WO2021256017A1 - Dispositif de commande, système, procédé et programme - Google Patents

Dispositif de commande, système, procédé et programme Download PDF

Info

Publication number
WO2021256017A1
WO2021256017A1 PCT/JP2021/009555 JP2021009555W WO2021256017A1 WO 2021256017 A1 WO2021256017 A1 WO 2021256017A1 JP 2021009555 W JP2021009555 W JP 2021009555W WO 2021256017 A1 WO2021256017 A1 WO 2021256017A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
value
numerical values
time series
numerical
Prior art date
Application number
PCT/JP2021/009555
Other languages
English (en)
Japanese (ja)
Inventor
哲朗 杉原
Original Assignee
オムロン株式会社
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 オムロン株式会社 filed Critical オムロン株式会社
Publication of WO2021256017A1 publication Critical patent/WO2021256017A1/fr

Links

Images

Classifications

    • 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
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring

Definitions

  • the present invention relates to a controller, a system, a method and a program.
  • a controller that calculates statistical values such as the average value and standard deviation of time-series numerical values generated from the output signal of a sensor that observes the target state and judges the target state based on those statistical values is used. Has been done.
  • Patent Document 1 describes an abnormality determination system for determining an operation abnormality of a motor drive machine.
  • this abnormality determination system the observation operation data acquired from the motor during the observation drive of the motor drive machine and the reference data calculated based on the normal operation data acquired from the motor during the normal drive of the motor drive machine are used.
  • Patent Document 1 describes that the reference data is a sample mean and a sample covariance matrix calculated based on normal operation data and a data abnormality determination threshold. Further, it is described that when the abnormality determination system determines an abnormality in the data, the Mahalanobis distance is calculated based on the sample mean, the sample covariance matrix, and the data at the time of observation.
  • an object of the present invention is to provide a controller, a system, a method, and a program that allow a user to grasp at what timing in a time series a target state change has occurred.
  • the controller includes an acquisition unit that acquires a time-series numerical value generated from an output signal of a sensor that observes a target state, and n (n is a natural number) corresponding to a set cycle.
  • the first calculation unit that divides the time-series numerical values into groups, extracts the m-th numerical value (m is a natural number from 1 to n) in each group, and calculates the m-th statistical value, and each
  • the second calculation unit which calculates the difference between the m-th numerical value in the group and the m-th statistical value calculated by the first calculation unit, and the second calculation unit, which obtains the numerical values, are arranged according to the time series, and each numerical value is obtained. It is provided with a display information generation unit that generates display information obtained by arranging and plotting the difference values corresponding to the above in chronological order, and an output unit that outputs display information to the display unit.
  • the change in the state of the object that cannot be grasped only by the time-series numerical values can be obtained. It is possible to let the user know at what timing in the time series it occurred.
  • the reception unit that accepts the selection of at least a part of the period from the user
  • the calculation unit that calculates the feature amount from a plurality of numerical values included in the period accepted by the reception unit, and the target based on the feature amount.
  • a determination model generation unit that generates a determination model for determining the state of the above may be provided.
  • the state of the target can be judged more accurately.
  • a judgment model can be generated.
  • the period may be set based on the control signal output from the device that handles the target.
  • the first calculation unit calculates a plurality of statistical values different from each other
  • the second calculation unit calculates the difference value for each of the plurality of statistical values
  • the display information generation unit calculates a numerical value.
  • display information may be generated in which at least one difference value of a plurality of statistical values corresponding to each numerical value is arranged and plotted along the time series.
  • each difference value can be calculated from a plurality of statistical values different from each other, and these difference values can be displayed side by side along with the time series numerical values. Therefore, according to this aspect, it is possible to make the user grasp the state change of the target more comprehensively.
  • the determination unit that determines the state of the target based on the difference value, and when the determination unit determines that the state of the target is abnormal, notifies at least one of the device and the user that handles the target of the abnormality of the target. It may be provided with a notification unit.
  • the state of the target can be determined by the difference value. According to this aspect, it is possible to omit the work of extracting the feature amount from the difference value and generating a model. Therefore, according to this aspect, it is possible to determine the state of the target immediately after acquiring the numerical value in the time series and notify the device or the user who handles the target of the result of the determination.
  • a method is to obtain a time-series numerical value generated from an output signal of a sensor for observing the state of an object in a controller, and n (n is) corresponding to a set period. Divide the time-series numerical values into groups for each natural number), extract the m-th numerical value (m is a natural number from 1 to n) in each group, and calculate the m-th statistical value, and each Calculate the difference between the m-th numerical value and the calculated m-th statistical value in the group, arrange them according to the time series in which the numerical values were acquired, and set the difference values corresponding to each numerical value in time series. Generate display information plotted side by side along the line and output display information to the display unit.
  • the change in the state of the object which cannot be grasped only by the time-series numerical values, occurs at which timing in the time series. It is possible to let the user know whether or not.
  • the controller acquires a time-series numerical value generated from an output signal of a sensor for observing the state of an object, and n (n is) corresponding to a set cycle. Divide the time-series numerical values into groups for each natural number), extract the m-th numerical value (m is a natural number from 1 to n) in each group, and calculate the m-th statistical value, and each Calculate the difference between the m-th numerical value and the calculated m-th statistical value in the group, arrange them according to the time series in which the numerical values were acquired, and set the difference values corresponding to each numerical value in time series. Generate display information plotted side by side along the line and output display information to the display unit.
  • the change in the state of the object which cannot be grasped only by the time-series numerical values, occurs at which timing in the time series. It is possible to let the user know whether or not.
  • FIG. 1 is a diagram showing an outline of the system 1 according to the embodiment of the present invention.
  • the system 1 according to the present embodiment includes a controller 10, a sensor 30, a computer 40, and a transfer device 50.
  • the controller 10 is connected to the sensor 30, the computer 40, and the transport device 50, and the sensor 30 observes the target 100 to be transported one after another on the transport device 50.
  • the controller 10 acquires a time-series numerical value generated from the output signal output as an observation result of the sensor 30, and determines the state of the target 100 based on the numerical value.
  • the determination result by the controller 10 is output to the computer 40 or used for controlling the transport device 50.
  • each of the numerical values in the time series is also simply referred to as a "numerical value".
  • the controller 10 is a device that controls the movement of other devices or machines.
  • the controller 10 may be, for example, a PLC (Programmable Logic Controller) that controls these movements according to an order or conditions determined by a program.
  • the controller 10 has at least an arithmetic unit such as a CPU (Central Processing Unit), a memory, an input device, and an output device.
  • a CPU Central Processing Unit
  • the state change of the target 100 is changed by arranging the numerical value acquired from the sensor 30 and the difference value described later corresponding to each numerical value in a plot display on the display unit. It is possible to let the user know when it happened.
  • the "display unit” may be, for example, the display device of the computer 40, or may be the display unit of the controller 10 when the controller 10 includes the display unit.
  • the sensor 30 is a sensor that measures a predetermined physical amount, for example, an optical sensor that measures the presence or absence of the target 100 based on the amount of received light, or a proximity sensor that measures the presence or absence of the target 100 based on a change in the magnetic field. It may be a distance measuring sensor that measures the distance to the target 100 using light, a sensor that measures the state of the transport device 50, a temperature sensor, or a pressure sensor.
  • the computer 40 is a general-purpose computer, and has at least an arithmetic unit such as a CPU, a memory, a display device, and an input device.
  • the computer 40 displays the information received from the controller 10 and transmits the information input via the input device to the controller 10.
  • the transport device 50 is a device that handles the target 100 and is a device that transports the target 100.
  • the transport device 50 may be, for example, a belt conveyor or a roller conveyor.
  • the transport device 50 is an example of a device for operating the target 100, and the system 1 may include a device other than the transport device 50.
  • the system 1 may include a robot that operates the target 100 and a machine tool that manufactures the target 100. In that case, the robot or machine tool may be controlled by the controller 10.
  • FIG. 2 is a diagram showing a functional block of the controller 10 according to the present embodiment.
  • the controller 10 includes an acquisition unit 11, a calculation unit 12, a display information generation unit 13, an output unit 14, a reception unit 15, a calculation unit 16, a model generation unit 17, a storage unit 18, a determination unit 19, and a notification unit 20.
  • the acquisition unit 11 acquires a time-series numerical value generated from the output signal of the sensor 30 that observes the target state.
  • the time-series numerical values may be acquired at predetermined time intervals or irregularly.
  • the acquired time-series numerical values may be stored in the storage unit 18.
  • the calculation unit 12 includes a first calculation unit 12a and a second calculation unit 12b.
  • the first calculation unit 12a groups numerical values in time series for each n (n is a natural number) corresponding to a set cycle (hereinafter, also referred to as “set cycle”) (hereinafter, also referred to as “cycle group”). It is divided and the m-th numerical value (m is a natural number from 1 to n) in each cycle group is extracted to calculate the m-th statistical value.
  • the "setting cycle” may be, for example, a cycle in which the target 100 is controlled from the outside (hereinafter, also referred to as a "control cycle").
  • the control cycle may be, for example, a cycle set based on a control signal output from a device (for example, a transport device 50) that handles the target 100.
  • the control cycle may be, for example, a cycle in which the target 100 is transported by a transport device 50 by a predetermined distance, or a cycle in which the target 100 is operated by a robot or a machine tool.
  • the first calculation unit 12a may calculate, for example, a statistical value of a time-series numerical value for each set cycle. Further, the first calculation unit 12a may calculate, for example, statistical values of a plurality of numerical values included in at least a part of the set period.
  • "a plurality of numerical values included in at least a part of the set cycle” is, for example, two or more numerical values included in a specific set cycle, and is a subset of numerical values included in the specific set cycle (a subset of the numerical values included in the specific set cycle. For example, it may be m to m + 4th numerical value in the s cycle).
  • the "statistical value” is, for example, the average value, standard deviation, maximum value, minimum value, kurtosis, and / or skewness of time-series numerical values in each order or each set cycle in a set cycle over a plurality of set cycles. And so on.
  • the first calculation unit 12a may calculate, for example, a plurality of statistical values different from each other.
  • the first calculation unit 12a may calculate, for example, two different types of statistical values as the m-th average value and the standard deviation in each period group.
  • the second calculation unit 12b calculates the difference value between the m-th numerical value in each cycle group and the m-th statistical value calculated by the first calculation unit 12a.
  • the second calculation unit 12b may, for example, calculate a difference value for each of a plurality of statistical values calculated by the first calculation unit 12a.
  • the display information generation unit 13 arranges the numerical values in the acquired time series and plots the difference values corresponding to the numerical values in the time series (hereinafter, also simply referred to as “display information”). Generate.
  • the display information generation unit 13 may generate display information indicating the determination result of the state of the target 100 by the determination unit 19 described later, for example.
  • the output unit 14 outputs display information to the display unit.
  • the output unit 14 may output display information to, for example, the display device of the computer 40.
  • FIG. 3 is an example of a screen displayed on the display device of the computer 40, in which numerical values and difference values are displayed side by side in a time series and plotted.
  • this screen may be displayed on the display unit of the controller 10.
  • the screen 31 includes a first display area 31a and a second display area 31b.
  • the screen 31 displays the first display area 31a and the second display area 31b vertically side by side so as to align the horizontal axis (time axis).
  • the first display area 31a is a plot diagram showing time-series numerical values acquired by the controller 10 according to the present embodiment, that is, values generated from the output signal of the sensor 30 (hereinafter, also referred to as “sensor value plot diagram”). Is displayed.
  • the vertical axis shows the magnitude of the measured value of the time-series numerical value
  • the horizontal axis shows the time axis.
  • the second display area 31b is a plot diagram (hereinafter, also referred to as “difference value plot diagram”) showing the difference value calculated by the controller 10 according to the present embodiment.
  • the vertical axis shows the magnitude of the difference value
  • the horizontal axis shows the time axis.
  • the set cycle of 5 cycles (n to n + 4th cycle) is displayed. Further, in the sensor value plot diagram, the time-series numerical values are divided into cycle groups for each n pieces corresponding to the set cycle. In the sensor value plot diagram, as far as the user can see, the plots of the numerical values included in each period group look the same, and it seems that the abnormality of the target 100 does not occur.
  • the difference value plot diagram the set cycle of 5 cycles is displayed in the same manner, but the plot of the outliers is revealed in the cycle group of the 3rd cycle. In this way, outliers that are difficult to see in the sensor value plot are plotted so that they can be seen in the difference plot.
  • the sensor value plot diagram and the difference value plot diagram in a comparable manner, that is, in a mode in which they are arranged along the time series, which classification ( In this example, the user can grasp at which timing (for example, the mth, etc.) of the third cycle group) the state change occurs.
  • the reception unit 15 receives from the user the selection of at least a part of the set cycle in order to select the period for which the feature amount is to be calculated.
  • the "selection" referred to here may be performed via an input unit (not shown) provided in the controller 10 or may be performed via an input device of the computer 40.
  • the reception unit 15 may accept, for example, from the user the selection of whether to adopt a numerical value or a difference value as a feature amount.
  • the calculation unit 16 calculates the feature amount from a plurality of numerical values included in the period received by the reception unit 15. For example, the calculation unit 16 may calculate a statistical value as a feature quantity from a plurality of numerical values included in the period received by the reception unit 15.
  • the calculation unit 16 compares each of the plurality of numerical values included in the period received by the reception unit 15 with the set threshold value, and the feature amount is based on the magnitude relationship between each numerical value and the threshold value. May be calculated. For example, when the numerical value included in the period accepted by the reception unit 15 exceeds the threshold value, the calculation unit 16 may calculate the numerical value as a feature amount.
  • the calculation unit 16 may calculate a statistical value as a feature amount from a difference value corresponding to each of a plurality of numerical values included in the period received by the reception unit 15.
  • the model generation unit 17 generates a determination model 18a for determining the state of the target 100 based on the feature amount calculated by the calculation unit 16 (hereinafter, also simply referred to as “feature amount”).
  • the model generation unit 17 may not only store the generated determination model 18a in the storage unit 18, but also output it to an external device such as a computer 40.
  • the storage unit 18 stores at least the determination model 18a.
  • the determination model 18a may be, for example, a model in which the state of the target 100 is determined based on the magnitude relationship between the feature amount and the threshold value by comparing the feature amount with a set threshold value.
  • the determination model 18a may be, for example, a model that outputs a value representing the state of the target 100 (for example, 0: normal, 1: abnormal binary value, etc.) when a feature amount is input.
  • the determination model 18a may be a learning model such as a neural network that determines the state of the target 100 based on the feature amount.
  • the determination unit 19 determines the state of the target 100 using the determination model 18a based on the feature amount calculated by the calculation unit 16. For example, the determination unit 19 may input the feature amount into the determination model 18a and determine the state of the target 100 by the value representing the state of the target 100 output from the determination model 18a.
  • the target 100 whose state is determined by the determination unit 19 is exemplified as an object to be conveyed by the transfer device 50, but the object whose state is determined by the determination unit 19 is an arbitrary object. It may be, and the transfer device 50 may be the target, or the robot or the machine tool may be the target.
  • the determination unit 19 may determine the state of the target 100 based on the difference value.
  • the determination unit 19 may, for example, compare the difference value with the set threshold value and determine the state of the target 100 based on the magnitude relationship between the difference value and the threshold value. For example, when the difference value exceeds the set threshold value, the determination unit 19 may determine the state of the target 100 as abnormal.
  • the notification unit 20 notifies at least one of the device (for example, the transport device 50) that handles the target 100 and the user of the abnormality of the target 100.
  • the notification unit 20 when the determination unit 19 determines that the state of the target 100 is abnormal, the notification unit 20 outputs a signal for notifying the device handling the target 100 of the abnormality of the target 100 to the device via the output unit 14. May be good. Further, the notification unit 20 may generate display information for notifying the user of the abnormality of the target 100 when the determination unit 19 determines that the state of the target 100 is abnormal. The notification unit 20 may output the generated display information to the display unit via the output unit 14.
  • FIG. 4 is a flowchart showing the flow of the determination model generation process.
  • the acquisition unit 11 of the controller 10 acquires a time-series numerical value generated from the output signal of the sensor 30 for observing the state of the target 100 (S10).
  • the first calculation unit 12a divides the time-series numerical values into cycle groups for each n pieces corresponding to the set cycle, and determines the trigger for each cycle group (S11).
  • the trigger is the numerical value at the earliest point in the periodic group, but the purpose is not limited to this.
  • the acquisition unit 11 associates the acquired numerical value with the order s of the cycle group and the order m from the trigger in the cycle group (S12).
  • V (s, m) be the numerical value of this associated time series.
  • the order s of the cycle group is, for example, a number indicating the order of n, n + 1, n + 2 ... (cycle th) and the like with respect to the set cycle shown in FIG.
  • the order m from the trigger for example, if the numerical value at the earliest time in the cycle group is the order "1", the numerical value acquired next is the order "2", and the numerical value acquired next is the order "3". ", Which is the number incremented in the order of acquisition.
  • the first calculation unit 12a extracts the m-th numerical value in each cycle group and calculates the m-th average value Ave (m) (S13).
  • the first calculation unit 12a is, for example, order 1 to order s.
  • the second calculation unit 12b has a difference value W (s, m) between the m-th numerical value V (s, m) in each cycle group and the m-th average value Ave (m) calculated by the first calculation unit 12a. m) is calculated respectively (S14).
  • the output unit 14 arranges the numerical values V (s, m) along the acquired time series, and displays the display information in which the difference values W (s, m) corresponding to the respective numerical values are arranged and plotted in the time series. Output to the unit (S15).
  • the reception unit 15 receives from the user the selection of at least a part of the set cycle (S16).
  • the reception unit 15 accepts the selection of whether to adopt the numerical value V (s, m) or the difference value W (s, m) as the feature amount (S17).
  • the calculation unit 16 When the value received by the reception unit 15 in step S17 is the difference value W (s, m) (“difference value” in S18), the calculation unit 16 has the difference value W for a part of the section received by the reception unit 15. The statistical value of (s, m) is calculated as a feature amount (S19).
  • step S17 When the value received by the reception unit 15 in step S17 is a numerical value V (s, m) (“numerical value” in S18), the calculation unit 16 has a time-series numerical value V for a part of the section received by the reception unit 15. The statistical value of (s, m) is calculated as a feature quantity (S20).
  • the model generation unit 17 generates a determination model 18a for determining the state of the target 100 based on the feature amount calculated by the calculation unit 16 (S21).
  • FIG. 5 is a flowchart showing the flow of the determination process of the state of the target 100.
  • the initial values of the order s and the order m are both set to "1".
  • the acquisition unit 11 of the controller 10 acquires a time-series numerical value generated from the output signal of the sensor 30 for observing the state of the target 100 (S30).
  • the acquisition unit 11 When the value received by the reception unit 15 in the determination model generation process (for example, step S17 in FIG. 4) is the difference value W (s, m) (“difference value” in S31), the acquisition unit 11 has acquired the numerical value.
  • the order s of the cycle group and the order m from the trigger in the cycle group are associated with each (S32).
  • the first calculation unit 12a extracts the m-th numerical value in each cycle group and calculates the m-th average value Ave (m) (S33).
  • the second calculation unit 12b calculates the difference value W (s, m) between the m-th numerical value V (s, m) and the m-th average value Ave (m) calculated by the first calculation unit 12a (. S34).
  • the calculation unit 16 calculates the feature amount from a plurality of numerical values included in the period accepted by the reception unit 15 (S36).
  • the determination unit 19 inputs the feature amount calculated by the calculation unit 16 into the determination model 18a, and determines the state of the target 100 with the output of the determination model 18a (S37).
  • the output unit 14 outputs display information indicating the result of the above determination by the determination unit 19 to the display unit (S38).
  • step S40 When m ⁇ n, that is, when the setting cycle is not one week (No in S35), the controller 10 increments the order m (S40). The flow transitions before step S30.
  • step S41 When the determination process of the state of the target 100 is not completed (No in S39), the controller 10 increments the order s (S41). The flow transitions before step S30.
  • the embodiments in this embodiment include the following disclosures.
  • An acquisition unit (11) that acquires a time-series numerical value generated from an output signal of a sensor (30) that observes the state of the target (100), and The time-series numerical values are divided into groups for each n (n is a natural number) corresponding to the set cycle, and the m-th numerical value (m is a natural number from 1 to n) in each group is extracted and m.
  • the first calculation unit (12a) that calculates the second statistical value
  • the second calculation unit (12b) that calculates the difference between the m-th numerical value in each group and the m-th statistical value calculated by the first calculation unit, respectively.
  • a display information generation unit (13) that generates display information in which numerical values are arranged along the acquired time series and the difference values corresponding to the respective numerical values are arranged and plotted along the time series.
  • An output unit (14) that outputs display information to the display unit is provided. Controller (10).

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

L'invention concerne un dispositif de commande (10) comprenant : une unité d'acquisition (11) qui acquiert des valeurs numériques dans une série chronologique, lesdites valeurs étant générées à partir d'un signal de sortie d'un capteur qui observe l'état d'un sujet ; une première unité de calcul (12a) qui sépare les valeurs numériques dans la série chronologique en groupes constitués chacun de n valeurs (n étant un nombre naturel) correspondant à un cycle défini, extrait la mième (m étant un nombre naturel de 1 à n) valeur numérique dans chacun des groupes, et calcule une mième valeur statistique ; une seconde unité de calcul (12b) qui calcule des valeurs de différence respectives entre la mième valeur numérique dans chacun des groupes et la mième valeur statistique calculée par la première unité de calcul ; une unité de génération d'informations d'affichage (13) qui génère des informations d'affichage dans lesquelles les valeurs numériques sont tracées le long de la série chronologique acquise et les valeurs de différence correspondant à chacune des valeurs numériques sont tracées le long d'une série chronologique ; et une unité de sortie (14) qui émet en sortie les informations d'affichage à une unité d'affichage.
PCT/JP2021/009555 2020-06-16 2021-03-10 Dispositif de commande, système, procédé et programme WO2021256017A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020103808A JP2021196950A (ja) 2020-06-16 2020-06-16 コントローラ、システム、方法及びプログラム
JP2020-103808 2020-06-16

Publications (1)

Publication Number Publication Date
WO2021256017A1 true WO2021256017A1 (fr) 2021-12-23

Family

ID=79195763

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/009555 WO2021256017A1 (fr) 2020-06-16 2021-03-10 Dispositif de commande, système, procédé et programme

Country Status (2)

Country Link
JP (1) JP2021196950A (fr)
WO (1) WO2021256017A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002215226A (ja) * 2001-01-16 2002-07-31 Shinko Electric Co Ltd プラント運転監視装置、その制御方法、プログラムおよび記録媒体
JP2004133588A (ja) * 2002-10-09 2004-04-30 Toshiba Corp トレンドグラフ表示装置
JP2018116545A (ja) * 2017-01-19 2018-07-26 オムロン株式会社 予測モデル作成装置、生産設備監視システム、及び生産設備監視方法
JP2019079452A (ja) * 2017-10-27 2019-05-23 株式会社安川電機 異常判定システム、データ送受装置、モータ制御装置、及び異常判定方法
JP6609391B1 (ja) * 2019-03-20 2019-11-20 株式会社 日立産業制御ソリューションズ 予測モデル作成装置、予測モデル作成方法及び予測モデル作成プログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002215226A (ja) * 2001-01-16 2002-07-31 Shinko Electric Co Ltd プラント運転監視装置、その制御方法、プログラムおよび記録媒体
JP2004133588A (ja) * 2002-10-09 2004-04-30 Toshiba Corp トレンドグラフ表示装置
JP2018116545A (ja) * 2017-01-19 2018-07-26 オムロン株式会社 予測モデル作成装置、生産設備監視システム、及び生産設備監視方法
JP2019079452A (ja) * 2017-10-27 2019-05-23 株式会社安川電機 異常判定システム、データ送受装置、モータ制御装置、及び異常判定方法
JP6609391B1 (ja) * 2019-03-20 2019-11-20 株式会社 日立産業制御ソリューションズ 予測モデル作成装置、予測モデル作成方法及び予測モデル作成プログラム

Also Published As

Publication number Publication date
JP2021196950A (ja) 2021-12-27

Similar Documents

Publication Publication Date Title
CN107924173B (zh) 监视装置、监视系统及计算机可读存储介质
US10657477B2 (en) Work data management system and work data management method
WO2016143072A1 (fr) Automate programmable industriel
US11493912B2 (en) Unsteadiness detection device, unsteadiness detection system and unsteadiness detection method
JP4957406B2 (ja) バッチプロセス解析システムおよびバッチプロセス解析方法
JP5062496B2 (ja) 運転状態解析システムおよび運転状態解析方法
WO2021256017A1 (fr) Dispositif de commande, système, procédé et programme
CN113874800B (zh) 提高生产效率的支援系统
CN110072670A (zh) 监测拧紧工具中能量流的方法、监测节点及计算机程序
JP7031512B2 (ja) 鉄鋼プラント用監視作業支援システム
JP2023178206A (ja) 異常検知装置、異常検知方法およびプログラム
JP6885321B2 (ja) プロセスの状態診断方法及び状態診断装置
JP7029647B2 (ja) コントローラ、システム、方法及びプログラム
JP2021179981A (ja) 情報処理システム、情報処理装置およびプログラム
WO2024116560A1 (fr) Dispositif de détermination d'anomalie et procédé de détermination d'anomalie
WO2021250959A1 (fr) Contrôleur, système, procédé et programme
CN107924186B (zh) 生成机器心跳的方法
WO2020203772A1 (fr) Système de support d'amélioration de rendement de production
CN113366528B (zh) 检查系统
JP7484281B2 (ja) 対策方法選定支援システム、及び方法
TWI735784B (zh) 資訊分析裝置、資訊分析方法及資訊分析程式產品
JP5286871B2 (ja) プレス工程の合否判定方法及び装置
US20210326600A1 (en) Information management device and information management method
JP2023023790A (ja) 成形管理装置
CN115195067A (zh) 成型机管理系统

Legal Events

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

Ref document number: 21825982

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21825982

Country of ref document: EP

Kind code of ref document: A1