CN108693448B - Partial discharge mode recognition system applied to power equipment - Google Patents
Partial discharge mode recognition system applied to power equipment Download PDFInfo
- Publication number
- CN108693448B CN108693448B CN201810261294.1A CN201810261294A CN108693448B CN 108693448 B CN108693448 B CN 108693448B CN 201810261294 A CN201810261294 A CN 201810261294A CN 108693448 B CN108693448 B CN 108693448B
- Authority
- CN
- China
- Prior art keywords
- discharge
- partial discharge
- spectrogram
- signal
- statistical characteristics
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
A partial discharge mode recognition system applied to power equipment comprises a signal preprocessing module for filtering and amplifying a sensor coupling signal; and then, the signals processed by the signal preprocessing module are collected, the data are transmitted to the data analysis module for analysis and processing, a partial discharge PRPD spectrogram and statistical characteristics are calculated, the statistical characteristics of the discharge spectrogram are input into an input layer of a BP network neural algorithm in groups to obtain different groups of discharge results, the discharge types are obtained comprehensively according to different assigned weights, and the pattern recognition accuracy of partial discharge is improved. The invention adopts high sampling rate and high pulse capture repetition rate, and can improve the accuracy and sensitivity of the system.
Description
Technical Field
The invention relates to the technical field of power equipment fault diagnosis, in particular to a partial discharge mode identification system applied to power equipment.
Background
Partial discharge occurs at certain weak parts in the electrical equipment under the action of high field intensity, and under certain conditions, the partial discharge can cause the deterioration, even breakdown and damage to life and property safety, so that the early defect or latent fault of the equipment can be timely found by carrying out live detection or online monitoring on the partial discharge of the equipment, and the method has very important significance for ensuring the safety and stability of the electrical equipment and an electric power system. Partial discharges caused by different types of defects may exist in the device, or pulse interference is included in the discharge signal, so that pattern recognition of the partial discharges is required to distinguish the harm degree of different discharge types.
Currently, the two most common detection methods for evaluating partial discharge signals are: the methods based on the phase distribution mode and the time distribution mode are classified into a phase statistical method, a time domain waveform method and a time domain waveform method, and the time domain waveform method comprises a frequency spectrum analysis method, a time frequency joint analysis method and the like. The identification and separation methods of the partial discharge signals are different with different detection methods (phase distribution or time distribution).
The method can detect the partial discharge signal of the cable, but has certain problems:
(1) partial discharge phase distribution statistics PRPD spectrogram
And the spectrogram is obtained by triggering continuous acquisition for 20ms by a power frequency signal and calculating after multiple acquisition, and the acquired data volume is large and the data analysis is slow in a high sampling rate mode.
(2) In the phase analysis of a spectrogram, the traditional statistical characteristics comprise skewness, steepness, peak number and the like, and the input weights of the statistical characteristics in a partial discharge classifier are consistent without primary and secondary scores.
Disclosure of Invention
Aiming at the defects of the existing power equipment partial discharge pattern recognition method, the invention aims to provide a power equipment partial discharge pattern recognition system which can be used for diagnosing partial discharge defects and evaluating risks of running power equipment and improving the pattern recognition accuracy of partial discharge.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a partial discharge mode recognition system applied to power equipment comprises a signal preprocessing module, a partial discharge acquisition module and a data analysis module; the signal preprocessing module is connected with an external sensor, digital filtering and amplification conditioning are carried out on signals coupled with the sensor, conditioned signals are collected by the partial discharge collection module, data are transmitted to the data analysis module, a partial discharge PRPD spectrogram and statistical characteristics are calculated, and a BP network neural algorithm is adopted to calculate the partial discharge type.
The signal preprocessing module is used for performing band-pass filtering and amplification on the signals coupled by the sensor, and the output end of the signal preprocessing module is used as the input end of the partial discharge acquisition module;
the partial discharge acquisition module comprises four-channel synchronous acquisition, internal power frequency signal output and internal and external power frequency signal switching functions, a partial discharge pulse signal is used as a trigger source, a preprocessed three-phase signal and a preprocessed power frequency signal are synchronously acquired, the acquisition rate is 250MS/s, the acquisition duration is 20us, after the preset times of continuous acquisition, data are returned once, and the minimum time interval between two acquisition is ensured and can reach the magnitude of several us;
the data analysis module processes and analyzes the collected partial discharge signal and power frequency signal, calculates the discharge capacity, discharge phase, PRPD and PRPS spectrogram of partial discharge, and further calculates the statistical characteristics of the spectrogram, including skewness Sk, steepness Ku, partial peak number Pe, asymmetry phi, cross correlation coefficient cc, Weibull parameter, and the normalized discharge capacity q of the discharge spectrogram+、q-And discharge phase center
And inputting the statistical characteristics of the discharge spectrogram into an input layer of a BP network neural algorithm in groups to obtain different groups of discharge results, and then synthesizing according to different distributed weights to obtain the discharge type.
The invention has the beneficial effects that:
(1) the system of the invention adopts a rapid frame technology, defines a partial discharge pulse segment as a frame, takes a partial discharge pulse signal as a trigger source, only collects the short time domain waveform of the pulse signal, continuously collects the set frame number and then displays the waveform at one time, and the rapid data frame technology can realize the continuous triggering, the high-speed collection and the small-capacity storage processing of the partial discharge pulse.
(2) According to the statistical characteristics of partial discharge, the partial discharge is divided into a plurality of combinations, the combinations are respectively input into a BP network neural algorithm, and then the output results are subjected to weighted synthesis, so that the pattern recognition accuracy of the partial discharge is improved.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
FIG. 2 is a flow chart of data analysis according to the present invention.
FIG. 3 is a graph of a suspension discharge spectrum.
Figure 4 is a corona discharge spectrum.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1, a partial discharge pattern recognition system applied to power equipment is characterized by comprising a signal preprocessing module, a partial discharge acquisition module and a data analysis module;
the signal preprocessing module is used for performing band-pass filtering and amplification on the signals coupled by the sensor, and the output end of the signal preprocessing module is used as the input end of the partial discharge acquisition module;
the partial discharge acquisition module comprises four-channel synchronous acquisition, internal power frequency signal output and internal and external power frequency signal switching functions, a partial discharge pulse signal is used as a trigger source, a preprocessed three-phase signal and a preprocessed power frequency signal are synchronously acquired, the acquisition rate is 250MS/s, the acquisition duration is 20us, after the preset times of continuous acquisition, data are returned once, and the minimum time interval between two acquisition is ensured and can reach the magnitude of several us;
the data analysis module processes and analyzes the collected partial discharge signal and power frequency signal, calculates the discharge capacity, discharge phase, PRPD and PRPS spectrogram of partial discharge, and further calculates the statistical characteristics of the spectrogram, including skewness Sk, steepness Ku, partial peak number Pe, asymmetry phi, cross correlation coefficient cc, Weibull parameter, and the normalized discharge capacity q of the discharge spectrogram+、q-Center of discharge phase
Inputting the statistical characteristics of the spectrogram into an input layer of a BP network neural algorithm in groups to obtain different discharge results, and then synthesizing according to different distributed weights to obtain discharge types;
example one
According to different detection equipment, different partial discharge sensors are adopted, for example, a high-voltage cable sensor adopts a high-frequency broadband electromagnetic sensor, the sensors are sleeved on a three-phase cable accessory grounding wire or a cross interconnection grounding wire, and a 50Hz power frequency voltage sensor is arranged on a body of the accessory and is used for coupling power frequency current signals; the sensor is connected with a signal preprocessing module, the preprocessing module carries out digital filtering and amplification conditioning on signals coupled with the sensor, a local discharge acquisition module acquires the conditioned signals, then data is transmitted to a data analysis module, spectrogram information such as local discharge parameters and PRPD (pulse-weighted sum) is calculated, and with reference to figures 3 and 4, statistical characteristics of spectrograms including skewness Sk, steepness Ku, local peak point number Pe, asymmetry phi, cross-correlation coefficient cc and Weibull+、q-Center of discharge phase
Inputting the statistical characteristics of the spectrogram into an input layer of a BP network neural algorithm in groups to obtain different groups of discharge results, and then synthesizing according to different distributed weights to obtain discharge types;
the signal preprocessing module performs hardware filtering and signal amplification on a sensor coupling signal to improve detection sensitivity, performs low-pass filtering on an interference signal above 30MHz, has the amplification factors of 1,2, 5, 10, 20, 50, 100 and 200 on a program control signal, and conditions the signal to the optimal input range of the partial discharge acquisition module.
The partial discharge acquisition module realizes the synchronous high-speed acquisition function of four channels, the three channels respectively correspond to three-phase cable signals coupled with the sensor, and the fourth channel acquires 50Hz power frequency sensor signals. The acquisition rate is 250MS/s, the acquisition time is 20us, the analog bandwidth is 60MHz, and the resolution is 14 bits. A rapid frame technology is adopted, a partial discharge pulse segment is defined as a frame, a partial discharge pulse signal is used as a trigger source, only a short time domain waveform of the pulse signal is collected, after a set number of frames are continuously collected, data stored in a Read Only Memory (ROM) of a collection card are returned once, the minimum time interval between two times of collection is ensured to be several us orders, and the rapid data frame technology can realize continuous triggering, high-speed collection and small-capacity storage processing of the partial discharge pulse. Meanwhile, the internal power frequency signal can be selected to be output according to the on-site requirement, namely the partial discharge module outputs a standard 50Hz power frequency signal to be connected to the fourth channel, or the standard power frequency signal with the same frequency and amplitude can be output by measuring a coupling signal of the 50Hz power frequency sensor, so that the coupled power frequency signal is replaced.
The data analysis module combines the embedded industrial personal computer and the virtual instrument technology, adopts Labview software to compile an operation interface, analyzes and displays data, calculates the spectrogram, the discharge capacity and the statistical characteristics of partial discharge, including skewness Sk, steepness Ku, the number Pe of partial peak points, asymmetry phi, cross correlation coefficient cc, Weibull parameters and the normalized discharge capacity q of the discharge spectrogram+、q-Center of discharge phase
Referring to fig. 2, the data analysis module includes the following steps:
step S10: partial discharge information calculates the discharge capacity, discharge phase,
Three-dimensional spectra, further subdivided into
I.e. average discharge-phase, and
namely a two-dimensional spectrogram of discharge times and phase;
step S20: computing
And
the statistical characteristics of the spectrogram include skewness Sk, steepness Ku, local peak number Pe,Asymmetry phi, cross correlation coefficient cc, Weibull parameter, discharge spectrum normalized discharge capacity q+、q-Center of discharge phase
Since the phase 0-360 ° can be divided into a positive cycle and a negative cycle, the statistical characteristics of the spectrogram are divided into: sk+And Sk-，Ku+And Ku-，Pe+And Pe-；
Step S30: the BP neural network is subjected to a large amount of sample learning and training, so that parameters such as weight, threshold value and the like of the network are optimized, when a new signal is output, the BP neural network classifies and identifies the new signal, statistical characteristics are divided into 10 groups, the statistical characteristics are input into the BP neural network algorithm in groups, and each group of characteristic input respectively obtains each group of identification results;
step S40: each group of identification results generally comprises all possible discharge types, and the discharge types are obtained through weighted integration, wherein the weighted integration method comprises the following steps:
1. statistical features of the spectrogram, comprising: sk+And Sk-，Ku+And Ku-，Pe+And Pe-20 groups of Weibull parameters and the like are input into a BP neural network algorithm to respectively obtain a judgment result;
2. the weight of each discrimination result is different and is divided into four weights, and the weights respectively correspond to coefficient scores which are 1,2,3 and 4 from small to large; the score of the final output type is determined by the product result of the weight corresponding coefficient and the weight times; taking the transformer internal discharge as an example, when the calculation results in each weight 1,2,3, 1, 4 and 0, the final result 1 x 2+2 x 3+3 x 1+4 x 0 is 11, and different scores correspond to the discharge types, the final result is output.
Claims (4)
1. A partial discharge mode recognition system applied to power equipment is characterized by comprising a signal preprocessing module, a partial discharge acquisition module and a data analysis module; the signal preprocessing module is connected with an external sensor, digital filtering and amplification conditioning are carried out on signals coupled with the sensor, conditioned signals are collected by the partial discharge collection module, data are transmitted to the data analysis module, a partial discharge PRPD spectrogram and statistical characteristics are calculated, and a BP network neural algorithm is adopted to calculate the partial discharge type;
the data analysis module comprises the following steps:
step S10: calculating discharge capacity, discharge phase and Q-phi-N three-dimensional spectrogram according to partial discharge information, and further dividing into QavgPhi is the average discharge amount-phase, and N-phi is the discharge number-phase two-dimensional spectrogram;
step S20: calculating QavgStatistical characteristics of-phi and N-phi spectrograms including skewness Sk, steepness Ku, local peak number Pe, asymmetry phi, cross correlation coefficient cc, Weibull parameter, normalized discharge capacity q of discharge spectrogram+、q-Discharge phase center phi+、φ-(ii) a Since the phase 0-360 ° can be divided into a positive cycle and a negative cycle, the statistical characteristics of the spectrogram are divided into: sk+And Sk-，Ku+And Ku-，Pe+And Pe-；
Step S30: the BP network neural algorithm is subjected to a large amount of sample learning and training, so that the weight and threshold parameters of the network per se are optimized, when a new signal is output, the BP network neural algorithm classifies and identifies the new signal, the statistical characteristics are divided into 10 groups, the statistical characteristics are input into the BP network neural algorithm in groups, and identification results of each group are respectively obtained;
step S40: each group of identification results generally comprises all possible discharge types, and the discharge types are obtained through weighted integration, wherein the weighted integration method comprises the following steps:
(1) statistical features of a spectrogram comprising: sk+And Sk-，Ku+And Ku-，Pe+And Pe-20 groups of Weibull parameters are input into a BP neural network algorithm in total to respectively obtain a judgment result;
(2) the weight of each discrimination result is different and is divided into four weights, and the weights respectively correspond to coefficient values which are 1,2,3 and 4 from small to large; the score of the final output type is determined by the product result of the weight corresponding coefficient and the weight times; taking the transformer internal discharge as an example, when the calculation results in each weight 1,2,3, 1, 4 and 0, the final result 1 x 2+2 x 3+3 x 1+4 x 0 is 11, and different scores correspond to the discharge types, the final result is output.
2. The system for identifying the partial discharge pattern of the power equipment as claimed in claim 1, wherein the signal preprocessing module is configured to band-pass filter and amplify the signal coupled by the sensor, and an output end of the signal preprocessing module is used as an input end of the partial discharge acquisition module.
3. The system of claim 1, wherein the partial discharge acquisition module comprises four-channel synchronous acquisition, internal power frequency signal output, and internal and external power frequency signal switching functions, and is configured to synchronously acquire the preprocessed three-phase signal and power frequency signal by using a partial discharge pulse signal as a trigger source, wherein the acquisition rate is 250MS/s, the acquisition duration is 20us, and after the set number of continuous acquisition, the data is returned once, so that the minimum time interval between two acquisition can be ensured, and can reach several us magnitude.
4. The system of claim 1, wherein the data analysis module processes and analyzes the collected partial discharge signal and power frequency signal, calculates the discharge amount, discharge phase, PRPD, and PRPS spectrogram of the partial discharge, and further calculates statistical characteristics of the spectrogram, including skewness Sk, steepness Ku, number of partial peaks Pe, asymmetry Φ, cross-correlation coefficient cc, weibull parameter, and normalized discharge amount q of the discharge spectrogram+、q-And discharge phase center phi+、φ-And inputting the statistical characteristics of the discharge spectrogram into an input layer of a BP network neural algorithm in groups to obtain different groups of discharge results, and then synthesizing according to different distributed weights to obtain the discharge type.
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 CN108693448A (en) | 2018-10-23 |
| CN108693448B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040087905A (en) * | 2003-04-09 | 2004-10-15 | 파이오니아 가부시키가이샤 | Plasma display panel |
-
2018
- 2018-03-28 CN CN201810261294.1A patent/CN108693448B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| 基于关联规则与变权重的变压器状态评估方法;谢荣斌 等;《高压电器》;20140131;第50卷(第1期);第133-138页 * |
| 融合集对分析和关联规则的变压器故障诊断方法;谢龙君 等;《中国电机工程学报》;20150120;第35卷(第2期);第277-286页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108693448A (en) | 2018-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108693448B (en) | Partial discharge mode recognition system applied to power equipment | |
| CN104198898B (en) | Local discharge development process diagnosis method based on pulse-train analysis | |
| Hao et al. | Partial discharge source discrimination using a support vector machine | |
| CN105044566B (en) | A kind of GIS partial discharge fault detection method of feature based ultra-high frequency signal | |
| Sharkawy et al. | Particle swarm optimization feature selection for the classification of conducting particles in transformer oil | |
| CN105548832A (en) | High-voltage power cable fault recognition method | |
| CN110108992B (en) | Cable partial discharge fault identification method and system based on improved random forest algorithm | |
| CN107942210A (en) | The classification of transformer pulse electric current Partial Discharge and denoising method and system | |
| CN109061426A (en) | Partial discharge of transformer method for diagnosing faults and on-Line Monitor Device | |
| CN114325256A (en) | Power equipment partial discharge identification method, system, equipment and storage medium | |
| Chang et al. | Application of fuzzy entropy to improve feature selection for defect recognition using support vector machine in high voltage cable joints | |
| CN113805018A (en) | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network | |
| CN112285494A (en) | Power cable partial discharge mode recognition analysis system | |
| CN115993511A (en) | Partial discharge type high-precision detection and identification device, method and equipment | |
| CN114755543A (en) | Power equipment partial discharge detection method and equipment | |
| CN104865508B (en) | The Recognition of Partial Discharge quantified based on packet | |
| CN117289067B (en) | Transformer running state on-line monitoring system | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| CN110197120B (en) | Personnel target identification method for unattended sensor system | |
| CN116008751A (en) | Sample enhancement-based cable partial discharge fault characteristic identification method | |
| Happe et al. | Advanced suppression of stochastic pulse shaped partial discharge disturbances | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| Jin et al. | Classification of partial discharge events in gas-insulated substations using wavelet packet transform and neural network approaches | |
| Chang et al. | Partial discharge pattern recognition for underground cable joints using convolutional neural network | |
| Sinaga et al. | Neuro fuzzy recognition of ultra-high frequency partial discharges in transformers |
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 |