WO2025203302A1 - 情報処理装置、情報処理方法、及び情報処理プログラム - Google Patents

情報処理装置、情報処理方法、及び情報処理プログラム

Info

Publication number
WO2025203302A1
WO2025203302A1 PCT/JP2024/012194 JP2024012194W WO2025203302A1 WO 2025203302 A1 WO2025203302 A1 WO 2025203302A1 JP 2024012194 W JP2024012194 W JP 2024012194W WO 2025203302 A1 WO2025203302 A1 WO 2025203302A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
parameter
physical parameter
normal
diagnosis
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.)
Pending
Application number
PCT/JP2024/012194
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
英明 寺島
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.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
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 Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to PCT/JP2024/012194 priority Critical patent/WO2025203302A1/ja
Priority to JP2026509515A priority patent/JPWO2025203302A1/ja
Publication of WO2025203302A1 publication Critical patent/WO2025203302A1/ja
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

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

  • This disclosure relates to an information processing device, an information processing method, and an information processing program.
  • Changes in the characteristics of each physical parameter (such as temperature and operating speed) related to the equipment to be diagnosed can change the operating noise and vibration of the equipment to be diagnosed. Furthermore, changes in the characteristics of each physical parameter can change the characteristics of the sensor measurement results, which can result in a decrease in the accuracy of abnormality diagnosis. Therefore, it is desirable to consider the characteristics of each physical parameter and the operating noise and vibration of the machine when estimating the cause of a decrease in the accuracy of abnormality diagnosis for the equipment to be diagnosed.
  • the technology disclosed in Patent Document 1 does not consider the characteristics of each physical parameter and the operating noise and vibration of the equipment to be diagnosed when estimating the cause of a decrease in the accuracy of abnormality diagnosis for the equipment to be diagnosed.
  • the present disclosure aims to take into consideration the characteristics of each physical parameter corresponding to a physical quantity in a device to be diagnosed and the operating noise or vibration of the machine when estimating the cause of a decrease in the accuracy of abnormality diagnosis for the device to be diagnosed.
  • the information processing device includes: a normal/abnormality diagnosing unit that, when each physical parameter of a physical parameter group consisting of a plurality of physical parameters each corresponding to a physical quantity in a diagnosis target device is taken as a target physical parameter, inputs feature quantities corresponding to target input data, which is data acquired in the diagnosis target device and corresponds to time-series data indicating frequency, into a normal/abnormality diagnosing model to acquire target output data used to diagnose the diagnosis target device and estimated values of the target physical parameters, and determines whether or not an abnormality has occurred in the diagnosis target device based on the target output data; a parameter estimation unit that acquires an estimate of the target physical parameter by inputting a feature quantity corresponding to the target input data into a parameter estimation model corresponding to the target physical parameter;
  • the device is equipped with an integration unit that outputs information corresponding to the difference between the estimated value of the target physical parameter using the normal/abnormal diagnosis model and the estimated value of the target physical parameter using a parameter estimation model corresponding to the target
  • the integrating unit outputs a result corresponding to the difference between the estimated value of the target physical parameter according to the normal/abnormality diagnosis model and the estimated value of the target physical parameter according to the parameter estimation model corresponding to the target physical parameter, and the result of determining whether or not an abnormality has occurred in the device to be diagnosed.
  • the normal/abnormality diagnosis model and each parameter estimation model receive as input feature quantities corresponding to target input data, which is data acquired in the device to be diagnosed and corresponds to time-series data indicating frequency.
  • FIG. 2 is a diagram showing an example of the configuration of an information processing device 100 during learning according to the first embodiment.
  • FIG. 2 is a diagram showing an example of the configuration of the information processing device 100 at the time of diagnosis according to the first embodiment.
  • 3A and 3B are diagrams illustrating a normal/abnormal diagnosis model according to the first embodiment.
  • 3A to 3C are diagrams illustrating parameter estimation models according to the first embodiment.
  • 5A and 5B are diagrams for explaining the processing of an integration unit 160 according to the first embodiment.
  • FIG. 1 is a diagram showing an example of the hardware configuration of an information processing device 100 according to a first embodiment.
  • 4 is a flowchart showing the operation of the information processing device 100 during learning according to the first embodiment.
  • FIG. 6 is a flowchart showing the operation of the information processing device 100 during diagnosis according to the first embodiment.
  • FIG. 10 is a diagram showing an example of the hardware configuration of an information processing device 100 according to a modification of the first embodiment.
