CN108693448A - One kind being applied to power equipment PD Pattern Recognition system - Google Patents
One kind being applied to power equipment PD Pattern Recognition system Download PDFInfo
- Publication number
- CN108693448A CN108693448A CN201810261294.1A CN201810261294A CN108693448A CN 108693448 A CN108693448 A CN 108693448A CN 201810261294 A CN201810261294 A CN 201810261294A CN 108693448 A CN108693448 A CN 108693448A
- Authority
- CN
- China
- Prior art keywords
- discharge
- signal
- result
- acquisition
- statistical nature
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Relating To Insulation (AREA)
Abstract
One kind being applied to power equipment PD Pattern Recognition system, includes being filtered to sensor coupled signal and the signal pre-processing module of enlarging function;By signal pre-processing module, treated that signal is acquired again, then it passes data to data analysis module and carries out analyzing processing, calculate shelf depreciation PRPD spectrograms and statistical nature, the statistical nature grouping of discharge spectrum is input to the input layer of BP network neural algorithms, obtain different groups of electric discharge result, electric discharge type is obtained further according to the different weights synthesis of distribution, improves the pattern-recognition accuracy of shelf depreciation.The present invention uses high sampling rate and high pulse capture repetitive rate, can improve the accuracy and sensitivity of system.
Description
Technical field
The present invention relates to Fault Diagnosis for Electrical Equipment technical fields, and in particular to is locally put applied to power equipment to one kind
Power mode identifying system.
Background technology
Under high field intensity effect shelf depreciation will occur for certain weak parts in electrical equipment, under certain condition, part
Electric discharge can lead to the deterioration of insulation, or even breakdown, life threatening property safety, therefore the band electric-examination of shelf depreciation is carried out to equipment
Survey or on-line monitoring can discovering device in time early defect or Hidden fault, for ensureing electrical equipment and electric system
It is safe and stable to have a very important significance.There may be the shelf depreciation caused by different types of defect inside equipment,
Or it is mingled with impulse disturbances in discharge signal, this just needs to carry out pattern-recognition to shelf depreciation, to distinguish different put
The extent of injury of electric type.
Being presently used for two kinds of most common detection methods of assessment local discharge signal is respectively:Based on phase distribution mould
Formula and and be based on Annual distribution pattern, that is, being divided into phase statistic law, time domain waveform method, time domain waveform method has including Spectral Analysis Method
With time-frequency combination analytic approach etc..Using different detection methods (phase distribution or Annual distribution), the knowledge of local discharge signal
It is not also differed with separation method.
Above method is capable of the local discharge signal of detection cable, but exists simultaneously certain problem:
(1) shelf depreciation phase distribution statistics PRPD spectrograms areSpectrogram is to trigger continuous acquisition with power frequency component
Spectrogram is calculated later in 20ms, multi collect, and gathered data amount is larger under high sampling rate pattern, and data analysis is slower.
(2) in the phase analysis of spectrogram, traditional statistical nature includes degree of skewness, steepness, peak number etc., and statistical nature exists
Input weight is consistent in shelf depreciation grader, without point of primary and secondary.
Invention content
For the defect of existing power equipment Partial Discharge Pattern Recognition Method, the purpose of the present invention is to provide one kind
Applied to power equipment PD Pattern Recognition system, the power equipment of operation can be carried out shelf depreciation defect diagonsis and
Risk assessment improves the pattern-recognition accuracy of shelf depreciation.
To achieve the goals above, technical scheme is as follows:
One kind being applied to power equipment PD Pattern Recognition system, including signal pre-processing module, shelf depreciation are adopted
Collect module and data analysis module;The signal pre-processing module connects external sensor, to the signal of sensor coupling into
After row digital filtering and amplification conditioning, then by the signal after partial discharge collection module acquisition conditioning, then by data transmission in number
According to analysis module, calculates shelf depreciation PRPD spectrograms and statistical nature calculates shelf depreciation class using BP network neural algorithms
Type.
The signal pre-processing module carries out bandpass filtering and amplification to the signal of sensor coupling, and output end is made
For the input terminal of partial discharge collection module;
The partial discharge collection module, including four-way synchronous acquisition, the output of internal power frequency component and it is internal and
External power frequency component handoff functionality, using partial discharge pulse's signal as trigger source, synchronous acquisition is believed by pretreated three
Number and power frequency component, acquisition rate 250MS/s, acquire duration 20us, continuous acquisition set number after, then by data one
Secondary property returns, and ensures that acquisition time interval is minimum twice, up to a few us magnitudes;
The data analysis module is handled and is analyzed to the local discharge signal and power frequency component of acquisition, is calculated
The discharge capacity, discharge phase, PRPD, PRPS spectrogram for obtaining shelf depreciation, further calculate the statistical nature of spectrogram, including deflection
Spend Sk, steepness Ku, local peaks points Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalizing of discharge spectrum
Change discharge capacity q+,q-With discharge phase centerThe statistical nature grouping of discharge spectrum is input to BP network neurals
The input layer of algorithm obtains different groups of electric discharge as a result, the different weights synthesis further according to distribution obtains electric discharge type.
Beneficial effects of the present invention are:
(1) present system uses quick frame technique, and partial discharge pulse's segment is defined as a frame, is put with part
Electric impulse signal is as trigger source, only acquisition pulse signal domain waveform in short-term, and continuous acquisition is set after frame number disposably by waveform
It has been shown that, rapid data frame technique can realize the continuous trigger of partial discharge pulse, high speed acquisition and low capacity storage processing.
(2) according to the statistical property of shelf depreciation, it is divided into multiple combinations, inputs BP network neural algorithms respectively, then to defeated
The result gone out is weighted synthesis, improves the pattern-recognition accuracy of shelf depreciation.
Description of the drawings
Fig. 1 is the structural diagram of the present invention.
Fig. 2 is the data analysis flowcharts of the present invention.
Fig. 3 is suspended discharge spectrogram.
Fig. 4 is corona discharge spectrogram.
Specific implementation mode
Below in conjunction with the accompanying drawings and specific embodiment the present invention is further described in more detail.
Referring to Fig.1, a kind of to be applied to power equipment PD Pattern Recognition system, which is characterized in that it includes signal
Preprocessing module, partial discharge collection module, data analysis module;
The signal pre-processing module carries out bandpass filtering and amplification to the signal of sensor coupling, and output end is made
For the input terminal of partial discharge collection module;
The partial discharge collection module, including four-way synchronous acquisition, the output of internal power frequency component and it is internal and
External power frequency component handoff functionality, using partial discharge pulse's signal as trigger source, synchronous acquisition is believed by pretreated three
Number and power frequency component, acquisition rate 250MS/s, acquire duration 20us, continuous acquisition set number after, then by data one
Secondary property returns, and ensures that acquisition time interval is minimum twice, up to a few us magnitudes;
The data analysis module is handled and is analyzed to the local discharge signal and power frequency component of acquisition, is calculated
The discharge capacity, discharge phase, PRPD, PRPS spectrogram for obtaining shelf depreciation, further calculate the statistical nature of spectrogram, including deflection
Spend Sk, steepness Ku, local peaks points Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalizing of discharge spectrum
Change discharge capacity q+,q-, discharge phase centerThe statistical nature grouping of spectrogram is input to the defeated of BP network neural algorithms
Enter layer, obtains different electric discharges as a result, the different weights synthesis further according to distribution obtains electric discharge type;
Embodiment one
According to different detection devices, using different local discharge sensors, such as high-tension cable sensor is to use
High-frequency wideband electromagnetic sensor, sensor sleeve are connected on threephase cable attachment ground wire or cross connection grounding line, 50Hz power frequencies
Voltage sensor is installed on the ontology of attachment for coupling power frequency current signal;The Signal Pretreatment mould of sensor and the present invention
Block connects, and after preprocessing module carries out digital filtering and amplification conditioning to the signal that sensor couples, mould is acquired by shelf depreciation
Signal after block acquisition conditioning, then data transmission is calculated into the spectrograms such as shelf depreciation parameter and PRPD letter in data analysis module
Breath further calculates out the statistical nature of spectrogram with reference to Fig. 3, Fig. 4, including degree of skewness Sk, steepness Ku, local peaks points Pe,
Degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalization discharge capacity q of discharge spectrum+,q-, discharge phase centerThe statistical nature grouping of spectrogram is input to the input layers of BP network neural algorithms, obtain different groups of electric discharge as a result,
Electric discharge type is obtained further according to the different weights synthesis of distribution;
1. the signal pre-processing module carries out hardware filtering to sensor coupled signal and signal amplifies, to improve
Detection sensitivity, in the interference signal of 30MHz or more, program control signal has 1,2,5,10,20,50,100,200 to be put low-pass filtering
Big multiple, will be in signal condition to partial discharge collection module optimal input range.
2. the partial discharge collection module realizes that four-way synchronous high-speed acquires function, triple channel is corresponding respectively to be passed
The threephase cable signal of sensor coupling, fourth lane acquire 50Hz power frequency sensor signals.Acquisition rate is 250MS/s, acquisition
Duration 20us, analog bandwidth 60MHz, resolution ratio are 14.Using quick frame technique, by partial discharge pulse's segment definition
For a frame, using partial discharge pulse's signal as trigger source, only domain waveform, continuous acquisition set frame number to acquisition pulse signal in short-term
Afterwards, it will be disposably stored in the return of capture card ROM data, ensure that acquisition time interval is minimum twice, up to a few us magnitudes, quickly
Data frame technique can realize the continuous trigger of partial discharge pulse, high speed acquisition and low capacity storage processing.It simultaneously can be according to existing
Field needs that interior power frequency component output, i.e. the 50Hz power frequency components of shelf depreciation module outputting standard is selected to be connected to fourth lane,
Or the standard normal signal of same frequency and amplitude can be exported by measuring 50Hz power frequency sensor coupled signals, to replace coupling
Power frequency component.
3. the data analysis module is compiled in conjunction with built-in industrial control machine and virtual instrument technique using Labview softwares
Write operation interface, data analysis and display, calculate the spectrogram, discharge capacity and statistical nature of shelf depreciation, including degree of skewness Sk, steep
Kurtosis Ku, local peaks points Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalization discharge capacity of discharge spectrum
q+,q-, discharge phase center
With reference to Fig. 2, the data analysis module comprising following steps:
Step S10:Shelf depreciation information calculate discharge capacity, discharge phase,Three-dimensional spectrum can further be divided intoI.e. mean discharge magnitude-phase andThat is discharge time-phase two dimension spectrogram;
Step S20:It calculatesWithThe statistical nature of spectrogram, including degree of skewness Sk, steepness Ku, local peaks
Points Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalization discharge capacity q of discharge spectrum+,q-, discharge phase
CenterSince 0-360 ° of phase can be divided into positive period and negative cycle, the statistical nature of spectrogram be divided into for:Sk+
And Sk-, Ku+And Ku-, Pe+And Pe-;
Step S30:BP neural network learns by great amount of samples and training so that the ginsengs such as weights, threshold value of network itself
Being optimal of number, when exporting new signal, BP network neurals are classified and are identified to it, and statistical nature is divided into 10 groups,
Grouping is input to BP network neural algorithms, and the input of each group feature obtains each group recognition result respectively;
Step S40:All possible electric discharge type can be generally contained in each group recognition result, weighted comprehensive obtains electric discharge
The method of type, weighted comprehensive is as follows:
1. the statistical nature of spectrogram, including:Sk+And Sk-, Ku+And Ku-, Pe+And Pe-, total 20 groups of Weibull parameter etc. is defeated
Enter to BP neural network algorithm, respectively obtains differentiation result;
2. each differentiates that the weight of result is different, it is divided into four kinds of weights, coefficient of correspondence score value is divided into from small to large respectively
1,2,3,4;The score value of final output type is determined by weight coefficient of correspondence and weight number result of product;It is put with inside transformer
For electricity, when 1 result of each weight being calculated 2 times, 2 result of weight 3 times, 3 result of weight 1 time, 4 result of weight 0 time most terminates
Fruit 1*2+2*3+3*1+4*0=11, different scores correspond to electric discharge type, to export final result.
Claims (5)
1. one kind being applied to power equipment PD Pattern Recognition system, which is characterized in that including signal pre-processing module, office
Discharge acquisition module and data analysis module in portion;The signal pre-processing module connects external sensor, is coupled to sensor
Signal carry out digital filtering and amplification conditioning after, then by the signal after partial discharge collection module acquisition conditioning, then by data
It is transmitted in data analysis module, calculates shelf depreciation PRPD spectrograms and statistical nature, using BP network neural algorithms, is calculated out
Portion's electric discharge type.
2. according to claim 1 a kind of applied to power equipment PD Pattern Recognition system, which is characterized in that institute
The signal pre-processing module stated carries out bandpass filtering and amplification to the signal of sensor coupling, and output end is as shelf depreciation
The input terminal of acquisition module.
3. according to claim 1 a kind of applied to power equipment PD Pattern Recognition system, which is characterized in that institute
The partial discharge collection module stated, including four-way synchronous acquisition, internal power frequency component output and inside and outside power frequency letter
Number handoff functionality, using partial discharge pulse's signal as trigger source, synchronous acquisition passes through pretreated three-phase signal and power frequency
Signal, acquisition rate 250MS/s acquire duration 20us and then disposably return to data after continuous acquisition sets number,
Ensure that acquisition time interval is minimum twice, up to a few us magnitudes.
4. according to claim 1 a kind of applied to power equipment PD Pattern Recognition system, which is characterized in that institute
The data analysis module stated is handled and is analyzed to the local discharge signal and power frequency component of acquisition, and part is calculated and puts
Discharge capacity, discharge phase, PRPD, PRPS spectrogram of electricity, further calculate the statistical nature of spectrogram, including degree of skewness Sk, precipitous
Spend Ku, local peaks points Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalization discharge capacity q of discharge spectrum+,q-With discharge phase centerThe statistical nature grouping of discharge spectrum is input to the input of BP network neural algorithms
Layer obtains different groups of electric discharge as a result, the different weights synthesis further according to distribution obtains electric discharge type.
5. according to claim 1 or 4 a kind of applied to power equipment PD Pattern Recognition system, feature exists
In the data analysis module comprising following steps:
Step S10:Shelf depreciation information calculate discharge capacity, discharge phase,Three-dimensional spectrum can further be divided intoI.e. mean discharge magnitude-phase andThat is discharge time-phase two dimension spectrogram;
Step S20:It calculatesWithThe statistical nature of spectrogram, including degree of skewness Sk, steepness Ku, local peaks points
Pe, degree of asymmetry Φ, cross-correlation coefficient cc, Weibull parameter, the normalization discharge capacity q of discharge spectrum+,q-, discharge phase centerSince 0-360 ° of phase can be divided into positive period and negative cycle, the statistical nature of spectrogram be divided into for:Sk+With
Sk-, Ku+And Ku-, Pe+And Pe-;
Step S30:BP neural network learns by great amount of samples and training so that the parameters such as weights, threshold value of network itself reach
To optimization, when exporting new signal, BP network neurals are classified and are identified to it, and statistical nature is divided into 10 groups, grouping
BP network neural algorithms are input to, the input of each group feature obtains each group recognition result respectively;
Step S40:All possible electric discharge type can be generally contained in each group recognition result, weighted comprehensive obtains electric discharge class
The method of type, weighted comprehensive is as follows:
(1) statistical nature of spectrograms, including:Sk+And Sk-, Ku+And Ku-, Pe+And Pe-, Weibull parameter etc. amounts to 20 groups of inputs
To BP neural network algorithm, differentiation result is respectively obtained;
(2) weight of each differentiation result of is different, is divided into four kinds of weights, and coefficient of correspondence score value is divided into 1 from small to large respectively,
2,3,4;The score value of final output type is determined by weight coefficient of correspondence and weight number result of product;It is discharged with inside transformer
For, when 1 result of each weight being calculated 2 times, 2 result of weight 3 times, 3 result of weight 1 time, 4 result of weight 0 time, final result
1*2+2*3+3*1+4*0=11, different scores correspond to electric discharge type, to export final result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810261294.1A CN108693448B (en) | 2018-03-28 | 2018-03-28 | Partial discharge mode recognition system applied to power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810261294.1A CN108693448B (en) | 2018-03-28 | 2018-03-28 | Partial discharge mode recognition system applied to power equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108693448A true CN108693448A (en) | 2018-10-23 |
| CN108693448B CN108693448B (en) | 2020-11-13 |
Family
ID=63844334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810261294.1A Active CN108693448B (en) | 2018-03-28 | 2018-03-28 | Partial discharge mode recognition system applied to power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108693448B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109100627A (en) * | 2018-10-31 | 2018-12-28 | 红相股份有限公司 | A kind of power equipment partial discharges fault diagnostic method based on end-to-end mode |
| CN110672988A (en) * | 2019-08-29 | 2020-01-10 | 国网江西省电力有限公司电力科学研究院 | Partial discharge mode identification method based on hierarchical diagnosis |
| CN111537850A (en) * | 2020-05-21 | 2020-08-14 | 北京传动联普科技有限公司 | Big data identification management system for intelligent separation and classification diagnosis of partial discharge signals |
| CN111999382A (en) * | 2020-09-17 | 2020-11-27 | 海南电网有限责任公司电力科学研究院 | Cable partial discharge characteristic parameter extraction method considering insulation aging |
| CN113064032A (en) * | 2021-03-26 | 2021-07-02 | 云南电网有限责任公司电力科学研究院 | Partial discharge mode identification method based on map features and information fusion |
| CN114325256A (en) * | 2021-11-25 | 2022-04-12 | 中国电力科学研究院有限公司 | Power equipment partial discharge identification method, system, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040189199A1 (en) * | 2003-02-09 | 2004-09-30 | Pioneer Corporation | Plasma display panel |
| CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
| CN103077402A (en) * | 2012-12-28 | 2013-05-01 | 湖北省电力公司电力科学研究院 | Transformer partial-discharging mode recognition method based on singular value decomposition algorithm |
| CN103218662A (en) * | 2013-04-16 | 2013-07-24 | 郑州航空工业管理学院 | Transformer fault diagnosis method based on back propagation (BP) neural network |
| CN103777123A (en) * | 2014-01-27 | 2014-05-07 | 国家电网公司 | Partial discharge fault comprehensive diagnosis method for GIS device |
| CN104407270A (en) * | 2014-12-04 | 2015-03-11 | 国家电网公司 | Online fault monitoring device for cable connector in 10-35kV power distribution network and method for evaluating system state |
| CN106124939A (en) * | 2016-06-12 | 2016-11-16 | 西安博源电气有限公司 | Distributed high tension cable partial discharge monitoring and alignment system |
| CN106503689A (en) * | 2016-11-14 | 2017-03-15 | 哈尔滨理工大学 | Neutral net local discharge signal mode identification method based on particle cluster algorithm |
-
2018
- 2018-03-28 CN CN201810261294.1A patent/CN108693448B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040189199A1 (en) * | 2003-02-09 | 2004-09-30 | Pioneer Corporation | Plasma display panel |
| CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
| CN103077402A (en) * | 2012-12-28 | 2013-05-01 | 湖北省电力公司电力科学研究院 | Transformer partial-discharging mode recognition method based on singular value decomposition algorithm |
| CN103218662A (en) * | 2013-04-16 | 2013-07-24 | 郑州航空工业管理学院 | Transformer fault diagnosis method based on back propagation (BP) neural network |
| CN103777123A (en) * | 2014-01-27 | 2014-05-07 | 国家电网公司 | Partial discharge fault comprehensive diagnosis method for GIS device |
| CN104407270A (en) * | 2014-12-04 | 2015-03-11 | 国家电网公司 | Online fault monitoring device for cable connector in 10-35kV power distribution network and method for evaluating system state |
| CN106124939A (en) * | 2016-06-12 | 2016-11-16 | 西安博源电气有限公司 | Distributed high tension cable partial discharge monitoring and alignment system |
| CN106503689A (en) * | 2016-11-14 | 2017-03-15 | 哈尔滨理工大学 | Neutral net local discharge signal mode identification method based on particle cluster algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 谢荣斌 等: "基于关联规则与变权重的变压器状态评估方法", 《高压电器》 * |
| 谢龙君 等: "融合集对分析和关联规则的变压器故障诊断方法", 《中国电机工程学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109100627A (en) * | 2018-10-31 | 2018-12-28 | 红相股份有限公司 | A kind of power equipment partial discharges fault diagnostic method based on end-to-end mode |
| CN110672988A (en) * | 2019-08-29 | 2020-01-10 | 国网江西省电力有限公司电力科学研究院 | Partial discharge mode identification method based on hierarchical diagnosis |
| CN111537850A (en) * | 2020-05-21 | 2020-08-14 | 北京传动联普科技有限公司 | Big data identification management system for intelligent separation and classification diagnosis of partial discharge signals |
| CN111537850B (en) * | 2020-05-21 | 2022-05-27 | 北京传动联普科技有限公司 | Big data identification management system for intelligent separation and classification diagnosis of partial discharge signals |
| CN111999382A (en) * | 2020-09-17 | 2020-11-27 | 海南电网有限责任公司电力科学研究院 | Cable partial discharge characteristic parameter extraction method considering insulation aging |
| CN113064032A (en) * | 2021-03-26 | 2021-07-02 | 云南电网有限责任公司电力科学研究院 | Partial discharge mode identification method based on map features and information fusion |
| CN113064032B (en) * | 2021-03-26 | 2022-08-02 | 云南电网有限责任公司电力科学研究院 | Partial discharge mode identification method based on map features and information fusion |
| CN114325256A (en) * | 2021-11-25 | 2022-04-12 | 中国电力科学研究院有限公司 | Power equipment partial discharge identification method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108693448B (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108693448A (en) | One kind being applied to power equipment PD Pattern Recognition system | |
| CN106124939A (en) | Distributed high tension cable partial discharge monitoring and alignment system | |
| CN105044566B (en) | A kind of GIS partial discharge fault detection method of feature based ultra-high frequency signal | |
| Contin et al. | Classification and separation of partial discharge signals by means of their auto-correlation function evaluation | |
| Yoshida et al. | Evaluation of UHF method for partial discharge measurement by simultaneous observation of UHF signal and current pulse waveforms | |
| WO2015024825A1 (en) | Diagnostic method for automatic discrimination of phase-to-ground partial discharge, phase-to-phase partial discharge and electromagnetic noise | |
| CN109298300A (en) | One kind being used for part discharge test system and method when high-tension cable pressure test | |
| CN107942210A (en) | The classification of transformer pulse electric current Partial Discharge and denoising method and system | |
| KR20140120331A (en) | System for analyzing and locating partial discharges | |
| CN102792173A (en) | Instrument and method for detecting partial electrical discharges | |
| CN102792174B (en) | Instrument and method for detecting partial electrical discharges | |
| Romano et al. | Partial discharges at different voltage waveshapes: Comparison between two different acquisition systems | |
| CN104865508B (en) | The Recognition of Partial Discharge quantified based on packet | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| Madariaga et al. | Partial discharge electrical tree growth identification by means of waveform source separation techniques | |
| CN116280628A (en) | Partial discharge test method for high-voltage power equipment withstand voltage test | |
| Olkhovskiy et al. | Impulse signals classification using one dimensional convolutional neural network | |
| CN115758112A (en) | Online identification method for transient disturbance of electric power | |
| Happe et al. | Advanced suppression of stochastic pulse shaped partial discharge disturbances | |
| Thirumala et al. | A generalized empirical wavelet transform for classification of power quality disturbances | |
| Ren et al. | The study of partial discharge in GIS under impulse voltage based on time-frequency analysis | |
| Yuan et al. | Lab investigation of PD development in transformer winding | |
| Lu et al. | Statistical Analysis and Discharge Type Identification of Partial Discharge Pulse Parameters of Oil-Paper Insulation Based on Ultra-wideband | |
| Sun et al. | GIS discharge fault diagnosis based on wavelet packet singular spectral entropy and WOA-SVM | |
| CN112345891A (en) | Fault arc detection method based on current multichannel time-frequency feature extraction |
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 |