EP2769303A1 - Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de détection préventive d'une panne d'un appareil - Google Patents
Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de détection préventive d'une panne d'un appareilInfo
- Publication number
- EP2769303A1 EP2769303A1 EP12775476.0A EP12775476A EP2769303A1 EP 2769303 A1 EP2769303 A1 EP 2769303A1 EP 12775476 A EP12775476 A EP 12775476A EP 2769303 A1 EP2769303 A1 EP 2769303A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- parameter
- failure
- value
- measured value
- monitored
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/008—Reliability or availability analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/62—Testing of transformers
-
- 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
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/42—Servomotor, servo controller kind till VSS
- G05B2219/42307—Compare actual feedback with predicted, simulated value to detect run away
Definitions
- the invention relates to the field of preventive fault detection in an industrial installation.
- the invention more particularly relates to a method for preventive detection of a device failure, a computer program, an installation and a module for detecting a failure of a device.
- Preventative failure detection in an industrial installation usually consists of individual monitoring of each device in the installation.
- This individual monitoring of each of the apparatuses is achieved by means of a failure detection method of measuring one or more parameters of the apparatus to determine whether or not these parameters are out of a so-called normal operating pattern.
- the invention aims to remedy these disadvantages.
- the invention relates to a method for the preventive detection of a failure of at least one device to be monitored in a group comprising at least two devices, the device to be monitored comprising at least a first parameter correlated with at least a second parameter of at least a second apparatus of the group, said parameters representing state variables of said apparatus, the method comprising the following steps:
- step C) analyzing the result of the comparison made in step B) to detect a possibility of failure.
- Such a method allows the preventive detection of a failure of a device to be monitored based on the measurements of at least one parameter representing a state value of a second device, this parameter being correlated with a parameter of the device. device to monitor.
- the steps of predicting the value of the first parameter from the second parameter and comparing the value of the first parameter predicted from the second parameter with a measured value of the first parameter make it possible to detect a correlation error between the first parameter and the first parameter.
- second parameter that may be characteristic of a future failure of the device to be monitored. Indeed, such a lack of correlation appears when there is a divergence between the value predicted the first parameter and a real measure of this parameter.
- the device to be monitored and the second device are redundant devices.
- Redundant devices are devices of the same type operating in parallel installation.
- Such a method is particularly suitable for redundant devices having a high correlation in operation.
- the analysis of the result of the comparison performed in step B) consists in checking whether there is a correlation defect between the first parameter and the second parameter at a time t.
- the method further comprises a step of diagnosing a type of failure when a possibility of failure is detected.
- diagnosis of the type of failure consists in carrying out at least one test of the apparatus to be monitored.
- the prediction of the value of the first parameter from a measured value of the second parameter is made from a prediction model defined by prior learning of a coherence relation between previously measured values of the first parameter and the first parameter. second parameter.
- Such a prediction model defined by learning makes it possible to adapt the model irrespective of the coherence relation between the first and the second parameters, so that it is not necessary to know precisely the correlation relation before the implementation. place of the process in an industrial installation.
- the prior learning is performed by means of a learning method using a neural network system.
- Such a neural network system is particularly suitable for setting up a flexible and adaptable learning method irrespective of the correlation relation between the first and the second parameter.
- the prior learning is performed by means of a statistical learning method.
- a statistical learning method makes it possible to simply obtain the correlation relation between the first and second parameters.
- steps A), B) and C) of the method according to the invention are systematically repeated as long as no correlation fault between the first parameter and the second parameter is detected.
- steps A), B) and C) makes it possible to carry out continuous and real-time monitoring of the device to be monitored, thereby providing early detection of a possibility of failure of the device to be monitored.
- the prediction model defined for a given instant t is corrected regularly as a function of the values of the first and second parameters measured at a time preceding the instant t.
- This correction of the model makes it possible to correct the slow drifts of the correlation relation between the first and the second parameter thus limiting the risks of an inadvertent detection of a possibility of failure which would be linked to this drift and not to a real risk of device failure.
- the prediction model defined for a given instant t is systematically corrected as a function of the values of the first and second parameters measured at a time preceding the instant t.
- At least one apparatus of the group is an oil-insulated power transformer or a power rectifier.
- the invention also relates to a computer program for implementing the method according to the invention when it is executed on a computer, the computer program comprising instructions for carrying out the following steps:
- Such a program by offering the possibility of implementing a method of preventive failure detection, makes it possible, when it is implemented in an installation, to detect a preventive failure limiting the implications that such a failure could have on the production of the installation.
- the invention also relates to an installation comprising a group of at least two devices, an apparatus to be monitored, comprising at least a first parameter correlated with at least a second parameter of at least a second apparatus of the group, said parameters representing variables. state of said apparatus, said apparatus being characterized in that it further comprises: an acquisition system adapted to measure the first and the second parameter,
- a processing module communicating with the acquisition system and adapted to predict a value of the first parameter from a measured value of the second parameter and to compare the predicted value of the first parameter with a measured value of this first parameter
- a decision module adapted to analyze the result of the comparison of the predicted value of the first parameter and the measured value of said first parameter in order to detect a possibility of failure.
- the installation may further comprise a diagnostic module communicating with the processing system, and adapted to determine the type of failure.
- Such a diagnostic module makes it possible to determine the type of fault detected.
- At least one apparatus of the group is an oil-insulated power transformer or a power rectifier.
- the invention also relates to a fault prevention detection module adapted to detect a correlation fault between at least two parameters respectively representing state variables of a first device to be monitored and a second device, both belonging to a group of mounted devices on an installation according to the invention and said module comprising:
- prediction means for predicting a value of the first parameter from a measured value of the second parameter
- comparison means for comparing the predicted value of the first parameter with a measured value of this same first parameter
- analysis means for analyzing the result of the comparison made by the comparison means in order to detect a possibility of failure.
- Such a module may be a computer program as well as an automaton having said means.
- Such a module allows a preventive detection of a fault when it is implemented in an installation according to the invention.
- FIG. 1 schematically illustrates a module for the preventive detection of a fault
- FIG. 2 illustrates a flowchart schematizing the main steps of a method according to the invention
- FIG. 3 illustrates an example of an installation on which a method according to the invention has been implemented
- FIG. 4 illustrates two graphs of the measured parameters and of a parameter predicted during the implementation of a method according to the invention on the installation illustrated in FIG. 3 during which no possibility of failure is detected
- FIG. 5 is a graph showing the comparative variation of the parameter of the apparatus to be monitored and of the predicted value of this same parameter for the implementation of a method according to the invention on an installation as illustrated on FIG. Figure 3 and for which a possibility of failure is detected at time td.
- the invention relates to a method of preventive detection of a failure of a device to monitor a facility.
- the apparatus to be monitored is a first apparatus of a group of at least two apparatus of the installation.
- the apparatus to be monitored has at least one state variable whose value is a first parameter.
- At least one second device in the group has a state variable whose value is a second parameter.
- the apparatus to be monitored and the second apparatus of the group are arranged in the installation such that in operation the first parameter and the second parameter are connected by a correlation relation. So we hear by such a correlation relation that the first parameter is correlated with the second parameter.
- the apparatus to be monitored and the second apparatus of the group are two redundant devices in the installation.
- the apparatus to be monitored and the second apparatus of the group are two redundant devices in the installation.
- the first parameter and the second parameter represent the value of the same state variable respectively of the device to be monitored and the second device of the group.
- the first and second parameters may also represent two different operating or state variables, respectively of the apparatus to be monitored and the second apparatus of the group, linked by a direct or indirect correlation relation.
- a correlation relationship is for example the relationship that can exist between a temperature of the device to be monitored and the electrical power consumed by the second device. or a pressure of a cylinder of the device to be monitored and a gas flow of the second device.
- the apparatus to be monitored and the second apparatus of the group are two non-redundant apparatus of the installation.
- the first and second parameters can be linked by a relation correlation due to a cause-and-effect relationship, such as whether the apparatus to be monitored and the second apparatus are positioned in the same production line, or set under identical operating conditions, the apparatus for monitor and the second device of the group may, for example, be subject to the same electromagnetic disturbances.
- the installation further comprises, as illustrated in FIG.
- an acquisition system 10 adapted to measure the first and the second parameter
- a processing module 21 communicating with the acquisition system 10 and adapted to predict a value of the first parameter from a measured value of the second parameter and to compare the predicted value of the first parameter with a measured value of the first parameter; parameter,
- a decision module 25 adapted to analyze the result of comparing the predicted value of the first parameter and the measured value of said first parameter in order to detect a possibility of failure
- a diagnostic module 30 adapted to diagnose the type of failure when the decision module detects a possibility of failure.
- the acquisition system 10, the processing module 22, the decision module 25 and the diagnostic module 30 can be programs or computer programs run by a computer, automata or parts of automata, or a hybrid combination of computer programs and electronic devices without departing from the scope of the invention.
- the acquisition system 10 is adapted to perform the measurements of the first and second parameters.
- the acquisition system 10 comprises for this purpose measuring means, such as sensors of the state variables corresponding to said parameters, or that the acquisition system is in communication with the corresponding apparatus of the invention. to retrieve the values of the corresponding state variables.
- the acquisition system 10 is adapted to measure the first and second parameters substantially simultaneously. Nevertheless, it is also conceivable for the acquisition system 10 to measure the first and second parameters with a time offset.
- this time shift is less than a given time which is characteristic of the dynamics of variation of the state variables corresponding to the first and second parameters so as to enable the correlation relationship to be determined.
- the acquisition system 10 supplied to the processing module 21 the values of the first and the second parameter.
- a part 22, called prediction, of the processing module 21 is adapted to determine a predicted value of the first parameter from the value of the second parameter. This predicted value is preferably determined from a model corresponding to the correlation relation between the first parameter and the second parameter.
- the model is obtained by a learning method which for example uses a neural network system or is of the statistical type.
- a learning method consists in the implementation of a preliminary learning phase by the module.
- Such a learning phase comprises in particular the determination of a correlation relation between previously measured values of the first parameter and the second parameter and the determination of a prediction model that uses the correlation relation determined by learning. With such a possibility it is therefore not necessary to know beforehand the correlation relation between the first and the second parameter.
- the prediction part 22 is adapted to regularly correct the prediction model outside the learning phase, the prediction model being updated at a time t in function of measured values of the first and the second parameters at one or more instants preceding the instant t.
- the prediction part 22 forms prediction means.
- a part 23 of the processing module 21, called the comparison module, is adapted to compare the predicted value, provided by the prediction part 22, with a measured value of the first parameter.
- the predicted value is compared with a measured value of the first parameter.
- the value of the first measured parameter to which the predicted value is compared is a value of the first parameter which is measured substantially simultaneously, or with the time offset, to that of the second parameter from which the predicted value is predicted.
- the comparison consists, for example, in determining the difference between the predicted value and the measured value of the first parameter or in measuring a ratio between the predicted value and the measured value of the first parameter.
- the comparison part 23 forms comparison means.
- the analysis module 25 communicates with the processing module 21 and is adapted to analyze the result of the comparison between the predicted value and the measured value of the first parameter performed by the processing module 21. This analysis consists in checking whether there is a correlation defect between the first parameter and the second parameter at a time t. The presence of such a correlation defect is characteristic of a possibility of failure of the device to be monitored.
- the comparison consists in determining the difference between the predicted value and the measured value of the first parameter
- the analysis and the detection of a correlation defect consist in determining whether this difference is greater in absolute value than a threshold. predetermined to detect a possibility of failure.
- the analysis and the detection of a correlation defect consist in determining whether said ratio is significantly away from the unit.
- the analysis module 25 forms means of analysis.
- the processing module 21 and the analysis module 25 can be arranged to form a preventive detection module 20 of a fault.
- the diagnostic module 30 communicates with the analysis module 25 and is adapted to perform, if necessary, one or more tests of the apparatus to be monitored and, from the result of the comparison of the predicted value and the measured value. the first parameter, and from the result of, or tests, determine the type of failure that is incurred by the device to monitor.
- the diagnostic module 30 forms diagnostic means adapted to determine the type of failure.
- the installation is adapted for implementing a method for detecting a failure, such a method comprises three different phases:
- the learning phase implemented by means of the acquisition system 10 and the processing module 21 consists of the determination a model of prediction by learning.
- Such learning phase L) may comprise the steps of:
- the detection method may not include a learning phase, the prediction being made, in this case according to a prediction model previously determined during the implementation of installation.
- the method comprises a learning phase
- this learning phase L performed and the prediction model determined.
- the monitoring phase is implemented by the acquisition system 10, the processing module 21 and the analysis module 25.
- the monitoring phase consists of the following steps:
- step C) analyzing the result of the comparison made in step B) to detect a possibility of failure.
- Step A) may comprise the substeps of measuring the values of the first and second parameters at a time t and predicting a value of the first parameter on from the prediction model and the measured value of the second parameter.
- the step A) further comprises a substep, which can be performed systematically or regularly, and which consists in correcting the model of the prediction model.
- steps A), B) and C) are repeated systematically as long as no possibility of failure is detected.
- diagnostic phase D) is implemented by means of the diagnostic module 30. Diagnostic phase D) consists of:
- the diagnostic phase D) comprises a preliminary step of choosing one or more tests from a battery of tests; the choice of test (s) being made on the basis of the comparison made in step B) of the monitoring phase.
- the diagnostic phase D) also comprises an alarm phase and communication of the possible fault detected, this phase of informing the detection of a failure and the type of failure incurred by the device to monitor.
- the method may not comprise a diagnostic phase.
- the analysis step C) comprises a communication step which, if a possible fault is detected, indicates that a possible fault is detected and that it is therefore necessary to call in a technician to diagnose the fault. type of fault detected.
- the method may for example be implemented in a feed unit of an aluminum electrolysis unit, as shown in FIG. 3.
- Such an installation is suitable for provide the power necessary for carrying out the electrolysis.
- the installation comprises for this purpose four groups of devices each comprising a first power transformers H1, H2, H3, H4, an electric filtering system Fl, F2, F3, F4, a second transformer G1, G2, G3 and G4. said rectifier, and two rectifiers R1, R1 ', R2, R2', R3, R3 ', R4 and R4'.
- each of the rectifying transformers G1, G2, G3 and G4 is an oil-insulated transformer and the state value considered is the temperature of the oil used to isolate said transformer.
- Rectifier transformers G1, G2, G3 and G4 are similar transformers placed in parallel and subjected to identical conditions. As a result, they are redundant and their state values therefore have similar variations.
- the parameters, representing the state values of the transformers, such as for example the temperature of the oil, are therefore correlated with each other.
- the apparatus to be monitored being the transformer G4, the first parameter being the temperature T4 of the transformer oil G4, the second apparatus being the transformer transformers G1. , G2 and G3, and the second parameters the temperature T1, T2 and T3 respectively of the rectifying transformers G1, G2 and G3.
- Tl T2 T3 T4 T ⁇ predicts
- Table 1 Matrix of correlation of the temperatures of the transformers G1, G2, G3, G4 and the predicted temperature of G4
- the table above shows the correlation matrix which is obtained during the realization of the learning phase L) to from a learning method based on a four-input neural network.
- Such a matrix shows, by the proximity of the values with the value 1, a strong correlation between the values T1, T2, T3 and T4.
- a prediction model is established making it possible to predict the value T4 as a function of the values T1, T2 and T3.
- a pre- said value T4 is predicted at each instant t of the learning phase L) from the values T1, T2 and T3.
- Table 1 also shows the correlation value between T4 and T4 pre- said. The value of 0, 93331393 of correlation between the value of T4 and the value of T4 predicts a good match between the established prediction model and the measurements of T4.
- Figure 4 illustrates the results obtained during the implementation of the method on such an installation.
- the upper part of Figure 4 presents a graph showing the variation of the input values that are T1, T2 and T3, while the part Figure 4 illustrates the comparison step between T4 and T4 pre-
- the correlation method relates to the prediction of a single parameter of the apparatus to be monitored from a parameter of a single second apparatus of the installation
- the method can be adapted to monitoring one or more parameters of the device to be monitored with a prediction of this or these parameters from one or more parameters of one or more second devices of the installation without leaving the frame of the invention.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Power Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Debugging And Monitoring (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1159360A FR2981474B1 (fr) | 2011-10-17 | 2011-10-17 | Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de detection preventive d'une panne d'un appareil |
PCT/EP2012/070455 WO2013057085A1 (fr) | 2011-10-17 | 2012-10-16 | Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de détection préventive d'une panne d'un appareil |
Publications (1)
Publication Number | Publication Date |
---|---|
EP2769303A1 true EP2769303A1 (fr) | 2014-08-27 |
Family
ID=47049152
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP12775476.0A Ceased EP2769303A1 (fr) | 2011-10-17 | 2012-10-16 | Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de détection préventive d'une panne d'un appareil |
Country Status (6)
Country | Link |
---|---|
US (1) | US9664725B2 (fr) |
EP (1) | EP2769303A1 (fr) |
CA (1) | CA2851124C (fr) |
FR (1) | FR2981474B1 (fr) |
RU (1) | RU2628146C2 (fr) |
WO (1) | WO2013057085A1 (fr) |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016008987B4 (de) * | 2015-07-31 | 2021-09-16 | Fanuc Corporation | Maschinenlernverfahren und Maschinenlernvorrichtung zum Lernen von Fehlerbedingungen, und Fehlervorhersagevorrichtung und Fehlervorhersagesystem, das die Maschinenlernvorrichtung einschließt |
CN106423611A (zh) * | 2016-10-14 | 2017-02-22 | 深圳万发创新进出口贸易有限公司 | 一种等离子喷涂设备用无水切断保护系统 |
FR3060803B1 (fr) | 2016-12-20 | 2021-12-10 | Ondilo | Procede pour maintenir un equilibre d'un parametre physico-chimique d'un milieu, produit programme d'ordinateur et moyen electronique associes |
US11054342B2 (en) * | 2017-02-20 | 2021-07-06 | Lifewhere, Llc | System for abnormal condition detection using nearest neighbor |
FR3074590B1 (fr) | 2017-12-04 | 2023-03-17 | Soc Air France | Methode de prediction d'une anomalie de fonctionnement d'un ou plusieurs equipements d'un ensemble |
US10396897B1 (en) * | 2018-04-17 | 2019-08-27 | General Electric Company | Systems and methods for predicting defects in optical transceiver devices |
DE102018121270B4 (de) | 2018-08-31 | 2023-12-21 | Volkswagen Aktiengesellschaft | Diagnoseverfahren, Diagnosesystem und Kraftfahrzeug |
RU2714219C1 (ru) | 2018-09-14 | 2020-02-13 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для планирования передачи операций ввода/вывода |
RU2731321C2 (ru) | 2018-09-14 | 2020-09-01 | Общество С Ограниченной Ответственностью "Яндекс" | Способ определения потенциальной неисправности запоминающего устройства |
RU2718215C2 (ru) | 2018-09-14 | 2020-03-31 | Общество С Ограниченной Ответственностью "Яндекс" | Система обработки данных и способ обнаружения затора в системе обработки данных |
RU2714602C1 (ru) | 2018-10-09 | 2020-02-18 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для обработки данных |
RU2721235C2 (ru) | 2018-10-09 | 2020-05-18 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для маршрутизации и выполнения транзакций |
RU2711348C1 (ru) | 2018-10-15 | 2020-01-16 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для обработки запросов в распределенной базе данных |
RU2714373C1 (ru) | 2018-12-13 | 2020-02-14 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для планирования выполнения операций ввода/вывода |
RU2749649C2 (ru) | 2018-12-21 | 2021-06-16 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для планирования обработки операций ввода/вывода |
RU2720951C1 (ru) | 2018-12-29 | 2020-05-15 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и распределенная компьютерная система для обработки данных |
RU2746042C1 (ru) | 2019-02-06 | 2021-04-06 | Общество С Ограниченной Ответственностью "Яндекс" | Способ и система для передачи сообщения |
CN110287640B (zh) * | 2019-07-03 | 2023-10-13 | 辽宁艾特斯智能交通技术有限公司 | 照明设备的寿命预估方法、装置、存储介质及电子设备 |
RU2719507C1 (ru) * | 2019-12-16 | 2020-04-20 | федеральное государственное бюджетное образовательное учреждение высшего образования "Санкт-Петербургский горный университет" | Способ оценки технического состояния потребителя-регулятора на основе нейросетевого диагностирования |
KR20230061480A (ko) * | 2021-04-09 | 2023-05-08 | 히타치 에너지 스위처랜드 아게 | 진단 파라미터 예측 에러의 변동을 이용한 전기 장비의 상태 결정 |
CN117991704A (zh) * | 2024-02-05 | 2024-05-07 | 河北固基机械设备有限公司 | 控制柜故障预警系统 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2202600A2 (fr) * | 2008-12-23 | 2010-06-30 | EMBRAER - Empresa Brasileira de Aeronáutica S.A. | Surveillance de la performance et pronostic pour vannes de contrôle pneumatiques d'avion |
Family Cites Families (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1629898A1 (ru) * | 1989-01-27 | 1991-02-23 | Горьковский Политехнический Институт | Устройство дл диагностики и прогнозировани отказов |
US5594180A (en) * | 1994-08-12 | 1997-01-14 | Micro Motion, Inc. | Method and apparatus for fault detection and correction in Coriolis effect mass flowmeters |
DE69729981T2 (de) * | 1996-05-28 | 2004-12-16 | Honda Giken Kogyo K.K. | Gerät zur Steuerung des Luft/Kraftstoffverhältnisses, das ein neuronales Netzwerk benutzt |
US5754963A (en) * | 1996-07-30 | 1998-05-19 | Hitachi America, Ltd. | Method and apparatus for diagnosing and isolating faulty sensors in a redundant sensor system |
US6073262A (en) * | 1997-05-30 | 2000-06-06 | United Technologies Corporation | Method and apparatus for estimating an actual magnitude of a physical parameter on the basis of three or more redundant signals |
DE19801177C2 (de) * | 1998-01-15 | 2000-04-13 | Jochen Pischel | Verfahren zum Zuteilen von industriellen oder technologischen Ressourcen in technischen Systemen |
US6345369B1 (en) * | 1998-11-12 | 2002-02-05 | International Business Machines Corporation | Environmental and power error handling extension and analysis for systems with redundant components |
US6459901B1 (en) * | 1999-07-01 | 2002-10-01 | At&T Corp. | Wireless network resource allocation |
US6898554B2 (en) * | 2000-06-12 | 2005-05-24 | Scientific Monitoring, Inc. | Fault detection in a physical system |
US6487847B1 (en) * | 2000-11-03 | 2002-12-03 | General Electric Company | Gas turbine engine fuel control system |
US6615146B1 (en) * | 2000-11-22 | 2003-09-02 | International Business Machines Corporation | Failure detection of an isolation device with PFA signal generation in a redundant power supply system |
US6859739B2 (en) * | 2001-01-19 | 2005-02-22 | Smartsignal Corporation | Global state change indicator for empirical modeling in condition based monitoring |
JP2005518178A (ja) * | 2002-02-13 | 2005-06-16 | コンティネンタル・テーベス・アクチエンゲゼルシヤフト・ウント・コンパニー・オッフェネ・ハンデルスゲゼルシヤフト | 電動機のエラー検出方法 |
US6892163B1 (en) * | 2002-03-08 | 2005-05-10 | Intellectual Assets Llc | Surveillance system and method having an adaptive sequential probability fault detection test |
US7552005B2 (en) * | 2004-03-16 | 2009-06-23 | Honeywell International Inc. | Method for fault diagnosis of a turbine engine |
US7415328B2 (en) * | 2004-10-04 | 2008-08-19 | United Technologies Corporation | Hybrid model based fault detection and isolation system |
US7751921B2 (en) * | 2004-12-28 | 2010-07-06 | Tokyo Electron Limited | Semiconductor manufacturing apparatus, method of detecting abnormality, identifying cause of abnormality, or predicting abnormality in the semiconductor manufacturing apparatus, and storage medium storing computer program for performing the method |
US7280941B2 (en) * | 2004-12-29 | 2007-10-09 | General Electric Company | Method and apparatus for in-situ detection and isolation of aircraft engine faults |
US7277823B2 (en) * | 2005-09-26 | 2007-10-02 | Lockheed Martin Corporation | Method and system of monitoring and prognostics |
US7256605B2 (en) * | 2005-11-14 | 2007-08-14 | Semiconductor Components Industries, L.L.C. | Diagnostic circuit and method therefor |
JP2008004641A (ja) * | 2006-06-20 | 2008-01-10 | Toshiba Corp | 不良検出システム、不良検出方法及びプログラム |
FR2911972B1 (fr) * | 2007-01-30 | 2009-03-27 | Hispano Suiza Sa | Procede de surveillance de moteurs d'avion |
US7900118B2 (en) * | 2007-02-12 | 2011-03-01 | Phison Electronics Corp. | Flash memory system and method for controlling the same |
US8067856B2 (en) * | 2008-09-04 | 2011-11-29 | Intel Corporation | Power management system |
US8375255B2 (en) * | 2009-12-23 | 2013-02-12 | At&T Intellectual Property I, Lp | Device and method for detecting and diagnosing correlated network anomalies |
US8862433B2 (en) * | 2010-05-18 | 2014-10-14 | United Technologies Corporation | Partitioning of turbomachine faults |
US9366451B2 (en) * | 2010-12-24 | 2016-06-14 | Commonwealth Scientific And Industrial Research Organisation | System and method for the detection of faults in a multi-variable system utilizing both a model for normal operation and a model for faulty operation |
US9050894B2 (en) * | 2011-07-06 | 2015-06-09 | General Electric Company | System and method for predicting mechanical failure of a motor |
US9201113B2 (en) * | 2012-12-17 | 2015-12-01 | General Electric Company | Systems and methods for performing redundancy tests on turbine controls |
-
2011
- 2011-10-17 FR FR1159360A patent/FR2981474B1/fr not_active Expired - Fee Related
-
2012
- 2012-10-16 EP EP12775476.0A patent/EP2769303A1/fr not_active Ceased
- 2012-10-16 WO PCT/EP2012/070455 patent/WO2013057085A1/fr active Application Filing
- 2012-10-16 RU RU2014119873A patent/RU2628146C2/ru not_active IP Right Cessation
- 2012-10-16 CA CA2851124A patent/CA2851124C/fr active Active
- 2012-10-16 US US14/351,334 patent/US9664725B2/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2202600A2 (fr) * | 2008-12-23 | 2010-06-30 | EMBRAER - Empresa Brasileira de Aeronáutica S.A. | Surveillance de la performance et pronostic pour vannes de contrôle pneumatiques d'avion |
Non-Patent Citations (6)
Title |
---|
"Fault Detection, Supervision and Safety of Technical Processes 2006", 1 January 2007, OXFORD : ELSEVIER, 2007, GB, ISBN: 978-0-08-044485-7, article PAUL SUNDVALL ET AL: "Fault Detection Using Redundant Navigation Modules", pages: 522 - 527, XP055729524, DOI: 10.1016/B978-008044485-7/50088-9 * |
ASAD M MADNI ET AL: "Fault-Tolerant Data Acquisition in Sensor Networks", SYSTEM OF SYSTEMS ENGINEERING, 2007. SOSE '07. IEEE INTERNATIONAL CONFERENCE ON, IEEE, PI, 1 April 2007 (2007-04-01), pages 1 - 6, XP031135452, ISBN: 978-1-4244-1159-7 * |
PADILLA M ET AL: "Poisoning fault diagnosis in chemical gas sensor arrays using multivariate statistical signal processing and structured residuals generation", INTELLIGENT SIGNAL PROCESSING, 2007. WISP 2007. IEEE INTERNATIONAL SYMPOSIUM ON, IEEE, PISCATAWAY, NJ, USA, 3 October 2007 (2007-10-03), pages 1 - 6, XP031228507, ISBN: 978-1-4244-0829-0 * |
R. DORR ET AL: "Detection, isolation, and identification of sensor faults in nuclear power plants", IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY., vol. 5, no. 1, 1 January 1997 (1997-01-01), US, pages 42 - 60, XP055729518, ISSN: 1063-6536, DOI: 10.1109/87.553664 * |
See also references of WO2013057085A1 * |
ZEHRA CATALTEPE ET AL: "A ROBUST METHOD TO IDENTIFY FAULTS IN CORRELATED SENSORS INMACHINE CONDITION MONITORING", 4 September 2005 (2005-09-04), pages 1 - 4, XP002628754, Retrieved from the Internet <URL:http://www.eurasip.org/Proceedings/Eusipco/Eusipco2005/defevent/papers/cr2039.pdf> [retrieved on 20110317] * |
Also Published As
Publication number | Publication date |
---|---|
WO2013057085A1 (fr) | 2013-04-25 |
CA2851124C (fr) | 2020-11-03 |
FR2981474A1 (fr) | 2013-04-19 |
FR2981474B1 (fr) | 2013-12-27 |
RU2014119873A (ru) | 2015-11-27 |
RU2628146C2 (ru) | 2017-08-15 |
CA2851124A1 (fr) | 2013-04-25 |
US20140285212A1 (en) | 2014-09-25 |
US9664725B2 (en) | 2017-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2851124C (fr) | Procede de detection preventive d'une panne d'un appareil, programme d'ordinateur, installation et module de detection preventive d'une panne d'un appareil | |
EP2169799B1 (fr) | Détection directionnelle d'un défaut à la terre | |
JP6580601B2 (ja) | 光学センサを使用したパルスプラズマのモニタリング | |
FR3067154A1 (fr) | Procede d'analyse de tendance et d'ajustement automatique de parametres d'alarme | |
CA2689615C (fr) | Systeme et procede pour porter une detection de defaut en utilisant une annulation de bruit de courant de stator | |
EP2383856B1 (fr) | Identification et détection directionnelle d'un défaut dans un reseau triphase | |
FR2983529A1 (fr) | Methode de surveillance d'un dispositif de commande d'un doseur de carburant d'un turboreacteur | |
EP3619408A1 (fr) | Système et procédé de surveillance d'une turbomachine à détection d'anomalie corrigée par un facteur d'usure | |
FR2997495A1 (fr) | Procede de surveillance de capteurs vibratoires | |
JP4657880B2 (ja) | 端子圧着不良検出装置の圧着不良判定データ作成方法および圧着不良判定データ検査方法 | |
WO2020193780A1 (fr) | Procede et dispositif d'estimation du vieillissement d'un composant electronique | |
KR20170045990A (ko) | 기계 상태 모니터링 방법 | |
KR101248232B1 (ko) | 병렬 부대설비의 이상 진단 방법 및 시스템 | |
EP3375982A1 (fr) | Procédés de détection d'une défaillance dans un brûleur d'une chambre de combustion et systèmes de turbine | |
FR2605170A1 (fr) | Procede et installation de surveillance de l'evolution de l'usure de machines | |
CN109212041A (zh) | 变压器油在线监测装置的远程实时标定方法 | |
FR3044490A1 (fr) | Procede et dispositif d'evaluation de l'energie produite par un arc electrique dans une installation photovoltaique | |
EP1193020A1 (fr) | Procédé de diagnostic dynamique et d'aide à la décision en temps réel pour une soudeuse électrique en bout par étincelage direct et ses soudures | |
WO2019101891A1 (fr) | Procédé et dispositif de diagnostic de défaut d'un alternateur | |
FR3065526B1 (fr) | Systeme de detection d'un etat ou d'un dysfonctionnement par analyse vibratoire | |
EP3384595B1 (fr) | Procédé et dispositif d'évaluation de l'énergie produite par un arc electrique dans une installation photovoltaïque | |
JP2001090554A (ja) | ガスタービンの異常診断方法 | |
KR101525819B1 (ko) | 플라즈마 cvd 장비의 히터의 결함 진단 방법 | |
FR2969845A1 (fr) | Dispositif et procede de protection terre restreinte | |
EP4063877A1 (fr) | Procédé de contrôle d'un appareil électrotechnique |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20140425 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAX | Request for extension of the european patent (deleted) | ||
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: GENERAL ELECTRIC TECHNOLOGY GMBH |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20171213 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20221218 |