  • FIG. 10 is a diagram showing an example of the configuration of an information processing device 100 at the time of collecting advance data according to a second embodiment.
  • FIG. 10 is a diagram showing an example of the configuration of an information processing device 100 during learning according to a second embodiment.
  • 10 is a flowchart showing the operation of the information processing device 100 during advance data collection according to the second embodiment.
  • 10 is a flowchart showing the operation of the information processing device 100 during learning according to the second embodiment.
  • the normal/abnormal diagnosis model corresponds to an estimator that estimates multiple physical parameters.
  • a regression model such as linear regression or symbolic regression is used as each dedicated model.
  • Each dedicated model corresponds to an estimator for each physical parameter.
  • the sound data is converted into the frequency domain using FFT (Fast Fourier Transform) or the like and used as features. Then, an estimator that estimates multiple physical parameters is created using the training data. When the evaluation data is input, each estimator estimates each physical parameter.
  • the threshold may be a preset value or may be a value derived using a statistical test or the like.
  • a domain shift is a state in which the characteristics of input data differ from the characteristics of normal data input during learning.
  • a domain shift may also be a state in which the characteristics of each physical quantity related to the input data differ from the characteristics of each physical quantity related to normal data input during learning.
  • Normal data is data corresponding to a normal state. Specific examples of normal data include data acquired in a normal state and data calculated based on the data acquired in the normal state.
  • a normal state is a state in which no abnormalities are observed.
  • domain shift causes a decrease in the diagnostic accuracy of the normal/abnormal diagnosis model.
  • causes of changes in data characteristics include changes in temperature, voltage, and sensor installation position.
  • the device to be diagnosed expands or contracts, which may change the tone of the operating sound.
  • the operating speed of the device to be diagnosed changes, which may change the period of the rotation sound of a motor or the like.
  • the sensor installation position changes, the distance between the device to be diagnosed and the microphone changes, which may change the volume of the operating sound.
  • the change in sound data and vibration data that can be acquired from the equipment to be diagnosed is treated as a domain shift.
  • FIG. 1 shows an example configuration of an information processing device 100 during learning according to the first embodiment.
  • the information processing device 100 may be part of the device to be diagnosed, or may be a device communicably connected to the device to be diagnosed.
  • the information processing device 100 includes an input unit 110, a feature amount calculation unit 120, a normal/abnormal diagnosis unit 130, a parameter estimation unit 140, and a parameter difference calculation unit 150.
  • the information processing device 100 also stores a normal data reference value DB 191, a parameter estimation model DB 192, and a parameter difference DB 193.
  • DB is an abbreviation for database.
  • the feature amount calculation unit 120, the normal/abnormal diagnosis unit 130, the parameter estimation unit 140, and the parameter difference calculation unit 150 are collectively referred to as a learning unit.
  • the information processing device 100 further includes an integration unit 160 and an output unit 170.
  • the input unit 110 includes only a microphone and a vibration sensor.
  • the feature calculation unit 120, the normal/abnormal diagnosis unit 130, the parameter estimation unit 140, the parameter difference calculation unit 150, and the integration unit 160 are collectively referred to as a diagnosis unit.
  • the information processing device 100 at the time of diagnosis may include each of the elements included in the information processing device 100 at the time of learning. However, among the elements included in the information processing device 100 at the time of learning, elements not shown in FIG. 2 are not used at the time of diagnosis.
  • All sensors included in the input unit 110 acquire data.
  • the feature amount calculation unit 120 calculates feature amounts related to frequency.
  • the feature amount calculation unit 120 calculates frequency domain data from sound data or vibration data using FFT, wavelet, or the like, and calculates feature amounts such as RMS (Root Mean Square) related to the calculated frequency domain data.
  • the feature calculation unit 120 performs the same operation during both learning and evaluation.
  • the normal/abnormality diagnosis unit 130 learns a normal/abnormality diagnosis model based on input data and physical quantities acquired by a sensor that acquires physical quantities corresponding to target physical parameters.
  • the input data is data acquired in the device to be diagnosed and corresponds to time-series data indicating frequency.
  • the normal/abnormality diagnosis unit 130 may learn the normal/abnormality diagnosis model by unsupervised learning.
  • the normalcy/abnormality diagnosis unit 130 performs normalcy/abnormality diagnosis using a normalcy/abnormality diagnosis model.
  • the normalcy/abnormality diagnosis unit 130 inputs feature quantities corresponding to target input data into the normalcy/abnormality diagnosis model to obtain target output data corresponding to the target input data and an estimated value of the target physical parameter.
