CN108535618A - A kind of GIS method for detecting insulation defect - Google Patents
A kind of GIS method for detecting insulation defect Download PDFInfo
- Publication number
- CN108535618A CN108535618A CN201810776458.4A CN201810776458A CN108535618A CN 108535618 A CN108535618 A CN 108535618A CN 201810776458 A CN201810776458 A CN 201810776458A CN 108535618 A CN108535618 A CN 108535618A
- Authority
- CN
- China
- Prior art keywords
- gis
- vfto
- fault
- fault waveform
- insulation defect
- 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
Classifications
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1254—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of gas-insulated power appliances or vacuum gaps
Abstract
This application discloses a kind of GIS method for detecting insulation defect, utilize the different characteristic of the VFTO fault waveforms of the GIS generations of different insulative defect type, by the VFTO fault waveforms characteristic quantity and VFTO fault waveforms extracted in advance, to judge the insulation defect type of failure GIS.The GIS method for detecting insulation defect of the application, by carrying out very fast transient overvoltage experiment to GIS device, the insulation defect inside GIS can effectively, be timely found, and judge the type of its insulation defect, to avoid that accident occurs in GIS operations, and then ensure power grid security, stable operation.
Description
Technical field
This application involves GIS failure analysis techniques field more particularly to a kind of GIS method for detecting insulation defect.
Background technology
GIS (Gas Isolated Switchgare, gas-insulated switchgear), may in transport and installation process
There is insulation defect, includes with regard to its type:1) it is that free conducting particle and dust invade inside GIS, and are moved down in electric field action
Dynamic to cause, referred to as movable insulation defect, 2) it is since the accident in the manufacturing defect of insulating part, installation and transportation causes electrode surface
Damage etc., referred to as fixed insulation defect, 3) be other insulation defects.
Currently, for the integrity of insulation performance after the completion of inspection GIS overall installations, to effectively find part inside GIS
Potential faults caused by insulation defect need to carry out ac voltage withstanding experiment to GIS.But just from the point of view of current test situation,
Ac voltage withstanding experiment is only carried out at scene can not expose all insulation defects of GIS, still be unable to ensure GIS in good situation
Under put into operation.For example, the logical switchyard 363kV GIS of Qinghai Power Grid 330kV peaces are tested in ac voltage withstanding and are passed through, have the item that puts into operation
After part, the supporting insulator edge flashing when putting into operation charging causes singlephase earth fault.Trace it to its cause is due to erecting bed ring
Border condition control is bad, causes dust to enter inside 363kV GIS, electrically conductive particles are attached to supporting insulator surface, cause to put
Electricity.And ac voltage withstanding experiment is extremely insensitive to the dirty and electric field structure of insulator surface, therefore the exchange before putting into operation is resistance to
Drawbacks described above is not found in pressure experiment.
Therefore, a kind of effectively to find that the detection method of GIS built-in electrical insulation defects urgently needs.
Invention content
This application provides a kind of GIS method for detecting insulation defect, can not be accurate to solve existing ac voltage withstanding experiment
Identification and the problem of judging insulation defect existing for GIS.
This application provides a kind of GIS method for detecting insulation defect, for detecting GIS built-in electrical insulation defects, including:
Acquire the corresponding VFTO fault waveforms of multiple failure GIS, wherein multiple failure GIS include different insulative defect
The GIS of type;
For each failure GIS, the fault waveform characteristic quantity of its VFTO fault waveform is extracted;
For each failure GIS, according to the fault waveform characteristic quantity of failure GIS, to the insulation defect class of failure GIS
Type is demarcated;
Using faulty GIS fault waveform characteristic quantity and insulation defect type, establish VFTO fault waveform databases;
Using VFTO fault waveform databases, corresponding Random Forest model is built;
The VFTO fault waveforms that failure GIS to be detected is inputted to Random Forest model, the insulation for obtaining failure GIS to be measured lack
Fall into type.
Preferably, fault waveform extracted amount includes polarity, breakdown crest voltage UP, breakdown peak point current IPAnd breakdown potential
Buckling rate U.
Preferably, the calculation formula of breakdown voltage change rate U is,Wherein, UPTo puncture peak value
Voltage value, UtFor 3 μ s when voltage value.
Preferably, using VFTO fault waveform databases, it further includes utilizing later to build corresponding Random Forest model
VFTO fault waveform databases, verify the Random Forest model of structure.
Preferably, using VFTO fault waveform databases, corresponding Random Forest model is built, and to the random gloomy of structure
Woods model is verified,
It specifically includes, randomly selects data at least more than half in VFTO fault waveform databases as sample data,
Using sample data, corresponding Random Forest model is built;
The data for doing sample data will not taken to utilize verification number as verify data in VFTO fault waveform databases
According to the Random Forest model progress cross validation built in previous step.
This application provides a kind of GIS method for detecting insulation defect, are generated using the GIS of different insulative defect type
The different characteristic of VFTO fault waveforms, by the VFTO fault waveforms characteristic quantity and VFTO fault waveforms extracted in advance, thus
Judge the insulation defect type of failure GIS.The GIS method for detecting insulation defect of the application, by carrying out express speed to GIS device
Transient overvoltage is tested, and can effectively, timely find the insulation defect inside GIS, and judge the type of its insulation defect, to
Accident occurs in avoiding GIS from running, and then ensures power grid security, stable operation.
Description of the drawings
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without creative efforts, also
It can be obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart of the application GIS method for detecting insulation defect.
Specific implementation mode
This application provides a kind of GIS method for detecting insulation defect, are used to detect GIS built-in electrical insulation defects, and judge
The insulation defect type of GIS.Before illustrating the specific steps of this method, the principle of first this method illustrates.In GIS,
Disconnecting switch point, sum velocity it is slower, therefore, when suiting capacity current, prebreakdown will occur between the contact of disconnecting switch
With repeatedly restrike, form a rise time very short shock wave, which, by multiple reflections, refraction, causes inside GIS
Fast transient oscillatory process, thus one very fast transient overvoltage of formation (very fast Transient Over-voltage,
VFTO).The GIS of different insulative defect type, very fast transient overvoltage waveform (the hereinafter referred to as VFTO fault waves formed
Shape) it is different, therefore, in the application, the very fast transient overvoltage waveform generated using the GIS of different insulative defect type is different
Characteristic, pass through the VFTO fault waveforms characteristic quantity and VFTO fault waveforms extracted in advance, the insulation defect of judgement failure GIS
Type.
Fig. 1 is the flow chart of the application GIS method for detecting insulation defect, as shown in Figure 1, this method specifically includes,
Step S1OO acquires the corresponding VFTO fault waveforms of multiple failure GIS, wherein multiple failure GIS include different
The GIS of insulation defect type.
Currently, GIS insulation defect types include movable insulation defect, fixed insulation defect and other insulation defects.For
Ensure accuracy of this method to the insulation defect type decision of failure GIS to be measured, it should be ensured that the VFTO fault waveform packets of acquisition
The VFTO fault waveforms of the GIS of each insulation defect type are contained.
Step S2OO extracts the fault waveform characteristic quantity of its VFTO fault waveform for each failure GIS.
In the present embodiment, fault waveform extracted amount includes polarity, breakdown crest voltage UP, breakdown peak point current IPAnd it hits
Wear voltage change ratio U.Wherein, the calculation formula of breakdown voltage change rate U is,Wherein, UPFor breakdown
Peak voltage, UtFor 3 μ s when voltage value.
Step S3OO, for each failure GIS, according to the fault waveform characteristic quantity of failure GIS, to failure GIS's
Insulation defect type is demarcated.
The detailed process demarcated to the insulation defect type of failure GIS includes, by the fault waveform feature of failure GIS
Amount carries out corresponding comparison with the fault waveform characteristic quantity of known fault type, the insulation defect type of GIS so that judgement is out of order.
In the present embodiment, GIS fault types are divided into movable insulation defect, fixed insulation defect and other insulation defects, for every
Kind fault type, has its distinctive fault waveform characteristic quantity, therefore, can judge failure GIS's by fault waveform characteristic quantity
Fault type.
Step S4OO, using faulty GIS fault waveform characteristic quantity and insulation defect type, establish VFTO fault waves
Graphic data library.
Step S5OO builds corresponding Random Forest model using VFTO fault waveform databases.
For ensure structure Random Forest model accuracy, in the application, build corresponding Random Forest model it
After further include step S6OO, using VFTO fault waveform databases, the Random Forest model of structure is verified.
In the present embodiment, using VFTO fault waveform databases, build corresponding Random Forest model, and to structure with
Machine forest model is verified, and is specifically included, and is randomly selected data at least more than half in VFTO fault waveform databases and is made
For sample data corresponding Random Forest model is built using sample data;It is done not taken in VFTO fault waveform databases
The data of sample data hand over the Random Forest model built in previous step using verify data as verify data
Fork verification.
Those skilled in the art can according to actual needs, adjust the sample data of extraction and the quantity of sample data, such as
75% data are as sample data in extraction VFTO fault waveform databases, correspondingly, being remained in VFTO fault waveform databases
25% remaining data are as verify data.
Step S7OO inputs the VFTO fault waveforms of failure GIS to be detected to Random Forest model, obtains failure to be measured
The insulation defect type of GIS.
Certainly, in practical applications, when getting the VFTO fault waveforms of greater number of failure GIS, will can newly obtain
The VFTO fault waveforms taken are added to VFTO fault waveform databases, then, to the VFTO fault waveforms database that newly obtains into
Row training rebuilds more accurate Random Forest model, and then improves accuracy of this method to insulation defect type decision.
The GIS method for detecting insulation defect of the application can by carrying out very fast transient overvoltage experiment to GIS device
Effectively, it timely finds the insulation defect inside GIS, and judges the type of its insulation defect, to avoid occurring in GIS operations
Accident, and then ensure power grid security, stable operation.The GIS method for detecting insulation defect of the application, by being carried out to GIS device
Very fast transient overvoltage is tested, and can effectively, timely find the insulation defect inside GIS, and judge the class of its insulation defect
Type to avoid that accident occurs in GIS operations, and then ensures power grid security, stable operation.
Above-described the application embodiment does not constitute the restriction to the application protection domain.
Claims (5)
1. a kind of GIS method for detecting insulation defect, for detecting GIS built-in electrical insulation defects, which is characterized in that including:
Acquire the corresponding VFTO fault waveforms of multiple failure GIS, wherein multiple failure GIS include different insulative defect type
GIS;
For each failure GIS, the fault waveform characteristic quantity of its VFTO fault waveform is extracted;
For each failure GIS, according to the fault waveform characteristic quantity of failure GIS, to the insulation defect type of failure GIS into
Rower is fixed;
Using faulty GIS fault waveform characteristic quantity and insulation defect type, establish VFTO fault waveform databases;
Using VFTO fault waveform databases, corresponding Random Forest model is built;
The VFTO fault waveforms that failure GIS to be detected is inputted to Random Forest model obtain the insulation defect class of failure GIS to be measured
Type.
2. according to the method described in claim 1, it is characterized in that, fault waveform extracted amount includes polarity, breakdown crest voltage
UP, breakdown peak point current IPAnd breakdown voltage change rate U.
3. according to the method described in claim 2, it is characterized in that, the calculation formula of breakdown voltage change rate U is,Wherein, UPTo puncture peak voltage, UtFor 3 μ s when voltage value.
4. according to the method described in claim 1, it is characterized in that, using VFTO fault waveform databases, structure it is corresponding with
Further include, using VFTO fault waveform databases, being verified to the Random Forest model of structure after machine forest model.
5. according to the method described in claim 4, it is characterized in that, using VFTO fault waveform databases, structure it is corresponding with
Machine forest model, and the Random Forest model of structure is verified,
It specifically includes, randomly selects data at least more than half in VFTO fault waveform databases as sample data, utilize
Sample data builds corresponding Random Forest model;
Do not taken the data for doing sample data as verify data using in VFTO fault waveform databases, it is right using verify data
The Random Forest model built in previous step carries out cross validation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810776458.4A CN108535618A (en) | 2018-07-11 | 2018-07-11 | A kind of GIS method for detecting insulation defect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810776458.4A CN108535618A (en) | 2018-07-11 | 2018-07-11 | A kind of GIS method for detecting insulation defect |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108535618A true CN108535618A (en) | 2018-09-14 |
Family
ID=63488148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810776458.4A Pending CN108535618A (en) | 2018-07-11 | 2018-07-11 | A kind of GIS method for detecting insulation defect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108535618A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109376626A (en) * | 2018-10-10 | 2019-02-22 | 国网陕西省电力公司电力科学研究院 | A kind of GIS switch defect diagnostic method based on radiated electric field characteristic parameter support vector machines |
CN110231553A (en) * | 2019-07-12 | 2019-09-13 | 电子科技大学 | A kind of motor slot insulation electric field impact appraisal procedure and assessment device |
CN111123087A (en) * | 2019-12-24 | 2020-05-08 | 深圳供电局有限公司 | Power distribution network switching equipment fault detection method and device and computer equipment |
CN111965504A (en) * | 2020-08-14 | 2020-11-20 | 广东电网有限责任公司电力科学研究院 | Method and device for evaluating typical insulation defects of GIS (gas insulated switchgear) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102749559A (en) * | 2012-07-09 | 2012-10-24 | 云南电力试验研究院(集团)有限公司电力研究院 | VFTO (Very Fast Transient Overvoltage) online measurement and alarm system for electric power |
CN103048593A (en) * | 2012-12-12 | 2013-04-17 | 安徽省电力公司亳州供电公司 | Identification method of insulation defect type of gas-insulated switchgear |
CN103728543A (en) * | 2014-01-17 | 2014-04-16 | 国家电网公司 | Method and device for online monitoring and diagnosis on insulation state of gas insulated switchgear (GIS) invaded by steep waves |
CN105629145A (en) * | 2016-03-31 | 2016-06-01 | 国网天津市电力公司 | 10KV insulation tube bus ultrahigh frequency partial discharge detection device |
CN105676121A (en) * | 2016-03-11 | 2016-06-15 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Flashover fault evaluation method for 220kV and above porcelain knob type circuit breaker |
CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
CN106951863A (en) * | 2017-03-20 | 2017-07-14 | 贵州电网有限责任公司电力科学研究院 | A kind of substation equipment infrared image change detecting method based on random forest |
CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
CN107192943A (en) * | 2017-06-15 | 2017-09-22 | 国家电网公司 | Fault diagnosis method for switch in the GIS measured based on switching manipulation radiated electric field |
CN107356823A (en) * | 2017-09-01 | 2017-11-17 | 云南电网有限责任公司电力科学研究院 | A kind of 500kV GIS disc insulators VFTO experimental rigs |
CN108197639A (en) * | 2017-12-14 | 2018-06-22 | 佛山科学技术学院 | A kind of Diagnosis Method of Transformer Faults based on random forest |
-
2018
- 2018-07-11 CN CN201810776458.4A patent/CN108535618A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102749559A (en) * | 2012-07-09 | 2012-10-24 | 云南电力试验研究院(集团)有限公司电力研究院 | VFTO (Very Fast Transient Overvoltage) online measurement and alarm system for electric power |
CN103048593A (en) * | 2012-12-12 | 2013-04-17 | 安徽省电力公司亳州供电公司 | Identification method of insulation defect type of gas-insulated switchgear |
CN103728543A (en) * | 2014-01-17 | 2014-04-16 | 国家电网公司 | Method and device for online monitoring and diagnosis on insulation state of gas insulated switchgear (GIS) invaded by steep waves |
CN105676121A (en) * | 2016-03-11 | 2016-06-15 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Flashover fault evaluation method for 220kV and above porcelain knob type circuit breaker |
CN105629145A (en) * | 2016-03-31 | 2016-06-01 | 国网天津市电力公司 | 10KV insulation tube bus ultrahigh frequency partial discharge detection device |
CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
CN106951863A (en) * | 2017-03-20 | 2017-07-14 | 贵州电网有限责任公司电力科学研究院 | A kind of substation equipment infrared image change detecting method based on random forest |
CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
CN107192943A (en) * | 2017-06-15 | 2017-09-22 | 国家电网公司 | Fault diagnosis method for switch in the GIS measured based on switching manipulation radiated electric field |
CN107356823A (en) * | 2017-09-01 | 2017-11-17 | 云南电网有限责任公司电力科学研究院 | A kind of 500kV GIS disc insulators VFTO experimental rigs |
CN108197639A (en) * | 2017-12-14 | 2018-06-22 | 佛山科学技术学院 | A kind of Diagnosis Method of Transformer Faults based on random forest |
Non-Patent Citations (1)
Title |
---|
朱跃 等: "750 kV GIS电站VFTO波形特征参量的提取及统计分析", 《高压电器》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109376626A (en) * | 2018-10-10 | 2019-02-22 | 国网陕西省电力公司电力科学研究院 | A kind of GIS switch defect diagnostic method based on radiated electric field characteristic parameter support vector machines |
CN110231553A (en) * | 2019-07-12 | 2019-09-13 | 电子科技大学 | A kind of motor slot insulation electric field impact appraisal procedure and assessment device |
CN110231553B (en) * | 2019-07-12 | 2024-04-09 | 电子科技大学 | Motor slot insulation electric field impact evaluation method and evaluation device |
CN111123087A (en) * | 2019-12-24 | 2020-05-08 | 深圳供电局有限公司 | Power distribution network switching equipment fault detection method and device and computer equipment |
CN111965504A (en) * | 2020-08-14 | 2020-11-20 | 广东电网有限责任公司电力科学研究院 | Method and device for evaluating typical insulation defects of GIS (gas insulated switchgear) |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108535618A (en) | A kind of GIS method for detecting insulation defect | |
Schichler et al. | Risk assessment on defects in GIS based on PD diagnostics | |
CN105425076A (en) | Method of carrying out transformer fault identification based on BP neural network algorithm | |
CN110703036B (en) | Clustering-based high-resistance grounding fault positioning method for resonant grounding system | |
CN205643609U (en) | Inside multiple partial discharge's of GIS analogue means | |
CN110133438A (en) | A kind of singlephase earth fault discrimination method based on phase space reconfiguration Yu conductance feature | |
CN204595107U (en) | A kind of GIS device galvanic circle contact condition analoging detecting device | |
CN106707094A (en) | Classification recognition method of arc fault of low voltage power supply and distribution line | |
CN108445363A (en) | A kind of city net cable insulation defect inspection method based on fringe field | |
CN112505484B (en) | Medium-voltage distribution cable latent fault identification method for small-resistance grounding system | |
Wang et al. | Measurement and analysis of partial discharges in SF6 gas under HVDC | |
CN106980051B (en) | A kind of intermittence tandem type fault electric arc recognition methods | |
CN107505539A (en) | A kind of distribution arc grounding fault identification method | |
CN109782126A (en) | Power distribution network incipient fault detection method based on class people's concept learning | |
CN103983890B (en) | Search method for fault points generated due to the influence of alternating current crosstalk on relay and test circuit | |
CN116148599B (en) | Kurtosis and skewness coefficient-based high-resistance ground fault diagnosis protection method and device | |
CN105589015B (en) | A kind of method for building up of cable oscillatory wave partial discharge detection failure criterion | |
CN111044810B (en) | Simulation test method for lightning stroke protection and wire breaking effect of ground fault processing device | |
CN110212503A (en) | A kind of high resistance earthing protecting method suitable for small resistance grounding system | |
CN109387731A (en) | A kind of high resistance earthing fault discrimination method based on wavelet analysis and amplitude com parison | |
CN110988634B (en) | Partial discharge detection system of high-voltage direct-current gas insulated switchgear | |
CN110991240B (en) | Single-phase fault identification and classification method for low-voltage neutral point ungrounded system | |
CN104316791A (en) | Reason analyzing and locating method for high resistance grounding fault of transmission line | |
Jieqiu et al. | Arc fault identification method based on fractal theory and SVM | |
Ma et al. | Fractal theory based pattern recognition of motor partial discharge |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |