received, and causes the collection unit 31 to collect operating parameters, the model generation unit 32 to generate a new discrimination model based on the collected operating parameters, and the model registration unit 33 to register the generated discrimination model in place of the discrimination model already registered in the model registration unit 33.
  • the input unit 35 includes an operating member 37 such as a push button switch, a changeover switch, a touch panel, etc., installed on the side of the device case 2, and accepts input operations by the user via the operating member 37.
  • the input unit 35 issues a command to the registration control unit 34 to perform at least one of the registration operations of new registration, additional registration, and update registration of a discrimination model.
  • the input unit 35 is operated to input at least one of the commands of new registration, additional registration, and update registration.
  • the input unit 35 is provided with a registration area designation operating member that inputs a command to the registration control unit 34 specifying whether the registration operation instructed by the command issued by the registration control unit 34 should be performed on the first registration area or the second registration area.
  • the input unit 35 includes, as the operating member 37, a number of push button switches (37a, 37b, ...) corresponding to the first registration area and the second registration area, respectively, and when one of the push button switches (e.g., 37a) is pressed, a command is issued to the registration control unit 34 to generate a discrimination model and then register the discrimination model in the registration area corresponding to one of the push button switches (e.g., 37a).
  • the discrimination unit 36 analyzes the operating parameters representing the operating state of the dry vacuum pump 3 during operation collected by the collection unit 31 using the discrimination model registered in the model registration unit 33, and discriminates whether the operating state of the dry vacuum pump 3 is normal or not. Specifically, in the first embodiment, the discrimination unit 36 generates operating state data based on the operating parameters of the dry vacuum pump 3 during operation collected by the collection unit 31.
  • the discrimination unit 36 calculates the MD value (Mahalanobis distance) in the unit space of the discrimination model used for discrimination among the discrimination models registered as normal models in the model registration unit 33 for the operating state data, and determines that if the calculated MD value is smaller than the MD value of the boundary line separating the inside and outside of the unit space, it is normal, and if it is larger, it is possible that there is an abnormality or is abnormal.
  • the discrimination unit 36 outputs the discrimination result so as to present it to the user or to reflect it in the control of the operation control system 20.
  • the dry vacuum pump 3 is controlled and operated by the operation control system 20.
  • the operating parameters indicating the operating state of the dry vacuum pump 3 are detected by the detection element 10 and collected as necessary by the collection unit 31 of the predictive maintenance system 30.
  • the operating dry vacuum pump 3 is monitored by the discrimination unit 36 of the predictive maintenance system 30, which discriminates whether its operating state is normal or not using a discrimination model registered in the model registration unit 33.
  • the discrimination unit 36 of the predictive maintenance system in order to accurately make a judgment using the predictive maintenance system, it is necessary to use a discrimination model according to the installation environment and installation state.
  • a new discrimination model based on the operating parameters of the dry vacuum pump 3 in that installation environment and installation state is registered by the registration function of the registration control unit 34 in response.
  • FIG. 6 is a flowchart showing the processing performed in the vacuum pump device 1 of the first embodiment, particularly in the predictive maintenance system 30.
  • the processing performed in the vacuum pump device 1, particularly in the predictive maintenance system 30, will be described.
  • the power is turned on and the device is started.
  • the start-up read step ST1 is repeated the number of discrimination models that can be registered, and then the predictive maintenance step ST2 is repeatedly executed until a stop command is received.
  • the discrimination model registration step ST3 or the discrimination step ST4 is executed depending on the state of the model registration unit 33 or the input unit 35. Note that in the processing performed in the predictive maintenance system 30, a model generation flag is used for conditional branching, but the model generation flag is set to "OFF" at the time of startup. The steps are explained below.
  • a model registration unit confirmation process ST11 is performed to confirm the registration status of the discrimination model in the model registration unit 33. If it is confirmed in the model registration unit confirmation process ST11 that a discrimination model is registered in the model registration unit 33, a discrimination model read process ST12 is performed to read out the registered discrimination model so that it can be used in the discrimination step ST4 described below. On the other hand, if it is confirmed in the model registration unit confirmation process ST11 that a discrimination model is not registered in the model registration unit 33, a model generation flag ON process ST13 is performed to set the model generation flag to "ON". In the startup read step ST1, these processes are repeated the number of times equal to the number of discrimination models that can be registered in the model registration unit 33. For example, in the first embodiment, when at least the first and second discrimination models for the booster pump 4 and the first and second discrimination models for the back pump 5 can be registered, these processes are repeated at least four times to read out each discrimination model.
  • the input status of the input unit 35 is confirmed as an input unit confirmation process ST21. If it is confirmed in the input unit confirmation process ST21 that there is an input in the input unit 35, the model generation flag is set to "ON" as a model generation flag ON process ST22. On the other hand, if it is confirmed in the input unit confirmation process ST21 that there is no input in the input unit 35, the process proceeds directly to the next process.
  • a model generation flag confirmation process ST23 it is confirmed whether the model generation flag is ON or OFF, and if it is ON, the process proceeds to the discrimination model registration step ST3, and if it is OFF, the process proceeds to the discrimination step ST4.
  • the discrimination model registration step ST3 is executed, and if not, the discrimination step ST4 is executed.
  • the discrimination model registration step ST3 is a process of generating and registering a discrimination model to be used for predictive maintenance of the dry vacuum pump 3 from the operating parameters obtained by actually operating the dry vacuum pump 3 in a state in which the operating state can be grasped in order to generate a discrimination model.
  • a data collection process ST31, a discrimination model generation process ST32, and a discrimination model registration process ST33 are sequentially executed by one of the registration functions of the registration control unit 34, which is a new registration function, an additional registration function, and an update registration function.
  • the collection unit 31 collects the operating parameters of the dry vacuum pump 3 for a predetermined time period (for example, one hour).
  • the discrimination model generation process ST32 a new discrimination model is generated by the model generation unit 32 based on the operating parameters collected in the data collection process ST31.
  • the discrimination model registration process ST33 the discrimination model generated in the discrimination model generation process ST32 is registered in the registration area of the model registration unit 33 corresponding to the operating state specified when input to the input unit 35.
  • the discrimination model read process ST34 reads the new discrimination model so that it can be used in the discrimination step ST4 described below, and the model generation flag is changed from ON to OFF in the model generation flag OFF process ST35.
  • the discrimination step ST4 is a process for discriminating the operating state of the dry vacuum pump 3 during operation.
  • data collection process ST41, discrimination process ST42, and result output process ST43 are executed in sequence.
  • the collection unit 31 collects the operating parameters of the dry vacuum pump 3 for a predetermined time (for example, 60 seconds).
  • the discrimination unit 36 generates operating state data based on the operating parameters of the dry vacuum pump 3 during operation collected in the data collection process ST41.
  • the discrimination unit 36 calculates the MD value (Mahalanobis distance) in the unit space of the discrimination model that has been read out for that operating state data, and determines that if the calculated MD value is smaller than the MD value of the boundary line that separates the inside and outside of the unit space, it is normal, and if it is larger, it determines that there is a possibility of an abnormality or that it is abnormal.
  • the discrimination process ST42 a series of processes are performed to generate operating state data corresponding to the discrimination model that has been read out and to discriminate the generated operating state data.
  • discrimination process ST42 if multiple discrimination models are read out, this series of processes in discrimination process ST42 will be performed multiple times corresponding to each discrimination model by parallel processing or continuous processing.
  • result output process ST43 the discrimination result is output by discrimination unit 36 so as to be presented to the user or reflected in the control of operation control system 20. Note that once discrimination step ST4 is executed, if there is no input to input unit 35, the model generation flag will remain "OFF" and the process will flow from model generation flag confirmation process ST23 to discrimination step ST4 again. Therefore, discrimination step ST4 will be repeatedly executed until there is an input to input unit 35 and a stop command, and the operation of dry vacuum pump 3 in operation will be monitored.
  • the vacuum pump device 1 of embodiment 1 includes a collection unit 31 that collects operating parameters, a model generation unit 32 that generates a discrimination model based on collected data of the operating parameters collected by the collection unit 31, a model registration unit 33 in which the discrimination model is registered, and a registration control unit 34 that controls the collection operation of the operating parameters by the collection unit 31, the generation operation of the discrimination model by the model generation unit 32, and the registration operation of the discrimination model in the model registration unit 33.
  • This registration control unit 34 has a new registration function, an additional registration function, and an update registration function for the discrimination model by controlling the collection unit 31, the model generation unit 32, and the model registration unit 33.
  • the vacuum pump device 1 a new discrimination model is registered in a series of steps by which the registration function of this registration control unit 34 collects operating parameters of the operating dry vacuum pump 3, generates a discrimination model from the collected operating parameters, and registers the discrimination model in the model registration unit 33.
  • the vacuum pump device 1 further includes an input unit 35 that issues a command to the registration control unit 34 to perform at least one of the following registration operations: new registration, additional registration, and update registration of a discrimination model.
  • the input unit 35 is provided with one or more operating members 37 that are operated to input at least one of the commands for new registration, additional registration, and update registration of a discrimination model, so that a discrimination model can be more easily generated and registered simply by operating the operating members 37.
  • the operation member 37 is configured as a registration area designation operation member (37a, 37b%) that inputs a command to the registration control unit 34 specifying whether the new registration, additional registration, or update registration of the discrimination model should be performed in the first registration area or the second registration area, so that a discrimination model can be easily generated and multiple discrimination models can be easily and accurately registered.
  • the discrimination model generated by the model generation unit 32 is a normal model generated using the MT method (Mahalanobis-Taguchi system) from a group of multidimensional information including several different operating parameters that indicate the normal operating state of the dry vacuum pump 3.
  • the collected data used to generate the discrimination model is a series of data detected at a predetermined sampling period over a predetermined time.
  • the normal model can be created from a series of data detected by the dry vacuum pump 3 that is operating normally at a predetermined sampling period without waiting for an abnormal stop, so that the vacuum pump device 1 makes it possible to easily generate and register a discrimination model at any time.
  • FIG. 7 is a block diagram showing the configuration of a vacuum pump apparatus 101 of embodiment 2.
  • Fig. 8 is a flowchart mainly showing the processing performed in a predictive maintenance system 130 of the vacuum pump apparatus 101 of embodiment 2.
  • Fig. 9 is a flowchart showing each process in the discrimination model registration step ST103 in Fig. 8.
  • the vacuum pump device 101 according to the second embodiment basically has the same configuration as the vacuum pump device 1 according to the first embodiment, but differs in the following respects. That is, in the vacuum pump device 101 according to the second embodiment, as shown in FIG. 7, an operation member 137 different from the operation member 37 (see FIG. 1) of the first embodiment is provided in the input unit 135. Also, in the vacuum pump device 101 according to the second embodiment, as shown in FIGS. 8 and 9, the processing performed in the predictive maintenance system 130 differs from the processing performed in the predictive maintenance system 30 of the first embodiment (see FIG. 6). Note that, in the following, the same configurations and processing as those of the vacuum pump device 1 according to the first embodiment will be denoted by the same reference numerals in the drawings as those in the first embodiment, and description thereof will be omitted.
  • the operation member 137 installed in the input unit 135 includes a plurality of push button switches (37a, 37b, ...) corresponding to the first registration area and the second registration area, respectively, as in the first embodiment.
  • a command is issued to the registration control unit 34 to generate a discrimination model and then register the discrimination model in the registration area corresponding to one of the push button switches (e.g., 37a).
  • the operation member 137 further includes an additional registration operation member 137a and a successive registration operation member 137b.
  • the additional registration operation member 137a is, for example, a changeover switch, and issues a command to the registration control unit 34 as to whether to perform the registration operation using the new registration function or the update registration function, or the additional registration function, after generating a discrimination model. Specifically, when the additional registration operation member 137a is ON, and input is also given to the push button switches (37a, 37b, ...), it instructs the registration control unit 34 to register a discrimination model using the additional registration function. Also, when the additional registration operation member 137a is OFF, and input is also given to the push button switches (37a, 37b, ...), it instructs the registration control unit 34 to register a discrimination model using the new registration function or the update registration function.
  • the continuous registration operation member 137b is, for example, a changeover switch, and commands the registration control unit 34 to perform the registration operation of each of the multiple discrimination models as a series of registration operations while automatically switching the discrimination models to be generated and registered by determining the operating state of the dry vacuum pump 3 based on at least one of the operating parameters. Specifically, when the continuous registration operation member 137b is ON and the device is operated, it commands the registration control unit 34 to first generate and register a first discrimination model, monitor the average current value of the booster pump 4 using the registered first discrimination model, and generate and register a second discrimination model when the monitored average current value exceeds a threshold value, as a series of registration operations.
  • the processing performed in the vacuum pump device 101 will be described.
  • the vacuum pump device 101 as in the vacuum pump device 1 of embodiment 1, the power is turned on and the device is started, and after a certain time has elapsed since the device was started or after it is confirmed that the dry vacuum pump 3 has entered a stable state, the start-up read step ST101 is executed, and then the predictive maintenance step ST102 is repeatedly executed until a stop command is received.
  • the discrimination model registration step ST103 or the discrimination step ST4 is executed depending on the state of the model registration unit 33 or the input unit 135. Note that in the processing performed in the predictive maintenance system 130, a model generation flag is used for conditional branching, but the model generation flag is "OFF" at the time of startup. The steps are explained below.
  • a model registration unit confirmation process ST11 is performed to confirm the registration status of the discrimination model in the model registration unit 33. If it is confirmed in the model registration unit confirmation process ST11 that a discrimination model is registered in the model registration unit 33, a discrimination model read process ST12 is performed to read out the registered discrimination model so that it can be used in the discrimination step ST4 described below, and the process proceeds to the predictive maintenance step ST102. On the other hand, if it is confirmed in the model registration unit confirmation process ST11 that a discrimination model is not registered in the model registration unit 33, an input wait process ST113 is performed to wait until an input is received in the input unit 135. If an input is confirmed in the input wait process ST113, the process proceeds to the predictive maintenance step ST102.
  • the input status of the input unit 135 is confirmed as an input unit confirmation process ST21. If it is confirmed in the input unit confirmation process ST21 that there is input in the input unit 135, the model generation flag is set to "ON" as a model generation flag ON process ST22. On the other hand, if it is confirmed in the input unit confirmation process ST21 that there is no input in the input unit 135, the process proceeds directly to the next process. Note that when an input to the input unit 135 is confirmed in the input wait process ST113, it is simultaneously determined that there is also an input in the input unit confirmation process ST21. Next, in the model generation flag confirmation process ST23, it is confirmed whether the model generation flag is ON or OFF.
  • the process proceeds to the discrimination model registration step ST103. If it is OFF, the process proceeds to the discrimination step ST4. In other words, in the predictive maintenance system 130, if there is an input to the input unit 135, the discrimination model registration step ST103 is executed with the processing content selected according to the input content to the input unit 135 as described below, and if not, the discrimination step ST4 is executed.
  • the discrimination model registration step ST103 is a process of generating and registering a discrimination model to be used for predictive maintenance of the dry vacuum pump 3 from operating parameters obtained by actually operating the dry vacuum pump 3 in a state where the operating state can be grasped in order to generate a discrimination model.
  • a single new registration process ST103A, a continuous new registration process ST103B, a single additional registration process ST103C, or a continuous additional registration process ST103D is executed depending on the state of the model generation flag in the model generation flag confirmation process ST23 and the operation status of the additional registration operation member 137a and the continuous registration operation member 137b confirmed in the additional registration confirmation process ST124 and the continuous registration confirmation process ST125 (ST125a, 125b).
  • the registration process is selected and executed as follows. That is, if it is confirmed that the additional registration operation member 137a is OFF and the continuous registration operation member 137b is OFF, a single new registration process ST103A is executed. If it is confirmed that the additional registration operation member 137a is OFF and the continuous registration operation member 137b is ON, a continuous new registration process ST103B is executed. If it is confirmed that the additional registration operation member 137a is ON and the continuous registration operation member 137b is OFF, a single additional registration process ST103C is executed. If it is confirmed that the additional registration operation member 137a is ON and the continuous registration operation member 137b is ON, a continuous additional registration process ST103D is executed.
  • the data collection process ST31, the discrimination model generation process ST32, and the discrimination model registration process ST33 are executed in sequence.
  • the collection unit 31 collects the operating parameters of the dry vacuum pump 3 for a predetermined time (for example, one hour).
  • the model generation unit 32 generates a new discrimination model based on the operating parameters collected in the data collection process ST31.
  • the discrimination model registration process ST33 the discrimination model generated in the discrimination model generation process ST32 is newly registered or updated in the registration area of the model registration unit 33 corresponding to the operating state specified when input to the input unit 35.
  • the discrimination model is read out in the discrimination model readout process ST34 so that it can be used in the discrimination step ST4 described later, and the model generation flag is changed from ON to OFF in the model generation flag OFF process ST35.
  • a data collection process ST31a In order to generate and register a first discrimination model for a first operating state (e.g., an idle operating state), a data collection process ST31a, a first discrimination model generation process ST32a, and a first discrimination model registration process ST33a are sequentially executed.
  • the collection unit 31 collects operating parameters of the dry vacuum pump 3 for a predetermined time period (e.g., one hour).
  • a new discrimination model is generated by the model generation unit 32 based on the operating parameters collected in the data collection process ST31a.
  • the first discrimination model generated in the first discrimination model generation process ST32a is newly registered or updated in the registration area of the model registration unit 33 corresponding to the first operating state.
  • the new first discrimination model is read out as a first discrimination model readout process ST34a so that it can be used in the next process and in the discrimination step ST4 described later.
  • the operation parameters of the dry vacuum pump 3 are monitored as an operation parameter monitoring process ST36 until they exceed a threshold value in order to determine whether the operating state of the dry vacuum pump 3 has changed.
  • the first discrimination model read out in the first discrimination model readout process ST34a is used to monitor until the current average value of the booster pump 4 exceeds a threshold value.
  • a second discrimination model for a second operation state e.g., a process operation state
  • a data collection process ST31b, a second discrimination model generation process ST32b, and a second discrimination model registration process ST33b are sequentially executed.
  • the collection unit 31 collects the operation parameters of the dry vacuum pump 3 for a predetermined time period (e.g., one hour).
  • the model generation unit 32 In the second discrimination model generation process ST32b, the model generation unit 32 generates a new discrimination model based on the operation parameters collected in the data collection process ST31b.
  • the second discrimination model registration process ST33b the second discrimination model generated in the second discrimination model generation process ST32b is newly registered or updated in the registration area of the model registration unit 33 corresponding to the second operation state.
  • the new second discrimination model is read in the second discrimination model read process ST34b so that it can be used in the discrimination step ST4 described below, and the model generation flag is changed from ON to OFF in the model generation flag OFF process ST35.
  • the discrimination model registration process ST33 performs the same process as the one-time new registration process ST103A, except that the discrimination model generated in the discrimination model generation process ST32 is additionally registered rather than newly registered or updated.
  • the first discrimination model registration process ST33a and the second discrimination model registration process ST33b perform the same processing as the continuous new registration process ST103B, except that the discrimination models generated in the first discrimination model generation process ST32a or the second discrimination model generation process ST32b are additionally registered rather than newly registered or updated in the first discrimination model registration process ST33a and the second discrimination model registration process ST33b.
  • the determination step ST4 is the same as in embodiment 1, so a description thereof will be omitted.
  • the vacuum pump device 1 that performs predictive maintenance using the MT method has been described as an example, but the present invention is not limited to this. It may also be a vacuum pump device that performs predictive maintenance using other analysis methods. Therefore, the discrimination model registered according to the present invention is not limited to a normal model. For example, the discrimination model may be registered as an abnormal model.
  • the dry vacuum pump 3 is described as being composed of two pumps, the booster pump 4 and the back pump 5, but the present invention is not limited to this.
  • the present invention can be applied even if the dry vacuum pump is composed of one pump, or three or more pumps.
  • the discrimination model for the booster pump is generated from the operating parameters of vibration and current
  • the discrimination model for the back pump is generated from the operating parameters of vibration, current, temperature, and back pressure
  • the discrimination model for the booster pump may be generated from the operating parameters of vibration, current, and temperature.
  • the discrimination model may be generated from operating parameters other than vibration, current, temperature, and back pressure.
  • a first discrimination model corresponding to the idle operating state of the dry vacuum pump 3 and a second discrimination model corresponding to the process operating state of the dry vacuum pump 3 are set as discrimination models, but the present invention is not limited to this.
  • a third discrimination model, a fourth discrimination model, etc. may be set corresponding to other operating states.
  • the input unit 35 is described as including, as the operation member 37, a plurality of push button switches (37a, 37b, ...) corresponding to the first registration area and the second registration area, respectively, but the present invention is not limited to this.
  • the operation member may be an operation member such as a changeover switch, an operation panel, or an operation lever that can specify and input each registration area.
  • a single push button switch may be used as the operation member, and the switching function may be realized by time or number of times, such as by long pressing or repeated pressing.
  • the input unit may be configured to include a transmitter such as a communication terminal and a receiver that is installed in the vacuum pump device and capable of receiving a signal from the transmitter, and configured to allow input to be performed remotely from the transmitter.
  • the model registration unit 33 capable of registering (storing) the discrimination model is described as being disposed inside the device case 2 in FIG. 1 and the like, but the present invention is not limited to this.
  • the model registration unit may be configured to be externally attached via a connection terminal or wireless communication.
  • a first discrimination model is generated and registered, the average current value of the booster pump 4 is monitored using the registered first discrimination model, and a second discrimination model is generated and registered when the monitored average current value exceeds a threshold value.
  • the present invention is not limited to this.
  • the present invention may be configured to automatically generate and register another discrimination model by determining that the operating state has changed by monitoring the operating parameters of the back pump 5.
  • the present invention may be configured to automatically generate and register another discrimination model by determining that the operating state has changed by monitoring operating parameters other than the average current value, such as vibration and temperature.
  • the predictive maintenance system 30 is depicted as being disposed within the equipment case 2 and connected to the operation control system 20 and the detection element 10 by internal wiring or wires, but the present invention is not limited to this.
  • the predictive maintenance system may be configured as a unit separate from the unit housed in the equipment case and disposed outside the equipment case. In this case, the predictive maintenance system may wirelessly exchange data with the operation control system and the detection element disposed within the equipment case.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Compressors, Vaccum Pumps And Other Relevant Systems (AREA)
  • Control Of Positive-Displacement Pumps (AREA)

Abstract

Ce dispositif de pompe à vide (1) comprend : une unité de collecte (31) qui collecte des paramètres de fonctionnement d'une pompe à vide sèche (3) du dispositif de pompe à vide ; une unité de génération de modèles (32) qui génère des modèles de discrimination amenés à être utilisés pour déterminer si l'état de fonctionnement est normal ou non sur la base des données collectées des paramètres de fonctionnement collectés par l'unité de collecte (31) ; une unité d'enregistrement de modèles (33) dans laquelle sont enregistrés les modèles de discrimination ; une unité de commande d'enregistrement (34) qui commande l'opération de collecte de paramètres de fonctionnement effectuée par l'unité de collecte (31), l'opération de génération de modèles de discrimination effectuée par l'unité de génération de modèles (32), et l'opération d'enregistrement de modèles de discrimination effectuée par l'unité d'enregistrement de modèles (33) ; et une unité d'entrée (35) qui émet une commande destinée à l'unité de commande d'enregistrement (34) de façon à effectuer un nouvel enregistrement, un enregistrement supplémentaire ou un enregistrement de mise à jour des modèles de discrimination. Par conséquent, les modèles de discrimination peuvent être facilement générés et enregistrés.
PCT/JP2023/012529 2023-03-28 2023-03-28 Dispositif de pompe à vide Ceased WO2024201718A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2023/012529 WO2024201718A1 (fr) 2023-03-28 2023-03-28 Dispositif de pompe à vide
JP2025509340A JPWO2024201718A1 (fr) 2023-03-28 2023-03-28

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2023/012529 WO2024201718A1 (fr) 2023-03-28 2023-03-28 Dispositif de pompe à vide

Publications (1)

Publication Number Publication Date
WO2024201718A1 true WO2024201718A1 (fr) 2024-10-03

Family

ID=92903556

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/012529 Ceased WO2024201718A1 (fr) 2023-03-28 2023-03-28 Dispositif de pompe à vide

Country Status (2)

Country Link
JP (1) JPWO2024201718A1 (fr)
WO (1) WO2024201718A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005121639A (ja) * 2003-09-22 2005-05-12 Omron Corp 検査方法および検査装置ならびに設備診断装置
JP2006258535A (ja) * 2005-03-16 2006-09-28 Omron Corp 検査装置および検査方法
JP2008524492A (ja) * 2004-12-17 2008-07-10 コリア リサーチ インスティチュート オブ スタンダーズ アンド サイエンス 真空ポンプの傾向監視及び診断解析方法、その傾向監視及び診断解析システム、及びその方法を行うコンピュータプログラムを含むコンピュータ可読記憶媒体
JP2009053938A (ja) * 2007-08-27 2009-03-12 Toshiba Corp 複数モデルに基づく設備診断システム及びその設備診断方法
JP2010122847A (ja) * 2008-11-19 2010-06-03 Hitachi Ltd 装置異常診断方法及びシステム
JP2014096050A (ja) * 2012-11-09 2014-05-22 Toshiba Corp プロセス監視診断装置、プロセス監視診断プログラム

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005121639A (ja) * 2003-09-22 2005-05-12 Omron Corp 検査方法および検査装置ならびに設備診断装置
JP2008524492A (ja) * 2004-12-17 2008-07-10 コリア リサーチ インスティチュート オブ スタンダーズ アンド サイエンス 真空ポンプの傾向監視及び診断解析方法、その傾向監視及び診断解析システム、及びその方法を行うコンピュータプログラムを含むコンピュータ可読記憶媒体
JP2006258535A (ja) * 2005-03-16 2006-09-28 Omron Corp 検査装置および検査方法
JP2009053938A (ja) * 2007-08-27 2009-03-12 Toshiba Corp 複数モデルに基づく設備診断システム及びその設備診断方法
JP2010122847A (ja) * 2008-11-19 2010-06-03 Hitachi Ltd 装置異常診断方法及びシステム
JP2014096050A (ja) * 2012-11-09 2014-05-22 Toshiba Corp プロセス監視診断装置、プロセス監視診断プログラム

Also Published As

Publication number Publication date
JPWO2024201718A1 (fr) 2024-10-03

Similar Documents

Publication Publication Date Title
JP4071449B2 (ja) センサ異常検出方法及びセンサ異常検出装置
US7509537B1 (en) Prognostic processor system for real-time failure analysis of line replaceable units
JP7260292B2 (ja) 異常診断装置及び異常診断方法
EP3578825B1 (fr) Dispositif de commande, système de commande, procédé de commande, programme et dispositif d'apprentissage machine
US20200217542A1 (en) Diagnostic method, diagnostic apparatus, diagnostic system, and non-transitory computer readable recording medium storing diagnostic program
EP3795915B1 (fr) Système de diagnostic de dysfonctionnement
CN118517777B (zh) 水冷机环境适应性智能调节系统
TWI861824B (zh) 異常診斷方法、異常診斷裝置以及異常診斷程式
WO2020189245A1 (fr) Système de détection de symptôme de dysfonctionnement et procédé de détection de symptôme de dysfonctionnement
WO2024201718A1 (fr) Dispositif de pompe à vide
JP2001331215A (ja) プラント監視装置
AU2018404247A1 (en) State analyzer system and state analysis device
US10560762B2 (en) Sensing system, sensing method, and concentrator
US12405137B2 (en) Information processing system, information processing method, recording medium, node device, gateway device, manufacturing system, method of manufacturing product
JP2007108107A (ja) 設備診断装置
CN108691769A (zh) 真空泵装置及用于真空泵装置的运转控制方法
JP7240984B2 (ja) 通知管理サーバ、および、通知管理方法
KR102936932B1 (ko) 시계열로 측정된 3상 모터 진동 데이터의 분포 추정에 따른 고장 진단 방법 및 장치
KR20120014685A (ko) 히트펌프 시스템의 정상운전상태 감지장치 및 감지방법
RU2358133C2 (ru) Система контроля узлов газовой турбины и способ ее работы
JP2005265454A (ja) 車両用故障診断装置
KR20230081860A (ko) 클라우드 서버 효율향상을 위한 엣지컨트롤러 데이터 필터링 방법
CN114816897A (zh) 基于电流信号监测机器的方法和实现这样的方法的设备
TWI801324B (zh) 冷凍設備遠端故障診斷系統及其方法
CN220105675U (zh) 极值确定装置

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: 23930358

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2025509340

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23930358

Country of ref document: EP

Kind code of ref document: A1