  • the normalcy/abnormality diagnosis unit 130 also determines whether an abnormality has occurred in the diagnosis target device based on the target output data.
  • the normalcy/abnormality diagnosis unit 130 may determine whether an abnormality has occurred in the diagnosis target device based on the difference between the target input data and the target output data.
  • the target output data is data used to diagnose the diagnosis target device.
  • the target output data may be data corresponding to the target input data.
  • Condition 1 The model can be trained using only normal data.
  • Condition 2 It is possible to learn a model that estimates each physical parameter simultaneously with learning about the degree of anomaly.
  • the normal/abnormality diagnosis model includes generative models such as an AE (Auto Encoder), a VAE (Variational Auto Encoder), or flow.
  • AE Auto Encoder
  • VAE Virtual Auto Encoder
  • flow a conditional Auto Encoder
  • the normal/abnormality diagnosis model when an AE or a VAE is used as the normal/abnormality diagnosis model, the difference between input data and output data is output as the degree of anomaly.
  • the normality/abnormality diagnosis unit 130 performs different operations during learning and diagnosis as described below.
  • the normal/abnormality diagnosis unit 130 learns a normal/abnormality diagnosis model using only normal data. After learning, the normal/abnormality diagnosis unit 130 stores reference values required for normal/abnormal diagnosis in the normal data reference value DB 191. As a specific example, the normal/abnormality diagnosis unit 130 determines the reference values using the abnormality degrees obtained during learning through methods such as Hotelling's theory or quartiles. At the same time, the normal/abnormality diagnosis unit 130 also stores the estimation results of each physical parameter in the normal data reference value DB 191.
  • the normal/abnormality diagnosis unit 130 inputs data, which is unclear as to whether the data corresponds to a normal state or an abnormal state, into the normal/abnormality diagnosis model.
  • the normal/abnormality diagnosis model then outputs the degree of abnormality and also outputs the estimation results of each physical parameter.
  • the normal/abnormal diagnosis unit 130 acquires a reference value from the normal data reference value DB 191, and judges it to be abnormal if the output abnormality level exceeds the acquired reference value, and judges it to be normal otherwise.
  • x indicates sound data or vibration data.
  • x is input to the normal/abnormal diagnosis model and each parameter estimation model.
  • x may also indicate a feature value corresponding to each data.
  • x' indicates sound data or vibration data output by the normal/abnormal diagnosis model.
  • x' may also indicate a feature value corresponding to each data.
  • D indicates the entire data set.
  • N D indicates the number of data included in D.
  • N x indicates the number of dimensions of x.
  • the abnormality level A is defined as shown in [Equation 2], and the normal/abnormality diagnosis unit 130 sets a threshold value for the abnormality level A for abnormality detection during learning using the Hotelling theory, quartiles, or the like.
  • the parameter estimation unit 140 trains each parameter estimation model.
  • Each parameter estimation model is a model that predicts physical parameters obtained from each sensor for estimating physical parameters from data obtained from a sensor for normal/abnormal diagnosis.
  • One parameter estimation model corresponds to one sensor for estimating physical parameters.
  • a specific example of the parameter estimation model is a regression model corresponding to linear regression or symbolic regression.
  • Each parameter estimation model constitutes a parameter estimation model group.
  • the parameter estimation model corresponding to the target physical parameter is a model that takes as input a feature corresponding to data acquired from the equipment to be diagnosed, which data corresponds to time series data indicating frequency, and outputs an estimated value of the target physical parameter.
  • Fig. 4 shows an overview of each parameter estimation model. Fig.
  • the parameter estimation unit 140 learns a parameter estimation model corresponding to the target physical parameter based on the input data and a physical quantity acquired by a sensor that acquires a physical quantity corresponding to the target physical parameter.
  • the parameter estimation unit 140 learns a model that estimates each physical parameter using only normal data.
  • the parameter estimation unit 140 creates parameter estimation models in the same number as the number of sensors used to estimate the physical parameters.
  • the parameter estimation unit 140 estimates each physical parameter using each parameter estimation model and data acquired by a sensor for normal/abnormal diagnosis. Specifically, the parameter estimation unit 140 acquires an estimated value of the target physical parameter by inputting a feature quantity corresponding to the target input data into a parameter estimation model corresponding to the target physical parameter.
  • the input data for each parameter estimation model is, for example, sound data.
  • the parameter difference calculation unit 150 calculates the difference between each physical parameter calculated by the normal/abnormal diagnosis model and each physical parameter calculated by each parameter estimation model as the difference calculation result.
  • the parameter difference calculation unit 150 operates differently during learning and during diagnosis, as described below.
  • the parameter difference calculation unit 150 stores the difference calculation results for each physical parameter in the parameter difference DB 193 .
  • the parameter difference calculation unit 150 calculates, for each physical parameter, the difference between the estimation result based on the normal/abnormal diagnosis model and the estimation result based on each parameter estimation model as a difference calculation result. Furthermore, the parameter difference calculation unit 150 obtains, for each physical parameter, the difference in normal data from the parameter difference DB 193 as a reference value, and determines whether the current difference calculation result exceeds the obtained reference value.
  • the reference value corresponding to the target physical parameter corresponds to the difference threshold corresponding to the target physical parameter.
  • the difference regarding the i-th physical parameter is calculated as shown in [Equation 3] as a specific example.
  • the integrating unit 160 integrates the determination result by the normal/abnormality diagnosis unit 130 and the determination result by the parameter difference calculation unit 150. Specifically, the integrating unit 160 outputs information corresponding to the difference between the estimated value of the target physical parameter according to the normal/abnormality diagnosis model and the estimated value of the target physical parameter according to the parameter estimation model corresponding to the target physical parameter, and the result of the determination as to whether an abnormality has occurred in the diagnosis target device.
  • the integrating unit 160 may output information indicating that, for the physical quantity corresponding to the target physical parameter, the physical characteristics at the time of learning the normal/abnormality diagnosis model differ from the physical characteristics at the time the target input data was acquired.
  • the integration unit 160 may not output information indicating that the physical characteristics of the physical quantity corresponding to the target physical parameter at the time of learning the normal/abnormal diagnosis model are different from the physical characteristics at the time the target input data was acquired, but may output information indicating the result of determining whether or not an abnormality has occurred in the equipment to be diagnosed.
  • the integration unit 160 appropriately outputs the result of determining whether the domain is normal or abnormal, and each physical parameter that may be the cause of the domain shift.
  • the integration unit 160 When the normality/abnormality diagnosis unit 130 determines that an abnormality has occurred, if all of the difference calculation results related to the physical parameters are equal to or less than the reference value, the integration unit 160 outputs information indicating that the equipment to be diagnosed is abnormal. When the normal/abnormality diagnosis unit 130 determines an abnormality and any of the difference calculation results related to the physical parameters exceeds a reference value, the integrating unit 160 outputs information indicating that the degree of abnormality is increasing due to the occurrence of a domain shift or an abnormality in the device to be diagnosed. The integrating unit 160 also outputs information indicating that each physical parameter corresponding to the difference calculation result exceeding the reference value may be the cause of the domain shift.
  • the output unit 170 outputs the output of the integration unit 160 to the outside of the information processing device 100.
  • the information processing device 100 is made up of a computer.
  • the information processing device 100 may be made up of multiple computers.
  • the information processing device 100 is connected to various sensors, input devices, and output devices.
  • the information processing device 100 is a computer equipped with a processor 11, a main memory device 12, and an auxiliary memory device 13. These pieces of hardware are connected as appropriate via signal lines.
  • the processor 11 is an integrated circuit (IC) that performs arithmetic processing and controls the hardware of the computer. Specific examples of the processor 11 include a central processing unit (CPU), a digital signal processor (DSP), or a graphics processing unit (GPU).
  • the information processing apparatus 100 may include a plurality of processors that replace the processor 11. The plurality of processors share the role of the processor 11.
  • the main memory device 12 is typically a volatile memory device, a specific example of which is RAM (Random Access Memory).
  • the main memory device 12 is also called the main memory device or main memory. Data stored in the main memory device 12 is saved in the auxiliary memory device 13 as needed.
  • the auxiliary storage device 13 is typically a non-volatile storage device, and specific examples thereof include a ROM (Read Only Memory), an HDD (Hard Disk Drive), or a flash memory. Data stored in the auxiliary storage device 13 is loaded into the main storage device 12 as needed.
  • the main storage device 12 and the auxiliary storage device 13 may be configured as an integrated unit.
  • Embodiment 2 The following mainly describes the differences from the above-described embodiment with reference to the drawings.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)
PCT/JP2024/012194 2024-03-27 2024-03-27 情報処理装置、情報処理方法、及び情報処理プログラム Pending WO2025203302A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2024/012194 WO2025203302A1 (ja) 2024-03-27 2024-03-27 情報処理装置、情報処理方法、及び情報処理プログラム
JP2026509515A JPWO2025203302A1 (cg-RX-API-DMAC7.html) 2024-03-27 2024-03-27

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2024/012194 WO2025203302A1 (ja) 2024-03-27 2024-03-27 情報処理装置、情報処理方法、及び情報処理プログラム

Publications (1)

Publication Number Publication Date
WO2025203302A1 true WO2025203302A1 (ja) 2025-10-02

Family

ID=97218062

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2024/012194 Pending WO2025203302A1 (ja) 2024-03-27 2024-03-27 情報処理装置、情報処理方法、及び情報処理プログラム

Country Status (2)

Country Link
JP (1) JPWO2025203302A1 (cg-RX-API-DMAC7.html)
WO (1) WO2025203302A1 (cg-RX-API-DMAC7.html)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2022190376A (ja) * 2021-06-14 2022-12-26 株式会社日立製作所 異常検知システムおよび方法
JP2024041064A (ja) * 2022-09-13 2024-03-26 ローベルト ボツシユ ゲゼルシヤフト ミツト ベシユレンクテル ハフツング センサ測定値の異常検出

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7493930B2 (ja) * 2019-12-10 2024-06-03 キヤノン株式会社 情報処理方法、情報処理装置、生産システム、プログラム、記録媒体

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2022190376A (ja) * 2021-06-14 2022-12-26 株式会社日立製作所 異常検知システムおよび方法
JP2024041064A (ja) * 2022-09-13 2024-03-26 ローベルト ボツシユ ゲゼルシヤフト ミツト ベシユレンクテル ハフツング センサ測定値の異常検出

Also Published As

Publication number Publication date
JPWO2025203302A1 (cg-RX-API-DMAC7.html) 2025-10-02

Similar Documents

Publication Publication Date Title
CN112955839B (zh) 异常检测装置、异常检测方法和程序
JP4183185B2 (ja) 診断装置、検出装置、制御方法、検出方法、プログラム、及び記録媒体
JP3254624B2 (ja) スティックスリップ検出方法および検出装置
JP2004150439A (ja) 故障事象を判定する方法
US8355879B2 (en) Trending of vibration data taking into account torque effect
JP2015170121A (ja) 異常診断装置及びプログラム
JP5771317B1 (ja) 異常診断装置及び異常診断方法
JP2023126703A (ja) 異常検出装置、異常検出方法、及びプログラム
JP7188143B2 (ja) 異常予兆検出システム、異常予兆検出方法
JP2004156616A (ja) 高温計信号と関連させてニューラルネットワーク利用診断技法を使用してタービンブレード(バケット)の健康状態を監視し、予後を診断する方法
CN119025953A (zh) 噪声点故障诊断方法及故障诊断系统
TW202343247A (zh) 異常診斷方法、異常診斷裝置以及異常診斷程式
JPWO2004068078A1 (ja) 状態判定方法と状態予測方法及び装置
JP3759881B2 (ja) 加工診断監視システム
JP2002181038A (ja) 異常診断装置
JP7350667B2 (ja) 異常検出装置、回転機械、異常検出方法、及びプログラム
JP7770646B2 (ja) 検知装置,検知方法およびプログラム
CN115825480B (zh) 轮速信号分析方法、装置、设备及存储介质
JP2024025095A (ja) トレンド算出装置、トレンド算出システム、及び、トレンド算出方法
KR102936932B1 (ko) 시계열로 측정된 3상 모터 진동 데이터의 분포 추정에 따른 고장 진단 방법 및 장치
JP2021110977A (ja) 診断装置、診断方法およびプログラム
JP3710126B2 (ja) 測定波形診断方法およびその装置
JP7603512B2 (ja) 異常検出装置、異常検出方法、およびプログラム
JP2020067750A (ja) 学習方法、装置及びプログラム、並びに設備の異常診断方法
JP2016045853A (ja) 異常診断装置及び異常診断方法

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: 24932475

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2026509515

Country of ref document: JP

Kind code of ref document: A