CN113933707A - Self-adjusting method for judging reliability of fault reason of generator set - Google Patents

Self-adjusting method for judging reliability of fault reason of generator set Download PDF

Info

Publication number
CN113933707A
CN113933707A CN202111186278.9A CN202111186278A CN113933707A CN 113933707 A CN113933707 A CN 113933707A CN 202111186278 A CN202111186278 A CN 202111186278A CN 113933707 A CN113933707 A CN 113933707A
Authority
CN
China
Prior art keywords
fault
reason
reliability
fault reason
generator set
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.)
Granted
Application number
CN202111186278.9A
Other languages
Chinese (zh)
Other versions
CN113933707B (en
Inventor
孙永鑫
高洪军
杨世海
冯超
魏立华
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.)
Harbin Electric Machinery Co Ltd
Huaneng Yarlung Tsangpo River Hydropower Development Investment Co Ltd
Original Assignee
Harbin Electric Machinery Co Ltd
Huaneng Yarlung Tsangpo River Hydropower Development Investment Co 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 Harbin Electric Machinery Co Ltd, Huaneng Yarlung Tsangpo River Hydropower Development Investment Co Ltd filed Critical Harbin Electric Machinery Co Ltd
Priority to CN202111186278.9A priority Critical patent/CN113933707B/en
Publication of CN113933707A publication Critical patent/CN113933707A/en
Application granted granted Critical
Publication of CN113933707B publication Critical patent/CN113933707B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34Testing dynamo-electric machines
    • G01R31/343Testing dynamo-electric machines in operation

Abstract

The invention discloses a self-adjusting method for judging reliability of a fault reason of a generator set, and belongs to the field of intelligent operation and maintenance of generator sets. According to the method, a fault reason criterion result in a fault diagnosis system is determined according to on-line monitoring point data in the fault diagnosis process of the generator set, and the reliability of fault reason judgment is automatically corrected and updated in real time through a self-adjusting algorithm. The invention has the advantages of clear principle, simple structure, accurate calculation and high operation efficiency, can continuously self-adjust the reliability of each fault reason judgment according to the generator operation monitoring data, ensures that the reliability is consistent with the unit deterioration degree, improves the accuracy of the fault diagnosis reason probability, and provides scientific and effective technical support for realizing automation and intellectualization of the generator unit fault diagnosis.

Description

Self-adjusting method for judging reliability of fault reason of generator set
Technical Field
The invention relates to the field of intelligent operation and maintenance of a generator set, in particular to a self-adjusting method for judging reliability of fault reasons of the generator set.
Background
The fault diagnosis and the reason judgment are important components in the intelligent operation and maintenance field of the generator set. Accurate fault diagnosis and reason judgment can ensure that the reason of the fault is quickly positioned when the generator set has problems, and corresponding processing measures and schemes are made, thereby providing powerful support for intelligent maintenance decision of the generator set.
In the fault cause judgment of the generator set, the reliability of the judgment result is an important index for determining the correctness of the reasoning result. In the conventional fault cause diagnosis method, the reliability of the judgment structure is usually a fixed value, is determined according to expert experience, and is not changed along with the operation parameters of the group. The method can obtain the probability of the failure reason of the unit, but can not establish direct connection with the running state of the unit, so that the inference result and the actual working condition have larger difference.
In view of this, it is necessary to develop a self-adjusting method for determining reliability of a fault cause of a generator set. The method needs to consider the influence of the measured point data on the reliability of the fault reason judgment when the unit runs, the more normal the measured point data is, the smaller the reliability of the fault reason judgment is, the more abnormal the measured point data is, the greater the reliability of the fault reason judgment is, so that the strong correlation between the unit running condition and the reliability of the fault reason judgment is achieved, the reliability of the fault reason judgment is automatically adjusted and updated in real time along with the measured point data, and the judgment result of the fault diagnosis reason of the generator set is ensured to be consistent with the running state of the unit all the time.
Disclosure of Invention
The invention aims to provide a self-adjusting method for judging reliability of a fault reason of a generator set, and the technical scheme of the invention comprises the following steps:
The method comprises the following steps: establishing a method for judging fault reasons of the generator set according to the design and operation principle of the generator set, and determining that k fault reason criteria are provided for one fault reason A, wherein the k fault reason criteria are c1、c2、…、ckFor i ≦ 1 ≦ k, when all k cause criteria ciIf both are true, the fault reason A is true, and when any reason is judged as ciIf it is false, thenThe failure cause A is false;
step two: criterion c for each cause of failureiAll the unified logic judgment modes are Li1≤Ti≤Li2Wherein T isiCriterion c for indicating fault causeiCorresponding measured point data of, Li1Representing measured point data TiLower limit of (D), Li2Representing measured point data TiUpper limit of (c) when all k causal criteria areiWhen all are true, the reason is judged as ciAnd the corresponding criterion value LiLinear normalization processing is carried out to obtain a criterion value LiExpressed as:
Figure BDA0003299355160000021
step three: the lower limit of the reliability of the judgment of the failure reason A is set as R1The upper limit of reliability of the failure cause A judgment is R2According to the criterion c of each fault reason in the step twoiIs determined by the criterion value LiAnd obtaining the reliability R when the fault reason A is judged to be true:
Figure BDA0003299355160000031
step four: and repeating the first step, the second step and the third step to obtain the credibility of each fault reason when the fault reason is judged to be true, and further comprehensively obtaining the occurrence probability of each fault reason.
In the self-adjusting method for judging reliability of fault reasons of the generator set, in the second step, each fault reason criterion c is determinediHas and only one corresponding measuring point data Ti
In the self-adjusting method for judging reliability of fault reasons of the generator set, in the second step, a reason criterion c is adoptediCorresponding criterion value LiSatisfies 0<Li≤1。
In the self-adjusting method for judging reliability of fault cause of the generator set, in the third step, the reliability when the fault cause A is judged to be true is judgedDegree R satisfies R1<R≤R2
The invention has the beneficial effects that:
the self-adjusting method for judging the reliability of the fault reason of the generator set, provided by the invention, has the following technical effects:
1. and the reliability of fault reason judgment is adaptive to the state of the unit. In the process of determining the reliability of fault cause judgment, the influence of the unit state monitoring data on the reliability is considered, and the reliability change trend is adaptive to the unit state.
2. And adjusting the fault reason judgment credibility result in real time. The state monitoring data of the unit is refreshed in real time, so that the automatic adjustment and real-time update of the judgment reliability of the fault reason are realized, and the fault diagnosis result is ensured to meet the requirement of the dynamic change of the unit.
Drawings
FIG. 1 is a flow chart of a self-adjusting method for determining reliability of a fault cause of a generator set.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
A self-adjusting method for judging reliability of a fault reason of a generator set comprises the following steps:
the method comprises the following steps: establishing a method for judging fault reasons of the generator set according to the design and operation principle of the generator set, and determining that k fault reason criteria are provided for one fault reason A, wherein the k fault reason criteria are c1、c2、…、ckFor i ≦ 1 ≦ k, when all k cause criteria ciIf both are true, the fault reason A is true, and when any reason is judged as ciIf the result is false, the fault reason A is false; in this step when ciWhen the false is taken as the criterion, c can be takeniConvert to self complement as the cause criterion to ensure all ciIf true, the failure cause a is true.
Step two: criterion c for each cause of failureiAll the unified logic judgment modes are Li1≤Ti≤Li2Wherein T isiCriterion c for indicating fault causeiCorresponding measured point data of, Li1Representing measured point data T iLower limit of (D), Li2Representing measured point data TiUpper limit of (c) when all k causal criteria areiWhen all are true, the reason is judged as ciAnd the corresponding criterion value LiLinear normalization processing is carried out to obtain a criterion value LiExpressed as:
Figure BDA0003299355160000051
criterion c for each fault reason in the stepiHas and only one corresponding measuring point data TiThe reason criterion ciCorresponding criterion value LiSatisfies 0<LiLess than or equal to 1; the purpose of this step is to establish a criterion value LiAnd measurement point data TiThe relationship between the point data T and the point dataiThe larger the value, the higher the deterioration degree, and the criterion value LiThe larger.
Step three: the lower limit of the reliability of the judgment of the failure reason A is set as R1The upper limit of reliability of the failure cause A judgment is R2According to the criterion c of each fault reason in the step twoiIs determined by the criterion value LiAnd obtaining the reliability R when the fault reason A is judged to be true:
Figure BDA0003299355160000052
the reliability R when the fault cause A is judged to be true in the step satisfies R1<R≤R2(ii) a The purpose of the step is to adjust the credibility R by using all the criterion values judged by the fault reason A, wherein the larger each criterion value is, the larger the adjusted credibility R is, and the higher the occurrence probability of the fault reason A is.
Step four: and repeating the first step, the second step and the third step to obtain the credibility of each fault reason when the fault reason is judged to be true, and further comprehensively obtaining the occurrence probability of each fault reason. The purpose of the step is to realize the self-adjustment of the judgment reliability of the fault reason of the generator set at each moment, ensure the dynamic change of the judgment reliability of the fault reason and ensure that the judgment reliability of the fault reason is consistent with the running condition of the generator set.
The present invention is illustrative only and not intended to limit the scope thereof, and those skilled in the art can make modifications to the present invention without departing from the spirit and scope thereof.

Claims (4)

1. A self-adjusting method for judging reliability of a fault reason of a generator set is characterized by comprising the following steps:
the method comprises the following steps: establishing a method for judging fault reasons of the generator set according to the design and operation principle of the generator set, and determining that k fault reason criteria are provided for one fault reason A, wherein the k fault reason criteria are c1、c2、…、ckFor i ≦ 1 ≦ k, when all k cause criteria ciIf both are true, the fault reason A is true, and when any reason is judged as ciIf the result is false, the fault reason A is false;
step two: criterion c for each cause of failureiAll the unified logic judgment modes are Li1≤Ti≤Li2Wherein T isiCriterion c for indicating fault causeiCorresponding measured point data of, Li1Representing measured point data TiLower limit of (D), Li2Representing measured point data TiUpper limit of (c) when all k causal criteria areiWhen all are true, the reason is judged as ciAnd the corresponding criterion value LiLinear normalization processing is carried out to obtain a criterion value LiExpressed as:
Figure FDA0003299355150000011
step three: the lower limit of the reliability of the judgment of the failure reason A is set as R 1The upper limit of reliability of the failure cause A judgment is R2According to each event in the second stepCriterion of cause of failure ciIs determined by the criterion value LiAnd obtaining the reliability R when the fault reason A is judged to be true:
Figure FDA0003299355150000021
step four: and repeating the first step, the second step and the third step to obtain the credibility of each fault reason when the fault reason is judged to be true, and further comprehensively obtaining the occurrence probability of each fault reason.
2. The self-adjusting method for determining reliability of a generator set fault cause according to claim 1, comprising: in the second step, each fault reason criterion ciHas and only one corresponding measuring point data Ti
3. The self-adjusting method for determining reliability of a generator set fault cause according to claim 1, comprising: in the second step, the reason criterion ciCorresponding criterion value LiSatisfies 0<Li≤1。
4. The self-adjusting method for determining reliability of a generator set fault cause according to claim 1, comprising: in the third step, the credibility R when the fault reason A is judged to be true satisfies R1<R≤R2
CN202111186278.9A 2021-10-12 2021-10-12 Self-adjusting method for judging reliability of fault cause of generator set Active CN113933707B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111186278.9A CN113933707B (en) 2021-10-12 2021-10-12 Self-adjusting method for judging reliability of fault cause of generator set

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111186278.9A CN113933707B (en) 2021-10-12 2021-10-12 Self-adjusting method for judging reliability of fault cause of generator set

Publications (2)

Publication Number Publication Date
CN113933707A true CN113933707A (en) 2022-01-14
CN113933707B CN113933707B (en) 2023-09-19

Family

ID=79278841

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111186278.9A Active CN113933707B (en) 2021-10-12 2021-10-12 Self-adjusting method for judging reliability of fault cause of generator set

Country Status (1)

Country Link
CN (1) CN113933707B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070192078A1 (en) * 2006-02-14 2007-08-16 Edsa Micro Corporation Systems and methods for real-time system monitoring and predictive analysis
JP2007249614A (en) * 2006-03-16 2007-09-27 Fujitsu Ltd System device and information collection method
US20100100259A1 (en) * 2008-10-22 2010-04-22 Denis Geiter Fault diagnosis device and method for optimizing maintenance measures in technical systems
US20130317768A1 (en) * 2011-03-17 2013-11-28 Abb Technology Ltd. Voltage based method for fault identification in a transmission line and apparatus thereof
CN103605787A (en) * 2013-12-03 2014-02-26 国家电网公司 Method and system for evaluating and analyzing relay protection
CN107065834A (en) * 2017-05-25 2017-08-18 东北大学 The method for diagnosing faults of concentrator in hydrometallurgy process
CN107103425A (en) * 2017-04-26 2017-08-29 哈尔滨电机厂有限责任公司 Generating equipment running status computer intelligence quantitatively evaluating system
CN110553821A (en) * 2019-07-08 2019-12-10 湖北华电襄阳发电有限公司 Visualized diagnosis method and system for faults of steam turbine generator unit
CN110617981A (en) * 2019-09-16 2019-12-27 江苏方天电力技术有限公司 Fault diagnosis method for phase modulator
CN111650476A (en) * 2020-07-06 2020-09-11 国网江苏省电力有限公司沛县供电分公司 Sampling value method-based single-phase arc ground fault line selection method for power distribution network
KR102278199B1 (en) * 2020-12-31 2021-07-16 주식회사 한국가스기술공사 Method for managing diagnostic data based on conditional probability

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070192078A1 (en) * 2006-02-14 2007-08-16 Edsa Micro Corporation Systems and methods for real-time system monitoring and predictive analysis
JP2007249614A (en) * 2006-03-16 2007-09-27 Fujitsu Ltd System device and information collection method
US20100100259A1 (en) * 2008-10-22 2010-04-22 Denis Geiter Fault diagnosis device and method for optimizing maintenance measures in technical systems
US20130317768A1 (en) * 2011-03-17 2013-11-28 Abb Technology Ltd. Voltage based method for fault identification in a transmission line and apparatus thereof
CN103605787A (en) * 2013-12-03 2014-02-26 国家电网公司 Method and system for evaluating and analyzing relay protection
CN107103425A (en) * 2017-04-26 2017-08-29 哈尔滨电机厂有限责任公司 Generating equipment running status computer intelligence quantitatively evaluating system
CN107065834A (en) * 2017-05-25 2017-08-18 东北大学 The method for diagnosing faults of concentrator in hydrometallurgy process
CN110553821A (en) * 2019-07-08 2019-12-10 湖北华电襄阳发电有限公司 Visualized diagnosis method and system for faults of steam turbine generator unit
CN110617981A (en) * 2019-09-16 2019-12-27 江苏方天电力技术有限公司 Fault diagnosis method for phase modulator
CN111650476A (en) * 2020-07-06 2020-09-11 国网江苏省电力有限公司沛县供电分公司 Sampling value method-based single-phase arc ground fault line selection method for power distribution network
KR102278199B1 (en) * 2020-12-31 2021-07-16 주식회사 한국가스기술공사 Method for managing diagnostic data based on conditional probability

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
范文涛, 王广延: "基于模糊集理论的变压器微机差动保护新判据", 中国电机工程学报, no. 06 *

Also Published As

Publication number Publication date
CN113933707B (en) 2023-09-19

Similar Documents

Publication Publication Date Title
CN108627720B (en) Power equipment state monitoring method based on Bayesian algorithm
CN108335021A (en) A kind of method and maintenance decision optimization of wind energy conversion system state Reliability assessment
CN113762604B (en) Industrial Internet big data service system
CN110687895B (en) Chemical process fault detection method based on self-adaptive kernel principal component analysis
CN110209144B (en) Two-layer real-time monitoring and alarm tracing method based on dynamic and static cooperative difference analysis
CN116467667B (en) Power failure monitoring and early warning method and system based on data fusion
CN110907170A (en) Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method
CN112563542A (en) Fuel cell online detection method and detection system
CN113933707A (en) Self-adjusting method for judging reliability of fault reason of generator set
CN116151799A (en) BP neural network-based distribution line multi-working-condition fault rate rapid assessment method
CN108282360B (en) Fault detection method for long-term and short-term prediction fusion
CN115856613A (en) Circuit breaker state evaluation method
CN112651444B (en) Self-learning-based non-stationary process anomaly detection method
CN111884487B (en) Control method and system of converter and wind power system
CN115456041A (en) Equipment fault early warning method and device, computing equipment and storage medium
CN112240267B (en) Fan monitoring method based on wind speed correlation and wind power curve
CN112084661B (en) Wind turbine converter water cooling system cooling state assessment early warning method
CN113704323A (en) Timing sequence anomaly detection algorithm based on HTM improvement
CN113418632A (en) Conceptual drift detection method for oil temperature prediction of oil-immersed transformer
CN113933708B (en) Self-correction method for intelligent fault cause diagnosis probability of generator set
CN113159138B (en) Gas boiler fault diagnosis method and device based on data fusion
Huang et al. Bearing Fault Diagnosis With Incomplete Training Data: Fault Data With Partial Diameters
CN116955091B (en) Data center fault detection system based on machine learning
CN117034157B (en) Hydropower equipment fault identification method and system combining multimodal operation data
Liu et al. Research on Multi-type Abnormal Data Preprocessing Method of Wind Turbine based on Data Identification

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