CN102129017A - Case-based intelligent local discharge fault identification system and identification method - Google Patents
Case-based intelligent local discharge fault identification system and identification method Download PDFInfo
- Publication number
- CN102129017A CN102129017A CN2010106157766A CN201010615776A CN102129017A CN 102129017 A CN102129017 A CN 102129017A CN 2010106157766 A CN2010106157766 A CN 2010106157766A CN 201010615776 A CN201010615776 A CN 201010615776A CN 102129017 A CN102129017 A CN 102129017A
- Authority
- CN
- China
- Prior art keywords
- module
- search method
- source
- case
- fault
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a case-based intelligent local discharge fault identification system and a case-based intelligent local discharge fault identification method, and relates to a fault identification system and a fault identification method. A local discharge detector can only display field acquired waveform and has no signal analysis function, the judgment of faults needs power experts to test and analyze on site, the search is slow, and the fault mode identification totally depends on experience and level of the field experts so as to bring great uncertainty to final fault diagnosis. The system comprises a signal sampling module, an example search module, a search method module, an example ordering module, a preferential standard module, a conclusion interpretation module, an example storage module and a source example module. Similar source examples are acquired form target examples, fault modes are determined through a built-in case by using a scientific geometric graph search method, and specific fault parts and serious degree are determined by using a Euclidean distance algorithm, so accuracy and reliability of fault diagnosis are improved.
Description
Technical field
The present invention relates to a kind of fault finding system and recognition methods, refer to based on the intelligent partial discharges fault recognition system and the recognition methods of citing a precedent especially.
Background technology
At present, Partial discharge detector can only show the waveform on the collection in worksite, does not have the analytic function of signal.More can not carry out pattern-recognition to partial discharges fault.Can only be in the unusual back alarm of on-site signal amplitude that detects, concrete failure judgment needs the electric power expert to the site test analysis, is unfavorable for searching fast of on-the-spot problem.And Fault Pattern Recognition relies on on-the-spot expert's experience and level fully, examines for final fault and brings very big uncertainty surely.
Summary of the invention
The technical assignment of the technical problem to be solved in the present invention and proposition is the prior art scheme to be carried out perfect, provides a kind of based on the intelligent partial discharges fault recognition system and the recognition methods of citing a precedent, with reach Fault Identification accurately, purpose easily.For this reason, the present invention takes following technical scheme.
1, based on the intelligent partial discharges fault recognition system of citing a precedent, it is characterized in that it comprises:
The signal sampling module is used for taking place to sample when unusual and successively preserve sample at signal;
The case retrieval module is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source model module is retrieved, and obtains a collection of source example similar to target case, then the source example is sent into the example order module;
The search method module, the query task of accepting the case retrieval module returns the recognition method of citing a precedent;
Example order module, example order module call according to qualifications that standard module obtains choice criteria, obtain after the choice criteria to the similar source of target case example ordering and select excellent;
Standard module is used to store choice criteria according to qualifications, and the query task of accepting the example order module returns choice criteria;
The conclusion explanation module links to each other with the example order module, according to the preferred source example to the explanation of drawing a conclusion of target model;
Example is preserved module, is used to store the target case of drawing a conclusion and explaining;
Source example module is used to store the typical case that comes from typical partial-discharge ultrahigh-frequency physics model emulation result and moved the unusual transformer of shelf depreciation in a large number.
The similar source example of this system from the prompting acquisition memory of target case, and by these mutually these similar source examples instruct the solution procedure of this target case, by built-in citing a precedent, can discern the fault mode type of shelf depreciation and the concrete trouble location and the order of severity accurately and reliably.
As the further of technique scheme improved and replenish, the present invention also comprises following additional technical feature.
The search method module is provided with to be utilized the geometric figure search method to determine the geometry search method unit of electric discharge type and utilizes the Euclidean distance algorithm to determine the Euclidean distance retrieval unit of concrete trouble location and order of severity.
Intelligent partial discharges fault recognition methods based on citing a precedent is characterized in that it may further comprise the steps:
1) sampling step takes place to sample when unusual and successively preserve sample at signal;
2) case retrieval step is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source model module is retrieved, and obtains a collection of source example similar to target case;
3) example ordered steps calls according to qualifications that standard module obtains choice criteria, and ordering is selected excellently to the similar source of target case example after obtaining choice criteria, obtains the best source example;
4) conclusion interpretation procedure is drawn a conclusion to the target model according to the preferred source example and to be explained and output;
5) example is preserved step, and the target case that storing draws a conclusion explains to example is preserved module and source example module.The similar source example of this method from the prompting acquisition memory of target case, and by these mutually these similar source examples instruct the solution procedure of this target case, by built-in citing a precedent, can discern the fault mode type of shelf depreciation and the concrete trouble location and the order of severity accurately and reliably.
Search method comprises the geometric figure search method that is used for determining electric discharge type, the Euclidean distance algorithm that is used for determining the concrete trouble location and the order of severity.
Beneficial effect: the similar source example of this system from the prompting acquisition memory of target case, and by these mutually these similar source examples instruct the solution procedure of this target case, by built-in citing a precedent, the geometric figure search method of employing science and Euclidean distance algorithm, utilize the geometric figure search method to determine fault mode, utilize the Euclidean distance algorithm to determine the concrete trouble location and the order of severity, improved accurate, the reliability of fault diagnosis.
Description of drawings
Fig. 1 is a structure principle chart of the present invention.
Fig. 2 is a process flow diagram of the present invention.
Embodiment
Below in conjunction with Figure of description technical scheme of the present invention is described in further detail.
Comprise based on the intelligent partial discharges fault recognition system of citing a precedent: the signal sampling module is used for taking place to sample when unusual and successively preserve sample at signal; The case retrieval module is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source example module is retrieved, and obtains a collection of source example similar to target case, then the source example is sent into the example order module; The search method module, the query task of accepting the case retrieval module returns the recognition method of citing a precedent; Example order module, example order module call according to qualifications that standard module obtains choice criteria, obtain after the choice criteria to the similar source of target case example ordering and select excellent; Standard module is used to store choice criteria according to qualifications, and the query task of accepting the example order module returns choice criteria; The conclusion explanation module links to each other with the example order module, according to the preferred source example to the explanation of drawing a conclusion of target model; Example is preserved module, is used to store the target case of drawing a conclusion and explaining; Source example module is used to store the typical case that comes from typical partial-discharge ultrahigh-frequency physics model emulation result and moved the unusual transformer of shelf depreciation in a large number.
Wherein the search method module is provided with and utilizes the geometric figure search method to determine the geometry search method unit of electric discharge type and utilize the Euclidean distance algorithm to determine the Euclidean distance retrieval unit of concrete trouble location and order of severity.
Based on the intelligent partial discharges fault recognition methods of citing a precedent, as shown in Figure 2, it may further comprise the steps:
1) sampling step takes place to sample when unusual and successively preserve sample at signal;
2) case retrieval step is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source model module is retrieved, and obtains a collection of source example similar to target case;
3) example ordered steps calls according to qualifications that standard module obtains choice criteria, and ordering is selected excellently to the similar source of target case example after obtaining choice criteria, obtains the best source example;
4) conclusion interpretation procedure is drawn a conclusion to the target model according to the preferred source example and to be explained and output;
5) example is preserved step, and the target case that storing draws a conclusion explains to example is preserved module and source example module.
Claims (4)
1. based on the intelligent partial discharges fault recognition system of citing a precedent, it is characterized in that it comprises:
The signal sampling module is used for taking place to sample when unusual and successively preserve sample at signal;
The case retrieval module is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source example module is retrieved, and obtains a collection of source example similar to target case, then the source example is sent into the example order module;
The search method module, the query task of accepting the case retrieval module returns the recognition method of citing a precedent;
Example order module, example order module call according to qualifications that standard module obtains choice criteria, obtain after the choice criteria to the similar source of target case example ordering and select excellent;
Standard module is used to store choice criteria according to qualifications, and the query task of accepting the example order module returns choice criteria;
The conclusion explanation module links to each other with the example order module, according to the preferred source example to the explanation of drawing a conclusion of target model;
Example is preserved module, is used to store the target case of drawing a conclusion and explaining;
Source example module is used to store the typical case that comes from typical partial-discharge ultrahigh-frequency physics model emulation result and moved the unusual transformer of shelf depreciation in a large number.
2. according to claim 1 based on the intelligent partial discharges fault recognition system of citing a precedent, it is characterized in that: the search method module is provided with to be utilized the geometric figure search method to determine the geometry search method unit of electric discharge type and utilizes the Euclidean distance algorithm to determine the Euclidean distance retrieval unit of concrete trouble location and order of severity.
3. according to claim 1 based on the intelligent partial discharges fault recognition methods of citing a precedent, it is characterized in that it may further comprise the steps:
1) sampling step takes place to sample when unusual and successively preserve sample at signal;
2) case retrieval step is accepted sample as the target model, calls the search method module and obtains search method, and according to search method source model module is retrieved, and obtains a collection of source example similar to target case;
3) example ordered steps calls according to qualifications that standard module obtains choice criteria, and ordering is selected excellently to the similar source of target case example after obtaining choice criteria, obtains the best source example;
4) conclusion interpretation procedure is drawn a conclusion to the target model according to the preferred source example and to be explained and output;
5) example is preserved step, and the target case that storing draws a conclusion explains to example is preserved module and source example module.
4. according to claim 3 based on the intelligent partial discharges fault recognition methods of citing a precedent, it is characterized in that: search method comprises the geometric figure search method that is used for determining electric discharge type, the Euclidean distance algorithm that is used for determining the concrete trouble location and the order of severity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010106157766A CN102129017A (en) | 2010-12-30 | 2010-12-30 | Case-based intelligent local discharge fault identification system and identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010106157766A CN102129017A (en) | 2010-12-30 | 2010-12-30 | Case-based intelligent local discharge fault identification system and identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102129017A true CN102129017A (en) | 2011-07-20 |
Family
ID=44267175
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010106157766A Pending CN102129017A (en) | 2010-12-30 | 2010-12-30 | Case-based intelligent local discharge fault identification system and identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102129017A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102707203A (en) * | 2012-02-16 | 2012-10-03 | 安徽理工大学 | Discriminating and measuring method for partial discharge modes of transformer |
CN106707118A (en) * | 2016-12-12 | 2017-05-24 | 国网北京市电力公司 | Method and device for identifying partial discharge pattern |
CN108375718A (en) * | 2017-01-30 | 2018-08-07 | 通用电气公司 | Assessment to phase-resolved shelf depreciation |
CN108414900A (en) * | 2018-03-08 | 2018-08-17 | 云南电网有限责任公司电力科学研究院 | A kind of method and system of detection partial discharge of transformer |
CN109523026A (en) * | 2018-10-17 | 2019-03-26 | 中国电力科学研究院有限公司 | It cites a precedent inference method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6088658A (en) * | 1997-04-11 | 2000-07-11 | General Electric Company | Statistical pattern analysis methods of partial discharge measurements in high voltage insulation |
JP2002090412A (en) * | 2000-09-12 | 2002-03-27 | Sumitomo Electric Ind Ltd | Partial-discharge measuring apparatus |
CN101251564A (en) * | 2008-04-08 | 2008-08-27 | 昆明理工大学 | Method for diagnosis failure of power transformer using extendible horticulture and inelegance collection theory |
KR20100048650A (en) * | 2008-10-31 | 2010-05-11 | 엘에스전선 주식회사 | Power apparatus defect detection method and system improved noise removal function |
CN102004211A (en) * | 2009-08-28 | 2011-04-06 | 上海市电力公司电缆输配电公司 | Method for detecting insulation defect of high-voltage cable accessory |
-
2010
- 2010-12-30 CN CN2010106157766A patent/CN102129017A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6088658A (en) * | 1997-04-11 | 2000-07-11 | General Electric Company | Statistical pattern analysis methods of partial discharge measurements in high voltage insulation |
JP2002090412A (en) * | 2000-09-12 | 2002-03-27 | Sumitomo Electric Ind Ltd | Partial-discharge measuring apparatus |
CN101251564A (en) * | 2008-04-08 | 2008-08-27 | 昆明理工大学 | Method for diagnosis failure of power transformer using extendible horticulture and inelegance collection theory |
KR20100048650A (en) * | 2008-10-31 | 2010-05-11 | 엘에스전선 주식회사 | Power apparatus defect detection method and system improved noise removal function |
CN102004211A (en) * | 2009-08-28 | 2011-04-06 | 上海市电力公司电缆输配电公司 | Method for detecting insulation defect of high-voltage cable accessory |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102707203A (en) * | 2012-02-16 | 2012-10-03 | 安徽理工大学 | Discriminating and measuring method for partial discharge modes of transformer |
CN106707118A (en) * | 2016-12-12 | 2017-05-24 | 国网北京市电力公司 | Method and device for identifying partial discharge pattern |
CN106707118B (en) * | 2016-12-12 | 2019-09-10 | 国网北京市电力公司 | Partial Discharge Pattern Recognition Method and device |
CN108375718A (en) * | 2017-01-30 | 2018-08-07 | 通用电气公司 | Assessment to phase-resolved shelf depreciation |
CN108375718B (en) * | 2017-01-30 | 2021-12-10 | 通用电气公司 | Evaluation of phase-resolved partial discharges |
CN108414900A (en) * | 2018-03-08 | 2018-08-17 | 云南电网有限责任公司电力科学研究院 | A kind of method and system of detection partial discharge of transformer |
CN109523026A (en) * | 2018-10-17 | 2019-03-26 | 中国电力科学研究院有限公司 | It cites a precedent inference method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105049814B (en) | A kind of method and system of monitoring analysis personnel motion trail | |
CN102129017A (en) | Case-based intelligent local discharge fault identification system and identification method | |
CN108763040A (en) | Collecting method and data acquisition device | |
CN104297577A (en) | Super capacitor-based aging state estimation detection system and method | |
CN101976401A (en) | Scanning test method used before delivery of batteries and system thereof | |
CN111711209B (en) | Optical storage and charging combined operation method and system based on energy storage life and frequency modulation performance | |
CN112614020A (en) | Electric propulsion state evaluation system based on electric energy quality | |
CN104344970A (en) | Equipment system fault integral diagnosis method and device | |
CN110826735B (en) | Electric SCADA intelligent multidimensional query and overhaul method | |
CN105954695A (en) | Synchronization-based homogeneous-sensor mutation parameter recognizing method and device | |
CN103957531B (en) | The method and apparatus that signal testing is carried out using intelligent communications terminal | |
CN109636663A (en) | The family of back-to-back distribution transformer becomes relation recognition method and apparatus | |
CN105974223A (en) | Method used for carrying out on-line detection on electric equipment work state and system thereof | |
CN105445591A (en) | Converter fault diagnosis method and converter fault diagnosis device | |
CN103198157B (en) | A kind of compression storage processing method of telluric electricity field data | |
CN103728134B (en) | The detection method of unit bearing and device and wind-powered electricity generation unit | |
CN104021232A (en) | Configuration item-based aircraft test data interpretation method | |
CN102540995B (en) | Produce line flow control system and method | |
CN108663568A (en) | Solar module debugging and testing device and testing method thereof | |
CN105791037B (en) | Automatic field test method and equipment | |
CN116430181A (en) | GIS external partial discharge identification method, device, equipment and medium | |
CN102905297A (en) | Base station engineering information acquisition method and system | |
CN114722310A (en) | Photovoltaic power station equipment fault diagnosis method, device, equipment and medium | |
CN114765574B (en) | Network anomaly delimitation positioning method and device | |
CN109342965A (en) | Alternating current-direct current internal resistance and insulation impedance detection system and method for battery module |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110720 |