[go: up one dir, main page]

WO2015193980A1 - Système d'aide au fonctionnement d'une installation - Google Patents

Système d'aide au fonctionnement d'une installation Download PDF

Info

Publication number
WO2015193980A1
WO2015193980A1 PCT/JP2014/066085 JP2014066085W WO2015193980A1 WO 2015193980 A1 WO2015193980 A1 WO 2015193980A1 JP 2014066085 W JP2014066085 W JP 2014066085W WO 2015193980 A1 WO2015193980 A1 WO 2015193980A1
Authority
WO
WIPO (PCT)
Prior art keywords
sensor
plant
sensor signal
abnormal
determined
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2014/066085
Other languages
English (en)
Japanese (ja)
Inventor
健一 上遠野
佳彦 石井
石川　忠明
昌基 金田
亮太 鴨志田
有田　節男
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.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to PCT/JP2014/066085 priority Critical patent/WO2015193980A1/fr
Publication of WO2015193980A1 publication Critical patent/WO2015193980A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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 plant operation support system.
  • Patent Document 1 As a support for an operator when an abnormality or an accident occurs, a plant operation support apparatus that can automatically diagnose the soundness of various instruments including sensors using a pre-installed plant simulator or equipment model is known (for example, Patent Document 1).
  • a device model that quantitatively simulates the static characteristics of plant constituent devices is stored in a property storage unit, an observation signal and a device model are input in a state estimation unit, and an observation signal is transmitted using the device model. To estimate the process state. Finally, the soundness of the sensor is evaluated using the result of the state estimation unit in fuzzy inference.
  • an object of the present invention is to provide a plant operation support system capable of accurately grasping a plant state by accurately excluding a sensor indicating an abnormal instruction value.
  • the present invention relates to a sensor soundness determination device for determining sensor soundness based on a process signal from an actual plant, a plant simulator having parameter correction means for correcting a model parameter based on the sensor signal and a simulation result, and a plant A plant state estimation device for estimating a state, wherein the sensor soundness determination device determines whether it is possible to determine a sensor that outputs an abnormal value by majority determination of output signals between redundant sensors.
  • the redundancy sensor abnormality determination enable / disable determination means, the redundancy sensor abnormality determination means for determining whether the sensor signal is normal or abnormal when it is determined that the sensor can be determined, and the sensor signal determined to be normal 1st abnormality sensor signal removal means transmitted to a plant simulator is provided,
  • the said plant simulation It is characterized in that it comprises a parameter correcting means for correcting the model parameters based on the sensor signals determined to be normal by the first abnormality sensor signal removing means.
  • a plant operation support system capable of accurately grasping a plant state by accurately excluding a sensor indicating an abnormal instruction value.
  • the present invention relates to a plant operation support system that supports plant operation. Embodiments will be described below with reference to the drawings.
  • FIG. 1 is an example of a configuration diagram of the plant operation support system 1.
  • the sensor signal 2 is a process signal such as the temperature, pressure, water level, and flow rate of the actual plant 3 and is taken into the process data server 4 and subsequently sent to the sensor soundness determination device 5.
  • the sensor soundness determination device 5 includes a redundant sensor abnormality determination availability determination unit 51, a redundant sensor abnormality determination unit 52, an abnormal sensor signal removal unit 53, a plant simulator cooperation abnormality determination unit 54, and an abnormal sensor signal removal unit 55.
  • Redundant sensor abnormality determination possibility determination means 51 determines whether or not a sensor that outputs an abnormal value can be determined by majority determination of output signals between redundant sensors. If possible, the redundant sensor abnormality determining means 52 determines whether the sensor signal 2 is normal or abnormal, and the abnormal sensor signal removing means 53 removes the sensor signal that is outputting an abnormal signal. The sensor signal 2 a determined to be normal by the redundant sensor abnormality determination means 52 is sent to the plant simulator 6.
  • the plant simulator 6 includes parameter correction means 61 and future prediction means 62.
  • the parameter correction means 61 corrects the model parameter in the plant simulator 6 based on the sensor signal 2a and the simulation result.
  • the plant simulator cooperation abnormality determination unit 54 detects the sensor signal 2.
  • the abnormal sensor signal removing means 55 removes the sensor signal that is outputting an abnormal signal.
  • the sensor signal 2b determined to be normal by the plant simulator cooperation abnormality determination unit 54 is sent to the plant state estimation device 7 together with the sensor signal 2a determined to be normal by the redundant sensor abnormality determination unit 52.
  • the plant state estimation device 7 estimates and identifies the state of the plant using a device state signal and an alarm signal (not shown) and a simulation result by the future prediction means 62 in the plant simulator 6 together.
  • FIG. 2 shows an example of the parameter correcting means 61 of the plant simulator 6 using the sensor signal 2a determined to be normal by the redundant sensor abnormality determining means 52.
  • the time-series change of the sensor signal 2a and the simulation result of the plant simulator 6 is shown, and here, as an example, the results of the inlet flow rate and outlet pressure of a certain pipe are shown.
  • the solid line is the sensor signal 2a, and the broken line is the simulation result of the plant simulator 6.
  • the flow sensor signal and the flow simulation result match within the allowable error, but the pressure sensor signal and the pressure simulation result are larger than the allowable error.
  • the parameter correction means 61 adjusts the model parameter (for example, the coefficient of wall friction of the inner wall of the pipe) so as to match the sensor signal of the outlet pressure within the allowable error, so that the pressure sensor signal and simulation are performed at time t2. The results are consistent within tolerance.
  • the accuracy of the simulation by the plant simulator 6 is poor, there is a possibility that the accuracy of the sensor soundness determination by the plant simulator cooperation abnormality determination means 54 is lowered. In this case, a sensor signal that does not correctly indicate the plant state is determined to be normal by the simulator cooperation abnormality determination unit 54. And when such a sensor signal is applied to the parameter correction means 61 of the plant simulator 6, there is a possibility that the model parameter is adjusted in such a direction that the accuracy of the simulation by the plant simulator 6 becomes worse. Therefore, in the present embodiment, the sensor signal 2a determined to be normal by the redundant sensor abnormality determining unit 52 is used as the sensor signal 2 used for the parameter correcting unit 61 of the plant simulator 6, so that the parameter correcting unit of the plant simulator 6 is used.
  • the redundant sensor abnormality determination means 52 and the abnormality sensor signal removal means 53 can provide a plant operation support system that can accurately grasp the plant state by accurately excluding the sensor indicating the abnormal instruction value.
  • the sensor signal 2 b determined to be normal by the plant simulator cooperation abnormality determination unit 54 is determined to be normal by the redundant sensor abnormality determination unit 52.
  • the sensor signal 2a can be applied to the parameter correction means 61 of the plant simulator 6.
  • the sensor signal 2a is used in the same manner as in FIG. 1, but the parameter correction means of the plant simulator 6 is obtained by using the sensor signal 2b only when the number of available sensor signals 2a is small. 61 can reduce the possibility of deteriorating the accuracy of the simulation.
  • the plant simulator is improved in accuracy online so that the actual plant behavior can be improved. Highly accurate prediction is possible.
  • FIG. 4 shows an example of pressure sensor abnormality.
  • a solid line is the sensor signal 2 and a broken line is a simulation result by the plant simulator 6.
  • the pressure simulation result is shown by a broken line, and there is no pressure change.
  • the pressure sensor signal has decreased since time t3. The deviation between the two increases with time, and it is determined that the sensor is abnormal when it deviates from the allowable error range.
  • both the flow rate sensor signal and the flow rate simulation result change in the same manner. That is, in this example, the result of the pressure sensor abnormality is output, and the pressure sensor signal is removed by the abnormality sensor signal removal means 55.
  • FIG. 5 shows an example of a display screen of the plant operation support system of the present embodiment.
  • the display screen of the plant operation support system includes a plant operation support system operation log display screen, a monitoring item selection button, and a time series data comparison graph of monitoring items.
  • the difference between the flow sensor signal and the simulation result increases, and the model parameter is corrected by the parameter correction means 61 of the plant simulation 6.
  • the operation is displayed on the plant operation support system operation log display screen and the time-series data comparison graph.
  • the redundant sensor abnormality determination availability determination unit 51 of the sensor soundness determination device 5 causes the sensor abnormality due to redundancy to occur. It is determined that the determination is impossible, and the soundness determination of the sensor is performed by the plant simulator cooperation abnormality determination unit 54 and is determined to be normal.
  • the plant simulator cooperation abnormality determination unit 54 of the sensor soundness determination apparatus 5 determines that the value is an abnormal value. Further, the future prediction means 62 of the plant simulator 6 also displays future prediction data after the current time.

Landscapes

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

Abstract

La présente invention est caractérisée en ce qu'elle comprend un dispositif de détermination d'intégrité de capteur, un simulateur d'installation, et un dispositif d'estimation d'état d'une installation. Le dispositif de détermination d'intégrité de capteur est caractérisé en ce qu'il comprend : des moyens de vérification de détermination d'anomalie de capteur redondant qui, s'il est déterminé qu'un capteur d'un ensemble redondant de capteurs délivre une valeur de sortie anormale, déterminent si le capteur peut être utilisé pour effectuer une détermination correcte, par l'application d'une règle majoritaire aux signaux de sortie provenant de l'ensemble redondant de capteurs ; des moyens de détermination d'anomalie de capteur redondant qui, s'il est déterminé que le capteur peut être utilisé pour effectuer une détermination correcte, déterminent si le signal du capteur est normal ou anormal ; et de premiers moyens de suppression de signal de capteur anormal qui transmettent le signal de capteur au simulateur d'installation s'il est déterminé que le signal de capteur est normal. Ledit simulateur d'installation est en outre caractérisé en ce qu'il comprend des moyens de modification de paramètre qui modifient les paramètres de modèle sur la base du signal de capteur déterminé comme étant normal par les premiers moyens de suppression de signal de capteur anormal. Ainsi, le système d'aide au fonctionnement d'une installation selon l'invention peut évaluer avec précision l'état d'une installation par l'identification précise et l'exclusion des capteurs indiquant une valeur de capteur anormale.
PCT/JP2014/066085 2014-06-18 2014-06-18 Système d'aide au fonctionnement d'une installation Ceased WO2015193980A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/066085 WO2015193980A1 (fr) 2014-06-18 2014-06-18 Système d'aide au fonctionnement d'une installation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/066085 WO2015193980A1 (fr) 2014-06-18 2014-06-18 Système d'aide au fonctionnement d'une installation

Publications (1)

Publication Number Publication Date
WO2015193980A1 true WO2015193980A1 (fr) 2015-12-23

Family

ID=54935012

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2014/066085 Ceased WO2015193980A1 (fr) 2014-06-18 2014-06-18 Système d'aide au fonctionnement d'une installation

Country Status (1)

Country Link
WO (1) WO2015193980A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023041618A (ja) * 2021-09-13 2023-03-24 インターナショナル・ビジネス・マシーンズ・コーポレーション コンピュータ実装方法、情報ハンドリングシステムおよびコンピュータプログラム製品（コグニティブマルチエージェントシステムにおけるデータ完全性の保持）

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62126407A (ja) * 1985-11-27 1987-06-08 Nissan Motor Co Ltd 異常検出装置
JP2013539886A (ja) * 2010-10-11 2013-10-28 ゼネラル・エレクトリック・カンパニイ センサ信号インパルス障害を検出及び除去するためのシステム、方法、及び装置

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62126407A (ja) * 1985-11-27 1987-06-08 Nissan Motor Co Ltd 異常検出装置
JP2013539886A (ja) * 2010-10-11 2013-10-28 ゼネラル・エレクトリック・カンパニイ センサ信号インパルス障害を検出及び除去するためのシステム、方法、及び装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023041618A (ja) * 2021-09-13 2023-03-24 インターナショナル・ビジネス・マシーンズ・コーポレーション コンピュータ実装方法、情報ハンドリングシステムおよびコンピュータプログラム製品（コグニティブマルチエージェントシステムにおけるデータ完全性の保持）

Similar Documents

Publication Publication Date Title
US9250616B2 (en) Process control system
EP2853972A3 (fr) Dispositif et procedé pour la detection et/ou le diagnostic de défauts dans un processus, équipement et capteurs
KR20190025474A (ko) 플랜트 데이터 예측 장치 및 방법
JP6509001B2 (ja) 故障診断システム
JP2009282804A (ja) 比較判定装置及び比較判定方法
WO2016133121A1 (fr) Procédé de diagnostic d'anomalie et système de diagnostic d'anomalie
WO2014091952A1 (fr) Dispositif de surveillance de capteur, procédé de surveillance de capteur et programme de surveillance de capteur
KR101734289B1 (ko) 원자력 발전소 계측기의 유효성 평가 방법 및 장치
JP2019505888A (ja) 少なくとも２つの冗長センサを監視する方法
TW202013110A (zh) 支援裝置、學習裝置以及廠房運轉條件設定支援系統
JP2022502737A (ja) ベイジアンネットワークによるボイラーの運転データの監視方法及び装置
JP6415335B2 (ja) 不具合診断方法及び不具合診断システム
JP2011107760A (ja) プラント異常検出装置
WO2015193980A1 (fr) Système d'aide au fonctionnement d'une installation
US20160195872A1 (en) System for Assisting Operation at the Time of Plant Accident and Method for Assisting Operation at the Time of Plant Accident
JP2010276339A (ja) センサ診断方法およびセンサ診断装置
US10222791B2 (en) Operation assistance apparatus at time of accident in plant
WO2020090715A1 (fr) Dispositif, procédé et support de données de programme de gestion de processus
Khentout et al. Fault monitoring and accommodation of the heat exchanger parameters of Triga-Mark II nuclear research reactor using model-based analytical redundancy
KR20190060614A (ko) 수중함의 이상상태 예측 시스템 및 예측 방법
CN112912903B (zh) 推论装置、信息处理装置、推论方法、程序以及记录介质
JP2016148963A (ja) 故障予兆診断システム及び故障予兆診断方法
WO2015040683A1 (fr) Procédé de détermination de l'intégrité d'un capteur et dispositif de détermination de l'intégrité d'un capteur
Sanchez et al. Fault diagnosis of advanced wind turbine benchmark using interval-based ARRs and observers
WO2016103229A1 (fr) Procédé de validation d'une logique de sécurité dans un processus industriel

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: 14895034

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: 14895034

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP