WO2020158466A1 - 支援装置、支援方法及び支援プログラム - Google Patents

支援装置、支援方法及び支援プログラム Download PDF

Info

Publication number
WO2020158466A1
WO2020158466A1 PCT/JP2020/001593 JP2020001593W WO2020158466A1 WO 2020158466 A1 WO2020158466 A1 WO 2020158466A1 JP 2020001593 W JP2020001593 W JP 2020001593W WO 2020158466 A1 WO2020158466 A1 WO 2020158466A1
Authority
WO
WIPO (PCT)
Prior art keywords
learning data
parameter
point position
change point
input
Prior art date
Application number
PCT/JP2020/001593
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
剛史 西
Original Assignee
住友重機械工業株式会社
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 住友重機械工業株式会社 filed Critical 住友重機械工業株式会社
Priority to KR1020217022490A priority Critical patent/KR20210124214A/ko
Priority to JP2020569512A priority patent/JP7449248B2/ja
Publication of WO2020158466A1 publication Critical patent/WO2020158466A1/ja

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
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • 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
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • 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
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0267—Fault communication, e.g. human machine interface [HMI]
    • G05B23/0272—Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present invention relates to an assisting device, an assisting method, and an assisting program for acquiring a parameter for identifying a change with time of a measurement value of a sensor.
  • monitoring devices capable of detecting state changes of various process systems
  • monitoring devices disclosed in Patent Documents 1 and 2 are known.
  • a monitoring device since it is determined whether or not a process state change has occurred by identifying a change over time in the measurement value of the sensor, it is possible to acquire a parameter for identifying the change over time. Required.
  • One of the exemplary objects of an aspect of the present invention is to provide a support device, a support method, and a support program for easily acquiring a parameter that specifies a change with time of a measurement value of a sensor.
  • an assisting device for acquiring a parameter that specifies a change with time of a measured value of a sensor, and changes with time of a measured value of a first sensor. And a second acquisition data for acquiring the first learning data and the second learning data showing the change with time of the measurement value of the second sensor and having a correlation with the first learning data, , A parameter for acquiring a parameter having a predetermined value based on an input unit for inputting a parameter and a change point position of the first learning data and a change point position of the second learning data corresponding to the parameter input by the input unit And an acquisition unit.
  • the first learning data and the second learning data having the correlation with the first learning data are acquired, and the first learning data corresponding to the parameter input by the input unit is acquired.
  • a parameter having a predetermined value is acquired based on the change point position and the change point position of the second learning data. According to this, it is possible to easily acquire the parameter that specifies the change with time of the measurement value of the sensor.
  • This method is a support method for acquiring a parameter for identifying a change with time of a measurement value of a sensor, and includes a first learning data indicating a change with time of a measurement value of a first sensor and a second learning sensor. Acquiring the second learning data, which shows a change with time of the measured value and has a correlation with the first learning data, by the data acquiring unit, inputting a parameter by the input unit, and The parameter acquisition unit acquires a parameter having a predetermined value based on the change point position of the first learning data and the change point position of the second learning data corresponding to the parameter input by the input unit.
  • Yet another aspect of the present invention is a support program.
  • This program is a support program executed by a computer to acquire a parameter for identifying a change in the measured value of the sensor with time, and a first learning that indicates to the computer the change in the measured value of the first sensor with time.
  • Data and second learning data showing a change with time of the measurement value of the second sensor and having a correlation with the first learning data, and input by the input unit.
  • the parameter acquisition unit Based on the change point position of the first learning data and the change point position of the second learning data corresponding to the parameter, acquires a parameter having a predetermined value.
  • 6 is a flowchart showing an example of a support method by the support device 10.
  • 6 is a flowchart showing an example of a support method by the support device 10. It is a figure for demonstrating the k-nearest neighbor method which is an example of the calculation method of the change point position of measurement data. It is a figure for explaining singular spectrum conversion which is an example of a calculation method of a change point position of measurement data.
  • 6 is a diagram for explaining a support method by the support device 10.
  • FIG. 1 to 6 are diagrams for explaining a support device and a support method according to an embodiment of the present invention.
  • FIG. 1 is a diagram showing a configuration of a support device 10 according to an embodiment of the present invention
  • FIGS. 2 and 3 are flowcharts showing an example of a support method by the support device 10
  • FIG. 5 is a diagram for explaining an example of a method of calculating a change point position of measurement data
  • FIG. 6 is a diagram for explaining a support method by the support device 10.
  • the support device 10 supports acquisition of a parameter that specifies a change with time of a measurement value of a sensor, and thereby supports detection of a characteristic change in a waveform of measurement data in a process system such as a power plant or a chemical plant. To do.
  • a parameter specifies the position of the change point of the measurement data indicating the change over time of the measurement value of the sensor.
  • the support device 10 includes a parameter optimization mechanism 20, a data evaluation mechanism 30, and a data storage unit 40.
  • the parameter optimizing mechanism 20 acquires an optimum parameter that is an example of a parameter having a predetermined value that specifies a change with time of the measurement value of the sensor.
  • the data evaluation mechanism 30 uses the optimum parameters acquired by the parameter optimization mechanism 20 to identify the change point position of the measurement data indicating the change over time of the measurement value of the sensor, and the characteristic of the waveform of the measurement data is thereby determined. Change detection can be performed, and thus the operating status of the process system can be evaluated.
  • the data storage unit 40 stores various types of measurement data, and changes the position of the optimum parameter acquired by the parameter optimization mechanism 20 and the change point position of the measurement data calculated or acquired by the parameter optimization mechanism 20 and the data evaluation mechanism 30. Store data.
  • the support device 10 is connected to, for example, a plurality of sensors (not shown) provided in a process system, and is configured to be able to acquire measurement data indicating a change with time of measurement values of the sensors.
  • the support device 10 is also connected to an operation unit (not shown) for inputting information and a display unit (not shown) for outputting information. With this, a calculation is performed based on the information input by the operation unit, the calculation result is displayed on the display unit, and the operator recognizes the screen on the display unit while the operation unit obtains necessary information for the support device 10. You can enter.
  • the support device 10 is a computer device including a CPU, a memory, and the like.
  • the memory stores a support program for executing each operation of the support method by the support apparatus 10 according to the present embodiment.
  • processing which will be described later, that causes the computer to execute the program that defines the support method according to the present embodiment causes the computer to perform the same as the functions and operations of the corresponding elements of the support apparatus 10 and the support method according to the present embodiment, respectively. ..
  • the parameter optimization mechanism 20 includes a learning data acquisition unit 21, a noise removal unit 22, a parameter input unit 23, a data display unit 24, and an optimum parameter acquisition unit 25.
  • the learning data acquisition unit 21 acquires the measurement data indicating the change over time of the measured value of the sensor as the learning data in order to acquire the optimum parameter optimum parameter.
  • the sensor is, for example, a pressure sensor, a temperature sensor, or a flow rate sensor.
  • the noise removal unit 22 removes noise from the measurement data acquired by the learning data acquisition unit 21, and acquires noise-removed measurement data.
  • the parameter input unit 23 receives an input of a parameter for specifying a change with time of the measurement value of the sensor. This parameter is input by, for example, an operator inputting it through the operation unit.
  • the data display unit 24 displays the noise-removed measurement data acquired by the noise removal unit 22.
  • the data display unit 24 also includes a parameter input field for prompting the operator to input a parameter, an execution button (for example, a change point calculation execution button and a change point extraction execution button) necessary for obtaining the optimum parameter, and learning.
  • Information necessary for the parameter optimization mechanism 20 to acquire the optimum parameter is displayed on the display unit (see FIG. 6).
  • the optimum parameter acquisition unit 25 includes a change point position calculation unit 26 that calculates the change point position of the measurement data and a change point position extraction unit 27 that extracts the change point position calculated by the change point position calculation unit 26.
  • the method of calculating the change point position is not limited, but for example, a known waveform feature change detection method such as the k-nearest neighbor method (see FIG. 4) or the singular spectrum conversion (see FIG. 5) can be used.
  • the data evaluation mechanism 30 includes an evaluation data acquisition unit 31, a noise removal unit 32, an optimum parameter input unit 33, a data display unit 34, and a change point position acquisition unit 35.
  • the evaluation data acquisition unit 31 acquires, as evaluation data, measurement data indicating a change with time of the measurement value of the sensor for detecting a characteristic change of the waveform of the measurement data.
  • the evaluation data is the same kind of measurement data based on the measurement value of the same sensor as the learning data acquired by the learning data acquisition unit 21 of the parameter optimizing mechanism 20. In this way, since the characteristic change of the waveform of the measurement data is detected using the optimum parameters obtained from the measurement data of the same kind, it is possible to specify the accurate change point position in the measurement data.
  • the noise removal unit 32 removes noise from the measurement data acquired by the evaluation data acquisition unit 31 and acquires measurement data from which noise has been removed.
  • the optimum parameter input unit 33 receives an input of optimum parameters for specifying a change with time of the measurement value of the sensor.
  • the input of the optimum parameter is performed, for example, by receiving the optimum parameter acquired by the optimum parameter acquisition unit 25 from the parameter optimization mechanism 20 or the data storage unit 40.
  • the optimum parameter acquired by the parameter optimizing mechanism 20 may be input by the operator via the operation unit to input the optimum parameter.
  • the data display unit 34 displays the noise-removed measurement data acquired by the noise removal unit 32. Further, the data display unit 34, like the data display unit 24 of the parameter optimization mechanism 20, has a parameter input field for prompting the operator to input the optimum parameter, and an execution button (for example, a change point) necessary for data evaluation.
  • the data evaluation mechanism 30 displays information necessary for data evaluation such as a calculation execution button and a change point extraction execution button) on the display unit.
  • the change point position acquisition unit 35 includes a change point position calculation unit 36 that calculates the change point position of the measurement data, and a change point position extraction unit 37 that extracts the change point position calculated by the change point position calculation unit 36. ..
  • the method of calculating the change point position is not limited, but is similar to the method of calculation by the optimum parameter acquisition unit 25, and for example, known methods such as the k-nearest neighbor method (see FIG. 4) and the singular spectrum conversion (see FIG. 5) The waveform feature change detection method of can be used.
  • the data storage unit 40 includes a measurement data storage unit 41, an optimum parameter storage unit 42, and a change point position data storage unit 43.
  • the measurement data storage unit 41 stores measurement data from each sensor provided in the process system.
  • the stored measurement data includes learning data for processing by the parameter optimization mechanism 20 and evaluation data for processing by the data evaluation mechanism 30.
  • the optimum parameter storage unit 42 stores the optimum parameters acquired by the optimum parameter acquisition unit 25.
  • the change point position data storage unit 43 stores the change point position data of the measurement data extracted by each of the change point position extraction units 27 and 37.
  • the stored data stored in the data storage unit 40 is associated with, for example, the operation timing and operation status of the process system.
  • the learning data acquisition unit 21 causes the first learning data indicating the change over time of the measurement value of the first sensor and the second learning data indicating the change over time of the measurement value of the second sensor. And are acquired (S10).
  • the first learning data is the same kind of measurement data as the measurement data to be evaluated by the data evaluation mechanism 30, and such measurement data is the same as the sensor of the measurement data acquired by the evaluation data acquisition unit 31. It can be obtained from the sensor.
  • the second learning data is measurement data having a correlation with the first learning data.
  • the second learning data is benchmark data for the first learning data.
  • the second learning data is measurement data having a response relationship of input or output (in other words, cause or result) with respect to the first learning data.
  • the first learning data and the second learning data are not limited to a mode in which one of the first learning data and the second learning data is in the input/output of one system with respect to the other, and the input/output of a plurality of systems is not limited.
  • the first learning data is input to the first system
  • the output of the first system is the input of the second system
  • the output of the second system is the second output. 2 Aspects of learning data) are also included.
  • the measurement data having such an input or output response has mutually the same change point position.
  • the second learning data is the pressure of the steam that causes the temperature change at the predetermined position or It may be measurement data from a sensor that detects the flow rate.
  • the second learning data may be measurement data having a correlation coefficient of a predetermined value or more with the first learning data.
  • noise of the first learning data and the second learning data is removed by the noise removing unit 22 (S11), and the noise-removed first learning data and second learning data are displayed by the data display unit 24. It is displayed on the section (S12). Then, the operator visually recognizes each waveform of the first learning data and the second learning data displayed on the display unit, and changes the measured value of the sensor with time by the parameter input unit 23 via the operation unit.
  • a parameter for specifying is input (S13).
  • the parameter here is a temporary parameter appropriately determined by the operator.
  • the change point position calculation unit 26 calculates the change point positions of the first learning data and the second learning data (S14).
  • FIG. 4 An example of the method of calculating the change point position is the k-nearest neighbor method shown in FIG.
  • the horizontal axis represents time and the vertical axis represents the measurement value of the sensor.
  • the k-nearest neighbor method is a known method for detecting a change in waveform characteristics and will be briefly described.
  • the k-nearest neighbor method creates a vector d of length w on the future side at the boundary of the calculation time t. By sliding a vector of the same length w on the past side, n vectors qi are prepared and a past matrix (one vector for one column) is created.
  • the parameter input in step S13 is a parameter corresponding to the time width of the horizontal axis in FIG. Specifically, this parameter corresponds to the separation distance g, the time width M, and the window size w in FIG.
  • FIG. 5 Another example of the method of calculating the change point position is the singular spectrum conversion shown in FIG.
  • the horizontal axis represents time and the vertical axis represents the measurement value of the sensor.
  • Singular Spectrum Transform is to cut out time series data with arbitrary length (window size) w to create a vector on the past side from the change degree calculation time t, and slide the vector with a score ⁇ . Creates n vectors. These n vectors are used as the past (n ⁇ w) matrix. By singular value decomposition of this matrix, an arbitrary number of past representative vectors are extracted. On the other hand, on the future side, a similar matrix is created and singular value decomposition is performed to extract one future representative vector.
  • the degree of change z(t) at that time is calculated from the following equation using a matrix U composed of a plurality of past representative vectors and one future representative vector ⁇ (t).
  • the parameter input in step S13 is a parameter corresponding to the time width on the horizontal axis in FIG. Specifically, this parameter corresponds to the separation distance g, the time width M, and the window size w in FIG.
  • the operator inputs these plurality of parameters through the parameter input unit 23, and changes position of each of the first learning data and the second learning data by the waveform feature change detection method such as k-nearest neighbor method or singular spectrum conversion. To calculate. After that, the change point positions extracted by the change point position extraction unit 27 are extracted in step S15 (S15), and these change point positions match each change point position in the first learning data and the second learning data. It is displayed on the display unit together with the rate determination result (S16).
  • the waveform feature change detection method such as k-nearest neighbor method or singular spectrum conversion.
  • FIG. 6 is an example of a display mode on the display unit after step S16.
  • the display area 50 includes a first learning data display field 60, a second learning data display field 70, a parameter input field 80, a change point calculation execution button 90, and a change point extraction execution button 92. , And a matching rate determination result 94.
  • the waveform 62 of the first learning data and its change point position 64 are shown on the coordinate axis with the measurement value of the first sensor as the vertical axis and the time as the horizontal axis. ..
  • the change point position 64 is indicated by a vertical line in each cycle of a waveform in which a substantially similar pattern is cyclically repeated.
  • the waveform 72 of the second learning data and its change point position 74 are shown on the coordinate axis with the measurement value of the second sensor as the vertical axis and the time as the horizontal axis. Has been done.
  • the changing point position 74 is indicated by a vertical line in each cycle of a waveform in which a substantially similar pattern is cyclically repeated.
  • the display fields 60 and 70 are arranged so that the horizontal axes indicating time coincide with each other, so that the matching rate of the change point positions 64 and 74 of the learning data can be visually recognized.
  • the parameters 82, 84, 86 input in step S13 for calculating the change point positions 64, 74 of the learning data are displayed. Thereby, the correspondence between each parameter and the change point position of each learning data can be visually recognized.
  • the change point calculation execution button 90 and the change point extraction execution button 92 are selected by the operator via the operation unit so that the change point position of each learning data can be calculated or extracted.
  • the match rate determination result 94 includes an item (YES) 96 when the match rate determination result indicates a match and an item (NO) 98 when the match rate determination result indicates a mismatch, and is determined according to the match rate determination result.
  • the lamp of either item is turned on. Thereby, the operator can easily visually recognize whether or not the change point position of the first learning data and the change point position of the second learning data corresponding to the parameter input in step S13 match.
  • step S17 the optimum parameter acquisition unit 25 determines whether or not the change point position of the first learning data and the change point position of the second learning data match.
  • the data display unit 24 prompts the operator to re-input the parameter, and repeats the series of steps from S13 to S16 until it is determined that the determination results match.
  • the optimum parameter acquisition unit 25 acquires the parameter having the predetermined value at this time as the optimum parameter.
  • the acquired optimum parameters are stored in the optimum parameter storage unit 42 and used in the data evaluation mechanism described later.
  • the change point positions 64 and 74 can be compared with each other to determine whether or not they match within the allowable error. That is, when the matching rate of the change point positions falls within the allowable error, the parameter is set as the optimum parameter.
  • the optimum parameter acquisition unit 25 may automatically calculate the matching rate of the change point positions.
  • the evaluation data acquisition unit 31 acquires measurement data of the same type as the first learning data as evaluation data for detecting a characteristic change of the waveform of the measurement data (S10).
  • the evaluation data is the measurement value of the same sensor as the first learning data, but the measurement data at different times.
  • the noise of the evaluation data is removed by the noise removing unit 32 (S21), and the evaluation data from which the noise is removed is displayed on the display unit by the data display unit 34 (S22). Further, the optimum parameter input unit 33 acquires optimum parameters for the measurement data of the same type as the evaluation data from the optimum parameter storage unit 42, and the optimum parameters are input to the data evaluation mechanism 30 (S23). It should be noted that the operator can input the optimum parameters again through the operation unit while visually checking the waveform of the evaluation data displayed on the display unit.
  • the change point position calculation unit 36 calculates the change point position of the evaluation data based on the optimum parameters input in step S23 (S24).
  • the worker calculates the change point position of the evaluation data by the waveform feature change detection method such as the k-nearest neighbor method or the singular spectrum conversion based on the optimum parameter, and then the change point position extraction unit 37 performs the step S24.
  • the change point position calculated in step S23 is extracted (S25).
  • the change point position thus extracted is displayed on the display unit as the evaluation result of the evaluation data (S26).
  • the support device acquires the first learning data and the second learning data that has a correlation with the first learning data, and supports the parameters input by the input unit.
  • a parameter having a predetermined value is acquired based on the change point position of the first learning data and the change point position of the second learning data. According to this, it is possible to easily acquire the parameter that specifies the change with time of the measurement value of the sensor. Therefore, for example, parameters can be efficiently acquired even in measurement data for which there is no past empirical value, and thus feature change detection of the waveform of measurement data can be easily performed.
  • a change in measurement data may be one of the factors that lead to a system abnormality. Therefore, by applying the support device, the support method, and the support program according to the present embodiment, it is possible to detect a system abnormality. It can also be useful.
  • the present invention can be variously modified and applied without being limited to the above embodiment.
  • the present invention is not limited to this, and a plurality of first learning data is referred to as second learning data.
  • the optimum parameter may be obtained by comparing. That is, the measurement data of the first learning data may be multidimensional. Such measurement data may be a change with time of each measurement value of the plurality of first sensors.
  • the determination of the concordance rate of each change point position for the first learning data and the second learning data is performed by, for example, averaging each of the plurality of first learning data and extracting the summed change point position. However, this may be performed by comparing this with the conversion point position of the second learning data.
  • the support device 10 includes the parameter optimization mechanism 20 and the data evaluation mechanism 30 has been described, but the present invention is not limited to this, and the support device includes at least the parameter optimization mechanism 20. It may be one. Further, the operation of the support device 10 is not limited to the one completely automated by the arithmetic processing of the computer, and at least a part of the operation includes the manual work by the worker. Further, in the above-described embodiment, the display mode of the display unit is merely an example, and the learning data in FIG. 6 is not limited to the display of the waveform data in the form of a graph, but may be in the form of a numerical table.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)
  • Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
  • Testing And Monitoring For Control Systems (AREA)
PCT/JP2020/001593 2019-01-31 2020-01-17 支援装置、支援方法及び支援プログラム WO2020158466A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020217022490A KR20210124214A (ko) 2019-01-31 2020-01-17 지원장치, 지원방법 및 지원프로그램
JP2020569512A JP7449248B2 (ja) 2019-01-31 2020-01-17 支援装置、支援方法及び支援プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019016314 2019-01-31
JP2019-016314 2019-01-31

Publications (1)

Publication Number Publication Date
WO2020158466A1 true WO2020158466A1 (ja) 2020-08-06

Family

ID=71840565

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/001593 WO2020158466A1 (ja) 2019-01-31 2020-01-17 支援装置、支援方法及び支援プログラム

Country Status (4)

Country Link
JP (1) JP7449248B2 (ko)
KR (1) KR20210124214A (ko)
TW (1) TWI734330B (ko)
WO (1) WO2020158466A1 (ko)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013156969A (ja) * 2012-02-01 2013-08-15 Fuji Xerox Co Ltd 障害予測システム、障害予測装置及びプログラム
JP2018112504A (ja) * 2017-01-13 2018-07-19 アズビル株式会社 時系列データ処理装置および処理方法
JP2019125230A (ja) * 2018-01-18 2019-07-25 ファナック株式会社 異常検知パラメータ調整表示装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3494851B2 (ja) * 1997-06-17 2004-02-09 株式会社東芝 発電プラント異常監視装置
CN1244801C (zh) * 2003-08-01 2006-03-08 重庆大学 旋转机械故障智能诊断方法与装置
US10460843B2 (en) * 2009-04-22 2019-10-29 Rodrigo E. Teixeira Probabilistic parameter estimation using fused data apparatus and method of use thereof
US9173574B2 (en) * 2009-04-22 2015-11-03 Rodrigo E. Teixeira Mechanical health monitor apparatus and method of operation therefor
JP5793299B2 (ja) * 2010-12-28 2015-10-14 株式会社東芝 プロセス監視診断装置
US20170277559A1 (en) * 2016-03-25 2017-09-28 Daqri, Llc Classifying work processes
CA3050129A1 (en) * 2017-01-13 2018-07-19 Ground Truth Consulting, Llc System and method for predicting well production
EP3616387A1 (en) * 2017-04-24 2020-03-04 Carnegie Mellon University Virtual sensor system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013156969A (ja) * 2012-02-01 2013-08-15 Fuji Xerox Co Ltd 障害予測システム、障害予測装置及びプログラム
JP2018112504A (ja) * 2017-01-13 2018-07-19 アズビル株式会社 時系列データ処理装置および処理方法
JP2019125230A (ja) * 2018-01-18 2019-07-25 ファナック株式会社 異常検知パラメータ調整表示装置

Also Published As

Publication number Publication date
KR20210124214A (ko) 2021-10-14
JP7449248B2 (ja) 2024-03-13
TWI734330B (zh) 2021-07-21
TW202030567A (zh) 2020-08-16
JPWO2020158466A1 (ja) 2021-12-02

Similar Documents

Publication Publication Date Title
JP6594044B2 (ja) 実時系列内の異常を検出するための方法
JP6810097B2 (ja) 異常検出器
De Ketelaere et al. Overview of PCA-based statistical process-monitoring methods for time-dependent, high-dimensional data
JP4394286B2 (ja) 統計的プロセス管理のための多次元的方法及びシステム
US20160231738A1 (en) Information processing apparatus and analysis method
US20150276557A1 (en) State monitoring system, state monitoring method and medium
JP7072531B2 (ja) 異常検出装置および異常検出方法
Lennox et al. Application of multivariate statistical process control to batch operations
US10955818B2 (en) System and method for extracting principal time series data
Zhu et al. Two-dimensional contribution map for fault identification [focus on education]
JP2015011027A (ja) 時系列データにおける異常を検出する方法
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
CN114112105A (zh) 异常温度检测装置、异常温度检测方法以及记录介质
CN108369416B (zh) 异常诊断系统
JP4610946B2 (ja) におい特定方法
Zhao et al. Reconstruction based fault diagnosis using concurrent phase partition and analysis of relative changes for multiphase batch processes with limited fault batches
WO2016121689A1 (ja) 不具合診断方法及び不具合診断システム
JP2007213194A (ja) 状況解析システムおよび状況解析方法
WO2020158466A1 (ja) 支援装置、支援方法及び支援プログラム
Chen et al. A non-Gaussian pattern matching based dynamic process monitoring approach and its application to cryogenic air separation process
Zhao et al. Comprehensive subspace decomposition and isolation of principal reconstruction directions for online fault diagnosis
JP6273835B2 (ja) 状態判定装置、状態判定方法および状態判定プログラム
CN112463646A (zh) 一种传感器异常检测方法及装置
CN104848883B (zh) 一种基于稀疏表示的传感器噪声与故障的判别方法
KR20200007083A (ko) 품질 분석 장치 및 품질 분석 방법

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: 20749304

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020569512

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20749304

Country of ref document: EP

Kind code of ref document: A1