CN111487950B - 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis - Google Patents
'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis Download PDFInfo
- Publication number
- CN111487950B CN111487950B CN202010330674.3A CN202010330674A CN111487950B CN 111487950 B CN111487950 B CN 111487950B CN 202010330674 A CN202010330674 A CN 202010330674A CN 111487950 B CN111487950 B CN 111487950B
- Authority
- CN
- China
- Prior art keywords
- online
- line
- prediction
- fault
- early warning
- 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.)
- Active
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
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
-
- 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
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
A 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis comprises an online early warning and offline diagnosis closed-loop system; the online early warning closed-loop system comprises online prediction, verification, feedback and optimization, the online prediction realizes fault type prediction, the online verification judges whether the online prediction is correct or not, the online feedback feeds fault information back to the fault early warning system, and the online optimization optimizes an online error self-checking algorithm to perfect a fault case base; the off-line diagnosis closed-loop system comprises off-line prediction, verification, feedback and optimization, wherein the off-line prediction establishes a precision degradation model to realize the off-line prediction of the health condition of the robot, the off-line verification of the accuracy of the off-line prediction, the off-line feedback feeds off-line prediction parameters back to the precision degradation model, and the off-line optimization analyzes the parameter influence and the evolution rule of the precision degradation model, improves the digital-analog linkage algorithm and optimizes the parameters; the invention realizes accurate fault early warning under complex working conditions and more accurate predictive maintenance.
Description
Technical Field
The invention relates to the technical field of industrial robots, in particular to a 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis.
Background
With the rapid development of industrial upgrading and intelligent manufacturing in China, industrial robots have become key supporting equipment for promoting and manufacturing strong country construction. Although China has become a big country for industrial robot application for 5 years, the whole level has a significant gap compared with the international level, and the reason for this is: domestic robots lack effective fault diagnosis and predictive maintenance support in their safe and reliable operation. Different from the traditional diagnosis object, the industrial robot has the characteristics of real-time driving and controlling, continuous operation, electromechanical control and inductive coupling and the like, and has the defects of obvious individual difference and complex and changeable working conditions, so that the reliable operation of the industrial robot is difficult to ensure in the conventional regular maintenance mode. In addition, the industrial robot has failure modes of a structure body, an execution part and a control circuit, and has the problems of accuracy loss, performance decline and the like, so that the development of health assessment and performance prediction on the industrial robot is difficult.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis, and a method such as big data and a neural network are cooperated to realize accurate fault early warning of an industrial robot under a complex working condition and realize more accurate predictive maintenance.
In order to achieve the purpose, the invention adopts the following technical scheme:
a 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis comprises an online early warning closed-loop system and an offline diagnosis closed-loop system; the online early warning closed-loop system comprises four links of online prediction, online verification, online feedback and online optimization, wherein the online prediction link realizes fault type prediction, the online verification link judges whether the online prediction is correct or not, the online feedback link feeds fault information back to the fault early warning system, and the online optimization link optimizes an online error self-checking algorithm to perfect a fault case base; the offline diagnosis closed-loop system comprises four links of offline prediction, offline verification, offline feedback and offline optimization, wherein the offline prediction link establishes a precision degradation model through a digital-analog linkage algorithm to realize offline prediction of the health condition of the robot at a certain time node, the offline verification link verifies the accuracy of the offline prediction, the offline feedback link feeds off offline prediction parameters to the precision degradation model, and the offline optimization link analyzes parameter influence and the evolution rule of the precision degradation model, so that the digital-analog linkage algorithm is improved and optimized.
The fault early warning system of the online early warning closed-loop system is carried on an edge end server and comprises an online error self-checking algorithm, a fault case library and a warning module; the online error self-checking algorithm extracts fault information, the fault case library provides characteristic information of different faults, and the alarm module alarms the faults.
The online prediction link in the online early warning closed-loop system comprises a fault early warning system which compares fault information extracted by an error self-checking algorithm with a fault case library, identifies the fault type and simultaneously utilizes a warning module to give a warning.
The online verification link in the online early warning closed-loop system comprises the steps of comparing the online predicted fault type with the actual fault type, judging the online predicted result, if the online predicted result is accurate, continuing to monitor the running state of the robot, and collecting fault information; and if the online prediction result is wrong, continuing to perform online feedback and online optimization links.
The online feedback link in the online early warning closed-loop system is to feed back fault information extracted by the online error self-checking algorithm to the fault early warning system.
The online optimization link in the online early warning closed-loop system is to optimize an online error self-checking algorithm according to fault information and improve the algorithm; if a novel fault occurs, the fault information is recorded into a fault case library, and the alarm accuracy of the system is improved.
The off-line prediction link in the off-line diagnosis closed-loop system comprises the steps of establishing an industrial robot precision degradation model by using a digital-analog linkage algorithm according to the historical working condition of the industrial robot, wherein the historical working condition comprises working time and working load parameters, and calculating the operation characteristic parameters of the industrial robot at a certain time node through the precision degradation model, so that the health state of the industrial robot is predicted off-line.
The off-line verification link in the off-line diagnosis closed-loop system comprises the steps of calculating an operation characteristic parameter of the industrial robot at a certain time node by using the precision degradation model, comparing the operation characteristic parameter with an actual characteristic parameter of the industrial robot when the industrial robot operates to the time node, and judging that the result comprises the accurate off-line prediction result and the deviation of the off-line prediction result; if the off-line prediction result is accurate, the health state of the industrial robot is continuously predicted by using the precision degradation model; and if the off-line prediction result has deviation, implementing off-line feedback and off-line optimization links.
The off-line feedback link in the off-line diagnosis closed-loop system is to feed back the operation characteristic parameters predicted by the digital-analog linkage algorithm to the precision degradation model.
The off-line optimization link in the off-line diagnosis closed-loop system comprises the steps of analyzing parameter influence and model evolution rules, improving a digital-analog linkage algorithm and optimizing parameters, and improving the accuracy of the precision degradation model on the health state prediction of the industrial robot.
Compared with the prior art, the invention has the following beneficial technical effects:
the online early warning closed-loop system compares the fault information extracted by an online error self-checking algorithm in the fault early warning system with a fault case library, identifies the fault type and gives an alarm, compares the fault type predicted online with the actual fault type, judges whether the alarm result is correct or not, feeds back the fault information extracted by the algorithm online, optimizes the algorithm, inputs the fault information into the fault case library if a novel fault occurs, and improves the alarm accuracy of the system; the offline diagnosis closed-loop system utilizes a digital-analog linkage algorithm to establish a precision degradation model according to historical working conditions, utilizes the precision degradation model to offline predict the operation characteristic parameters of the industrial robot at a certain time node, compares the offline prediction parameters with actual operation parameters, feeds the offline prediction parameters back to the precision degradation model if the offline prediction parameters are deviated from the actual operation parameters, analyzes the parameter influence and the model evolution rule, performs parameter optimization on the precision degradation model, and improves the health state prediction accuracy. The method realizes closed-loop feedback of online early warning and offline diagnosis, and has important significance for realizing accurate fault early warning of the industrial robot under complex working conditions and realizing more accurate predictive maintenance.
Drawings
FIG. 1 is a system configuration of the present invention.
Fig. 2 is a framework diagram of the operation of the on-line early warning closed-loop system of the present invention.
FIG. 3 is a block diagram of the operation of the off-line diagnostic closed loop system of the present invention.
Detailed Description
The present invention will be described in detail below with reference to examples and the accompanying drawings.
Referring to fig. 1, a 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis comprises an online early warning closed-loop system and an offline diagnosis closed-loop system; the online early warning closed-loop system comprises four links of online prediction, online verification, online feedback and online optimization, wherein the online prediction link realizes fault type prediction, the online verification link judges whether the online prediction is correct or not, the online feedback link feeds fault information back to the fault early warning system, and the online optimization link optimizes an online error self-checking algorithm to perfect a fault case base; the offline diagnosis closed-loop system comprises four links of offline prediction, offline verification, offline feedback and offline optimization, wherein the offline prediction link establishes a precision degradation model through a digital-analog linkage algorithm to realize offline prediction of the health condition of the robot at a certain time node, the offline verification link verifies the accuracy of the offline prediction, the offline feedback link feeds off offline prediction parameters to the precision degradation model, and the offline optimization link analyzes parameter influence and the evolution rule of the precision degradation model, so that the digital-analog linkage algorithm is improved and optimized.
Referring to fig. 2, the fault early warning system of the online early warning closed-loop system is mounted on an edge server, and comprises an online error self-checking algorithm, a fault case library and an alarm module; the online error self-checking algorithm extracts fault information, the fault case library provides characteristic information of different faults, and the alarm module alarms the faults.
The online prediction link in the online early warning closed-loop system comprises a fault early warning system which compares fault information extracted by an error self-checking algorithm with a fault case library, identifies the fault type and simultaneously utilizes a warning module to give a warning.
The online verification link in the online early warning closed-loop system comprises the steps of comparing the online predicted fault type with the actual fault type, judging the online predicted result, if the online predicted result is accurate, continuing to monitor the running state of the robot, and collecting fault information; and if the online prediction result is wrong, continuing to perform online feedback and online optimization links.
The online feedback link in the online early warning closed-loop system is to feed back fault information extracted by the online error self-checking algorithm to the fault early warning system.
The online optimization link in the online early warning closed-loop system is to optimize an online error self-checking algorithm according to fault information and improve the algorithm; if a novel fault occurs, the fault information is recorded into a fault case library, and the alarm accuracy of the system is improved.
Referring to fig. 3, the off-line prediction link in the off-line diagnosis closed-loop system includes that a precision degradation model of the industrial robot is established by using a digital-analog linkage algorithm according to the historical working condition of the industrial robot, the historical working condition includes parameters such as working time and working load, and the running characteristic parameters of the industrial robot at a certain time node are calculated through the precision degradation model, so that the health state of the industrial robot is predicted off-line.
The off-line verification link in the off-line diagnosis closed-loop system comprises the steps of calculating an operation characteristic parameter of the industrial robot at a certain time node by using the precision degradation model, comparing the operation characteristic parameter with an actual characteristic parameter of the industrial robot when the industrial robot operates to the time node, and judging that the result comprises the accurate off-line prediction result and the deviation of the off-line prediction result; if the off-line prediction result is accurate, the health state of the industrial robot is continuously predicted by using the precision degradation model; and if the off-line prediction result has deviation, implementing off-line feedback and off-line optimization links.
The off-line feedback link in the off-line diagnosis closed-loop system is to feed back the operation characteristic parameters predicted by the digital-analog linkage algorithm to the precision degradation model.
The off-line optimization link in the off-line diagnosis closed-loop system comprises the steps of analyzing parameter influence and model evolution rules, improving a digital-analog linkage algorithm and optimizing parameters, and improving the accuracy of the precision degradation model on the health state prediction of the industrial robot.
Claims (1)
1. A 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis is characterized in that: the system comprises an online early warning closed-loop system and an offline diagnosis closed-loop system; the online early warning closed-loop system comprises four links of online prediction, online verification, online feedback and online optimization, wherein the online prediction link realizes fault type prediction, the online verification link judges whether the online prediction is correct or not, the online feedback link feeds fault information back to the fault early warning system, and the online optimization link optimizes an online error self-checking algorithm to perfect a fault case base; the off-line diagnosis closed-loop system comprises four links of off-line prediction, off-line verification, off-line feedback and off-line optimization, wherein the off-line prediction link establishes a precision degradation model through a digital-analog linkage algorithm to realize off-line prediction of the health condition of the robot at a certain time node, the off-line verification link verifies the accuracy of the off-line prediction, the off-line feedback link feeds off-line prediction parameters back to the precision degradation model, and the off-line optimization link analyzes the parameter influence and the evolution rule of the precision degradation model to improve and optimize the digital-analog linkage algorithm;
the fault early warning system of the online early warning closed-loop system is carried on an edge end server and comprises an online error self-checking algorithm, a fault case library and a warning module; extracting fault information by an online error self-checking algorithm, providing characteristic information of different faults by a fault case library, and alarming by an alarm module;
the online optimization link in the online early warning closed-loop system is to optimize an online error self-checking algorithm according to fault information and improve the algorithm; if a novel fault occurs, the fault information is recorded into a fault case library, so that the alarm accuracy of the system is improved;
the online prediction link in the online early warning closed-loop system comprises a fault early warning system, a fault case library, a fault type identification module and a warning module, wherein the fault early warning system compares fault information extracted by an error self-checking algorithm with the fault case library, and simultaneously alarms;
the online verification link in the online early warning closed-loop system comprises the steps of comparing the online predicted fault type with the actual fault type, judging the online predicted result, if the online predicted result is accurate, continuing to monitor the running state of the robot, and collecting fault information; if the online prediction result is wrong, continuing to perform online feedback and online optimization links;
the online feedback link in the online early warning closed-loop system is to feed back fault information extracted by the online error self-checking algorithm to the fault early warning system;
the off-line prediction link in the off-line diagnosis closed-loop system comprises the steps of establishing an industrial robot precision degradation model by using a digital-analog linkage algorithm according to the historical working condition of the industrial robot, wherein the historical working condition comprises working time and working load parameters, and calculating the operation characteristic parameters of the industrial robot at a certain time node through the precision degradation model so as to perform off-line prediction on the health state of the industrial robot;
the off-line verification link in the off-line diagnosis closed-loop system comprises the steps of calculating an operation characteristic parameter of the industrial robot at a certain time node by using the precision degradation model, comparing the operation characteristic parameter with an actual characteristic parameter of the industrial robot when the industrial robot operates to the time node, and judging that the result comprises the accurate off-line prediction result and the deviation of the off-line prediction result; if the off-line prediction result is accurate, the health state of the industrial robot is continuously predicted by using the precision degradation model; if the off-line prediction result has deviation, implementing off-line feedback and off-line optimization links;
the off-line feedback link in the off-line diagnosis closed-loop system is that the operation characteristic parameters predicted by the digital-analog linkage algorithm are fed back to the precision degradation model;
the off-line optimization link in the off-line diagnosis closed-loop system comprises the steps of analyzing parameter influence and model evolution rules, improving a digital-analog linkage algorithm and optimizing parameters, and improving the accuracy of the precision degradation model on the health state prediction of the industrial robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010330674.3A CN111487950B (en) | 2020-04-24 | 2020-04-24 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010330674.3A CN111487950B (en) | 2020-04-24 | 2020-04-24 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111487950A CN111487950A (en) | 2020-08-04 |
| CN111487950B true CN111487950B (en) | 2021-11-16 |
Family
ID=71813019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010330674.3A Active CN111487950B (en) | 2020-04-24 | 2020-04-24 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111487950B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202093A (en) * | 2021-08-25 | 2022-03-18 | 优合集团有限公司 | Industrial chain optimization platform based on industrial internet |
| CN115809749B (en) * | 2023-02-09 | 2023-09-12 | 四川文韬工程技术有限公司 | Method for establishing comprehensive online prediction model of sewage treatment and prediction and early warning method |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101288089A (en) * | 2005-07-28 | 2008-10-15 | 西门子电力输送及配电有限公司 | Load prediction based on-line and off-line training of neural networks |
| CN102097636A (en) * | 2011-01-07 | 2011-06-15 | 武汉理工大学 | Fault diagnosis device and method of fuel cell system |
| CN102760192A (en) * | 2012-07-13 | 2012-10-31 | 中国电力科学研究院 | Real-time digital simulator-based power system closed loop verifying platform and method |
| CN103077103A (en) * | 2013-01-18 | 2013-05-01 | 浪潮电子信息产业股份有限公司 | Off-line diagnosing method for server faults |
| CN103810361A (en) * | 2012-11-09 | 2014-05-21 | 上海斐讯数据通信技术有限公司 | Diagnosis system and diagnosis method |
| CN104714175A (en) * | 2013-12-12 | 2015-06-17 | 北京有色金属研究总院 | Battery system fault diagnosis method and system |
| CN105846780A (en) * | 2016-03-19 | 2016-08-10 | 上海大学 | Decision tree model-based photovoltaic assembly fault diagnosis method |
| CN106705999A (en) * | 2016-12-21 | 2017-05-24 | 南京航空航天大学 | Fault diagnosis method for unmanned aerial vehicle gyroscope |
| CN106843172A (en) * | 2016-12-29 | 2017-06-13 | 中国矿业大学 | Complex industrial process On-line quality prediction method based on JY KPLS |
| CN107038453A (en) * | 2017-03-06 | 2017-08-11 | 辽宁大唐国际新能源有限公司 | The fault early warning system and determination methods of a kind of Wind turbines |
| CN107831652A (en) * | 2017-10-13 | 2018-03-23 | 国网河北能源技术服务有限公司 | A kind of unit load intelligent optimized control method based on cold end system energy storage |
| CN107944594A (en) * | 2017-09-30 | 2018-04-20 | 华南理工大学 | One kind is based on SPSS and RKELM microgrid short-term load forecasting methods |
| CN108287529A (en) * | 2017-12-28 | 2018-07-17 | 北京必可测科技股份有限公司 | Inspection, long-range accurate diagnosis and maintenance system and a method are patrolled in integration |
| CN109001979A (en) * | 2018-08-24 | 2018-12-14 | 东北大学 | Blast-melted quality adaptation Robust Predictive Control method based on Lazy learning |
| CN109446741A (en) * | 2018-12-21 | 2019-03-08 | 浙江工业大学 | A kind of modeling and prediction technique of mixing pump pump chamber transient temperature characteristic |
| CN109508818A (en) * | 2018-10-23 | 2019-03-22 | 保定正德电力技术有限公司 | A kind of online NOx prediction technique based on LSSVM |
| CN109800875A (en) * | 2019-01-08 | 2019-05-24 | 华南理工大学 | Chemical industry fault detection method based on particle group optimizing and noise reduction sparse coding machine |
| CN110262463A (en) * | 2019-07-09 | 2019-09-20 | 河海大学常州校区 | A kind of rail traffic platform door fault diagnosis system based on deep learning |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6326758B1 (en) * | 1999-12-15 | 2001-12-04 | Reliance Electric Technologies, Llc | Integrated diagnostics and control systems |
| US7301296B1 (en) * | 2001-07-23 | 2007-11-27 | Rockwell Automation Technologies, Inc. | Integrated control and diagnostics system |
| JP2004013450A (en) * | 2002-06-06 | 2004-01-15 | Hitachi Ltd | Distribution panel switch device and operation monitor control system |
| CN100470416C (en) * | 2006-12-28 | 2009-03-18 | 上海电力学院 | Power plant thermal equipment intelligent state diagnosing and analyzing system |
| US20190384255A1 (en) * | 2018-06-19 | 2019-12-19 | Honeywell International Inc. | Autonomous predictive real-time monitoring of faults in process and equipment |
| CN109146093B (en) * | 2018-08-08 | 2020-08-11 | 成都保源酷码科技有限公司 | Power equipment field investigation method based on learning |
| CN109977624A (en) * | 2019-05-06 | 2019-07-05 | 上海交通大学 | Photovoltaic plant soft fault monitoring method based on deep neural network |
-
2020
- 2020-04-24 CN CN202010330674.3A patent/CN111487950B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101288089A (en) * | 2005-07-28 | 2008-10-15 | 西门子电力输送及配电有限公司 | Load prediction based on-line and off-line training of neural networks |
| CN102097636A (en) * | 2011-01-07 | 2011-06-15 | 武汉理工大学 | Fault diagnosis device and method of fuel cell system |
| CN102760192A (en) * | 2012-07-13 | 2012-10-31 | 中国电力科学研究院 | Real-time digital simulator-based power system closed loop verifying platform and method |
| CN103810361A (en) * | 2012-11-09 | 2014-05-21 | 上海斐讯数据通信技术有限公司 | Diagnosis system and diagnosis method |
| CN103077103A (en) * | 2013-01-18 | 2013-05-01 | 浪潮电子信息产业股份有限公司 | Off-line diagnosing method for server faults |
| CN104714175A (en) * | 2013-12-12 | 2015-06-17 | 北京有色金属研究总院 | Battery system fault diagnosis method and system |
| CN105846780A (en) * | 2016-03-19 | 2016-08-10 | 上海大学 | Decision tree model-based photovoltaic assembly fault diagnosis method |
| CN106705999A (en) * | 2016-12-21 | 2017-05-24 | 南京航空航天大学 | Fault diagnosis method for unmanned aerial vehicle gyroscope |
| CN106843172A (en) * | 2016-12-29 | 2017-06-13 | 中国矿业大学 | Complex industrial process On-line quality prediction method based on JY KPLS |
| CN107038453A (en) * | 2017-03-06 | 2017-08-11 | 辽宁大唐国际新能源有限公司 | The fault early warning system and determination methods of a kind of Wind turbines |
| CN107944594A (en) * | 2017-09-30 | 2018-04-20 | 华南理工大学 | One kind is based on SPSS and RKELM microgrid short-term load forecasting methods |
| CN107831652A (en) * | 2017-10-13 | 2018-03-23 | 国网河北能源技术服务有限公司 | A kind of unit load intelligent optimized control method based on cold end system energy storage |
| CN108287529A (en) * | 2017-12-28 | 2018-07-17 | 北京必可测科技股份有限公司 | Inspection, long-range accurate diagnosis and maintenance system and a method are patrolled in integration |
| CN109001979A (en) * | 2018-08-24 | 2018-12-14 | 东北大学 | Blast-melted quality adaptation Robust Predictive Control method based on Lazy learning |
| CN109508818A (en) * | 2018-10-23 | 2019-03-22 | 保定正德电力技术有限公司 | A kind of online NOx prediction technique based on LSSVM |
| CN109446741A (en) * | 2018-12-21 | 2019-03-08 | 浙江工业大学 | A kind of modeling and prediction technique of mixing pump pump chamber transient temperature characteristic |
| CN109800875A (en) * | 2019-01-08 | 2019-05-24 | 华南理工大学 | Chemical industry fault detection method based on particle group optimizing and noise reduction sparse coding machine |
| CN110262463A (en) * | 2019-07-09 | 2019-09-20 | 河海大学常州校区 | A kind of rail traffic platform door fault diagnosis system based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| Generalized modeling and unbalanced fault simulation of saturated self-excited induction generators;R. Wamkeue etc.;<Electric Power Systems Research>;20021130;全文 * |
| 基于改进集成学习算法的在线空气质量预测;夏润 等;《武汉科技大学学报》;20190131;第42卷(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111487950A (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111487950B (en) | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis | |
| CN109459993B (en) | Online adaptive fault monitoring and diagnosing method for process industrial process | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| CN102361014B (en) | State monitoring and fault diagnosis method for large-scale semiconductor manufacture process | |
| CN111178553A (en) | Industrial equipment health trend analysis method and system based on ARIMA and LSTM algorithms | |
| CN113705924B (en) | Intelligent diagnosis method and system for thermal control equipment | |
| CN110097209A (en) | A kind of equipment deterioration analysis method based on parameter residual error | |
| CN111090939B (en) | Early warning method and system for abnormal working condition of petrochemical device | |
| CN106567964B (en) | A kind of flow control valve monitoring method based on DCS data | |
| CN109909306B (en) | Monitoring method for on-line monitoring and intelligent degradation trend early warning of acid rolling equipment | |
| KR102474332B1 (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
| CN110866695A (en) | Auxiliary maintenance decision method based on association of equipment running state and maintenance work | |
| CN116020879B (en) | Technological parameter-oriented strip steel hot continuous rolling space-time multi-scale process monitoring method and device | |
| CN103616877A (en) | Monitoring diagnostic method and system for energy pipe network | |
| CN111830871B (en) | Automatic equipment abnormality diagnosis system | |
| CN108628270A (en) | A kind of optimization network control unit and method based on PLC remote monitoring terminals | |
| CN116872206A (en) | Robot fault detection method and system based on industrial Internet | |
| CN112489841A (en) | Water level fault-tolerant control method for steam generator of nuclear power unit | |
| CN106439199A (en) | Monitoring method for control valve failure based on DCS data | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| CN115186754A (en) | Unit energy efficiency monitoring and diagnosing method based on information entropy and auto-associative regression model | |
| CN115407712A (en) | Intelligent maintenance system for hydraulic station of steel mill and working process | |
| JP2019191880A (en) | Equipment management support system | |
| CN116146402B (en) | Diagnosis and early warning method for pumping fault of main distributing valve of hydropower station speed regulator | |
| CN113681561B (en) | Intelligent industrial robot based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |