CN113325281A - Method and system for identifying each development stage of GIS insulation defect partial discharge - Google Patents
Method and system for identifying each development stage of GIS insulation defect partial discharge Download PDFInfo
- Publication number
- CN113325281A CN113325281A CN202110580942.1A CN202110580942A CN113325281A CN 113325281 A CN113325281 A CN 113325281A CN 202110580942 A CN202110580942 A CN 202110580942A CN 113325281 A CN113325281 A CN 113325281A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- metal particle
- gis
- insulator
- defect model
- 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
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
- G01R31/1245—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 line insulators or spacers, e.g. ceramic overhead line cap insulators; of insulators in HV bushings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical & Material Sciences (AREA)
- Ceramic Engineering (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a method and a system for identifying each development stage of GIS insulation defect partial discharge, wherein the method comprises the following steps: obtaining an insulator metal particle defect model; acquiring characteristic parameters under different voltage gradients based on the insulator metal particle defect model; the characteristic parameters comprise a maximum amplitude of partial discharge, a partial discharge phase width, partial discharge times and a partial discharge phase resolution spectrogram pulse point location distribution condition; adopting a K-Means clustering algorithm, and carrying out clustering algorithm analysis by taking the obtained characteristic parameters as samples to obtain a clustering result; and performing characterization and identification of each development stage of partial discharge based on the clustering result. The invention provides a method for identifying the partial discharge development stage of a GIS insulation defect based on a K-Means clustering algorithm, which provides a systematic and effective basis for judging the partial discharge development condition.
Description
Technical Field
The invention belongs to the technical field of electric power, relates to the field of partial discharge development stage judgment, and particularly relates to a method and a system for identifying each development stage of GIS insulation defect partial discharge.
Background
When the electric field unevenness in a Gas Insulated Switchgear (GIS) is high, the inside SF thereof6The dielectric strength of the gas is severely reduced, which is very likely to cause discharge. According to a large number of GIS fault cases in recent years, the reason that most faults are caused by internal electric field distortion due to metal particles remaining in a GIS shell is discovered, the faults gradually evolve into insulation breakdown under the action of a period of time, so that the development stages of GIS insulation defect partial discharge are not clearly defined, and the early discharge and the slow evolution process of the GIS insulation defect partial discharge are difficult to monitor, so that the identification of the characteristics of the development stages of the GIS insulator metal particle defect partial discharge is particularly important.
In recent years, some studies conducted at home and abroad on partial discharge induced by metal particles on the surface of an insulator in GIS equipment have shown that, the partial discharge development phenomenon presents three main stages of corona discharge, coexistence of corona discharge and along-surface streamer discharge, but a large amount of experimental data is not used for supporting, and the GIS insulation defect partial discharge development to flashover breakdown process is considered to have a 0-1 phenomenon, namely, when the external construction frequency voltage is lower than the breakdown voltage, the local discharge amount induced by the defects is extremely small and slowly increases to present a state of '0', however, when the applied voltage approaches the breakdown voltage, the partial discharge amount suddenly increases and the penetrating discharge immediately occurs, and the state "1" is assumed, but this point still lacks sufficient experimental basis, therefore, it is important to find a method for identifying the GIS insulation defect partial discharge development stage based on full and complete system.
Disclosure of Invention
The invention aims to provide a method and a system for identifying each development stage of GIS insulation defect partial discharge, and aims to solve the technical problems that in the prior art, the criterion of the GIS insulation defect partial discharge development stage is insufficient, and the past experience is over-dependent. The invention provides a method for identifying the partial discharge development stage of a GIS insulation defect based on a K-Means clustering algorithm, which provides a systematic and effective basis for judging the partial discharge development condition.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention discloses a method for identifying each development stage of GIS insulation defect partial discharge, which comprises the following steps:
obtaining an insulator metal particle defect model;
acquiring characteristic parameters under different voltage gradients based on the insulator metal particle defect model; the characteristic parameters comprise a maximum amplitude of partial discharge, a partial discharge phase width, partial discharge times and a partial discharge phase resolution spectrogram pulse point location distribution condition;
adopting a K-Means clustering algorithm, and carrying out clustering algorithm analysis by taking the obtained characteristic parameters as samples to obtain a clustering result; and performing characterization and identification of each development stage of partial discharge based on the clustering result.
The invention has the further improvement that the step of obtaining the insulator metal particle defect model specifically comprises the following steps:
according to the GIS operation condition, a simulation experiment platform is built;
and constructing and obtaining an insulator metal particle defect model based on the simulation experiment platform and the condition of the metal particle defects in the GIS.
The invention is further improved in that the step of building a simulation experiment platform according to the GIS operation condition specifically comprises the following steps:
constructing and obtaining a sealed GIS test cavity according to an actual GIS cavity structure and an operation working condition; placing the basin-type insulator in a GIS test cavity; the GIS test cavity is filled with SF6A gas;
an armored power frequency experiment transformer is used as a voltage source of the simulation experiment platform; setting a coupling resistor, an impedance box and a pulse current detection device; the coupling resistor is used for coupling pulse current flowing through the GIS test cavity, and the impedance box is used for detecting pulse current signals; the pulse current detection device is used for receiving a pulse current signal.
A further improvement of the present invention is that the pulse current detection device includes: a Rogowski coil; the Rogowski coil is arranged on a grounding wire of the GIS test cavity.
The further improvement of the invention is that the step of constructing and obtaining the insulator metal particle defect model based on the simulation experiment platform and the condition of the metal particle defect in the GIS specifically comprises the following steps:
the electrodes of the basin-type insulator are made of aluminum oxide, and the insulating part is made of epoxy resin material; the surface of the basin-type insulator is fixedly provided with aluminum linear metal particles for simulating the defects of the metal particles attached to the surface of the insulator.
The further improvement of the present invention is that the step of obtaining the characteristic parameters under different voltage gradients based on the insulator metal particle defect model specifically comprises:
obtaining partial discharge signals and phase resolution spectrograms of the insulator metal particle defect model under different voltage gradients through a pressurization test;
and extracting characteristic parameters under different voltage gradients from the phase resolution spectrogram.
The invention has the further improvement that the step of obtaining the partial discharge signal and the phase resolution spectrogram of the insulator metal particle defect model under different voltage gradients through the pressurization test specifically comprises the following steps:
pressurizing the insulator metal particle defect model by a step boosting method; firstly, boosting the voltage from zero to a partial discharge starting voltage, maintaining the partial discharge starting voltage constant until the insulator metal particle defect model is stably discharged and the spectrogram does not change any more, stopping boosting and detecting the partial discharge phase resolution spectrogram at the moment; then boosting the voltage until the partial discharge phase resolution spectrogram of the insulator metal particle defect model changes, keeping the voltage unchanged, and detecting the partial discharge phase resolution spectrogram at the moment; and repeating the detection of the partial discharge phase resolution spectrogram until the voltage applied to the insulator metal particle defect model reaches the flashover voltage, and finishing the detection.
The invention has the further improvement that the K-Means clustering algorithm is adopted, and the obtained characteristic parameters are taken as samples to carry out clustering algorithm analysis to obtain clustering results; the steps of characterizing and identifying each development stage of partial discharge based on the clustering result specifically comprise:
randomly selecting k points in a sample data set consisting of characteristic parameters as initial clustering centers, dividing the sample data set into k clusters according to the distance between the remaining points and each clustering center, and finishing clustering when the sample points in the clusters are not changed any more through continuous iteration to obtain clustering results; and dividing the partial discharge development process of the defect model into k stages according to the clustering result.
The invention discloses a system for identifying each development stage of GIS insulation defect partial discharge, which comprises the following steps:
the model obtaining module is used for obtaining an insulator metal particle defect model;
the characteristic parameter acquisition module is used for acquiring characteristic parameters under different voltage gradients according to the insulator metal particle defect model; the characteristic parameters comprise a maximum amplitude of partial discharge, a partial discharge phase width, partial discharge times and a partial discharge phase resolution spectrogram pulse point location distribution condition;
the clustering identification module is used for analyzing the clustering algorithm by using the acquired characteristic parameters as samples by adopting a K-Means clustering algorithm to obtain a clustering result; and performing characterization and identification of each development stage of partial discharge based on the clustering result.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, by utilizing the characteristic that clustering can be performed on any shape sample space in a clustering algorithm to converge on the global clustering, the local discharge process of GIS insulation defects is clustered and divided based on characteristic parameter samples, and stage identification is performed through clustering results; compared with the prior identification method, the method disclosed by the invention is simple and intuitive, has high accuracy and has better robustness.
In the method, a large amount of spectrogram data of each phase of partial discharge of the GIS insulation defect between the external construction frequency voltage and the breakdown voltage are collected for cluster analysis, and the partial discharge process of the GIS insulation defect is clustered and divided on the basis of spectrogram theory, so that the problem of deficient judgment sample is solved.
The system of the invention utilizes the running environment simulating the GIS working condition and identifies the partial discharge development stage of the GIS typical insulation defect through the clustering algorithm, can clearly divide the development process of the partial discharge and can control the discharge characteristics of each development stage; the method can better solve the problems of unclear food mixing in the development stage, insufficient safety evaluation criterion and the like in the process from the beginning to flashover breakdown of the GIS typical insulation defect partial discharge.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art are briefly introduced below; it is obvious that the drawings in the following description are some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic flow chart of a GIS insulation defect partial discharge development stage identification method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a GIS basin insulator metal particle defect model in an embodiment of the present invention;
FIG. 3 is a schematic flow chart of spectrogram recognition by using a K-Means clustering algorithm in the embodiment of the present invention;
FIG. 4 is a graph of the result of the discharge stage division by the K-Means clustering algorithm in the embodiment of the present invention;
FIG. 5 is a schematic diagram of a learning curve of the clustering classification quantity derived by the K-Means clustering algorithm in the embodiment of the present invention;
in the figure, 1, a linear metal particle defect; 2. a basin-type insulator.
Detailed Description
In order to make the purpose, technical effect and technical solution of the embodiments of the present invention clearer, the following clearly and completely describes the technical solution of the embodiments of the present invention with reference to the drawings in the embodiments of the present invention; it is to be understood that the described embodiments are only some of the embodiments of the present invention. Other embodiments, which can be derived by one of ordinary skill in the art from the disclosed embodiments without inventive faculty, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides a method for identifying a partial discharge development stage of a metal particle defect of a GIS insulator, which solves the problems of insufficient criterion and excessive dependence on past experience in the partial discharge development stage of a GIS insulation defect in the prior art, and provides a systematic and effective basis for judging the early warning and monitoring of the partial discharge development of the GIS insulation defect; the method specifically comprises the following steps:
(1) according to the GIS actual operation working condition, a simulation experiment platform is built, the simulation experiment platform aims at refining the whole process that insulation defects generate partial discharge in the GIS, and the experiment platform is composed of an armored power frequency experiment transformer, a test unit and a measurement system as shown in figure 1. The highest applied voltage of the armored power frequency experimental transformer is 100kV, the testing unit is a basin-type insulator, the insulator is manufactured by proportionally reducing the 220kV basin-type insulator serving as a reference, and the armored power frequency experimental transformer has the advantages of being clear, direct in view and convenient to operate. The measuring system consists of a coupling resistor, a pulse signal detection impedance box, a Rogowski coil, a pulse current detection device and an oscilloscope.
(2) The basin-type insulator model of the GIS insulation defect model consists of an aluminum electrode and an insulation part which is cast by epoxy resin materials and aluminum oxide. GIS inevitably produces metal particles with shapes of sphere, line and the like in the processes of production, transportation and operation. The invention aims to identify the whole process from early partial discharge to flashover breakdown of a GIS insulation defect office, so that linear metal particles attached to the surface are selected as insulation defects of a basin-type insulator model. In general, metal particles with the length of less than 5mm are difficult to detect by a pulse current method, an ultrahigh frequency method, an ultrasonic method and other methods, so that the aluminum linear metal particles with the length of 8mm attached to the surface of the insulator are selected as a research object and are vertically fixed on a movable operation platform in a GIS cavity; as shown in fig. 2, a linear metal particle defect 1 is fixedly disposed on the basin insulator 2.
(3) The method for acquiring partial discharge signals of the defect model at different stages and phase resolution spectrograms thereof through the pressurization test comprises the following steps: filling SF into GIS cavity6The method comprises the steps of enabling gas to reach 0.4Mpa in a cavity, pressurizing a basin-type insulator defect model by a step boosting method, firstly, slowly boosting the pressure from zero to a local discharge starting voltage, maintaining the voltage constant until the defect model is stably discharged and the spectrogram does not obviously change any more, stopping pressurizing, detecting the local discharge phase resolution spectrogram at the moment, slowly boosting the pressure until the local discharge phase resolution spectrogram of the defect model obviously changes, keeping the voltage constant and repeating the data acquisition process; the above process is repeated until the voltage applied to the defect model is about to reach the flashover voltage, and the test is ended. Multiple trials are repeated to collect a large amount of data to form a data set sample for globally convergent cluster analysis using a clustering algorithm.
(4) According to the test scheme, the characteristic parameters extracted under different voltage gradients are the maximum amplitude Vmax of the partial discharge capacity and the width of the partial discharge phase
And the number n of partial discharges and the phase of the partial discharges distinguish the distribution condition of the pulse points of the spectrogram. Wherein the maximum amplitude V of partial dischargemaxExtracting the original V-t signals one by one from each stage of oscilloscope acquisition, measuring the distribution condition of pulse point positions of a partial discharge phase resolution spectrogram by a partial discharge detector, and measuring the width of a partial discharge phase
Extracted from the spectrum, the number of partial discharges n is also obtained from the pulse count of the pulse current detector (the set count trigger level has been filtered)Except for background noise). According to the extracted partial discharge parameters and the pressurization duration, the following two-dimensional parameters are extracted: maximum amplitude of partial discharge-time (Vmax-t), partial discharge phase width-time
And the number of partial discharges-time (n-t).
(5) And clustering the data set formed by the characteristic parameters by adopting a K-Means clustering algorithm, wherein the K-Means clustering algorithm takes a computer programming language Python as a platform, two containers are required to be constructed to complete the iteration of the centroid, one container is used for storing and updating the centroid of the cluster, and the other container is used for recording, storing and updating the distance between each sample and the centroid. The initial centroid is generated randomly by calling a function of a numpy library in Python, and the distance between each sample and the centroid is calculated by constructing a Euclidean distance function. Firstly, randomly selecting K points in the characteristic parameter data set as initial clustering centers, dividing data samples into K clusters according to Euclidean distances between the remaining points and each clustering center, and finishing clustering by continuously iterating until the sample points in the clusters are not changed any more, wherein a schematic diagram of the principle of a K-Means clustering algorithm is shown in FIG. 3. The extracted two-dimensional parameters are subjected to time parameter elimination, pairwise combination is conducted, the two-dimensional parameters are led into a K-Means clustering algorithm, clustering division and drawing are conducted on the two-dimensional parameters after combination, a local discharge maximum amplitude-local discharge phase width clustering diagram is shown in fig. 4, and a discharge stage can be divided into 3 sections. After the clustering analysis is completed, a clustering classification quantity learning curve is drawn, the number of inflection points of the obtained curve is the optimal number of stages divided in the GIS metal particle partial discharge development process, as shown in the clustering learning curve of FIG. 5, when the number of inflection points appears in 3 and 4 clustering clusters, the discharge development process is judged to be divided into 3 stages according to the clustering result.
Tests show that the system basically conforms to the discharge experimental process for dividing the discharge development stage. The invention has the advantages of strong systematicness, small human intervention degree, higher accuracy, small time consumption and considerable application value.
In summary, the embodiment of the invention discloses a method and a system for identifying a partial discharge development stage of a GIS insulator metal particle defect, wherein the method comprises the steps of firstly, building a GIS simulation operation environment according to a GIS actual operation working condition; then, establishing an insulator metal particle defect model according to the actual situation of the metal particle defect in the GIS; then, acquiring partial discharge signals of the defect model at different stages and phase resolution spectrograms thereof through a pressurization test; extracting characteristic parameters of different discharge stages from the obtained spectrogram; and finally, drawing a related map by using the extracted characteristic parameters and performing clustering algorithm analysis by using the related map as a sample to represent the development process and stage of the partial discharge of the defect model. The method utilizes the operating environment simulating the GIS working condition and identifies the partial discharge development stage of the GIS typical insulation defect through the clustering algorithm, can clearly divide the development process of the partial discharge and can control the discharge characteristics of each development stage. The method well solves the problems that the GIS typical insulation defect partial discharge is unclear in the development stage from the beginning to flashover breakdown, the safety evaluation criterion is insufficient, and the like. The method is simple and practical, has strong reliability and has better robustness.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.
Claims (10)
1. A method for identifying each development stage of GIS insulation defect partial discharge is characterized by comprising the following steps:
obtaining an insulator metal particle defect model;
acquiring characteristic parameters under different voltage gradients based on the insulator metal particle defect model; the characteristic parameters comprise a maximum amplitude of partial discharge, a partial discharge phase width, partial discharge times and a partial discharge phase resolution spectrogram pulse point location distribution condition;
adopting a K-Means clustering algorithm, and carrying out clustering algorithm analysis by taking the obtained characteristic parameters as samples to obtain a clustering result; and performing characterization and identification of each development stage of partial discharge based on the clustering result.
2. The method according to claim 1, wherein the step of obtaining the insulator metal particle defect model specifically comprises:
according to the GIS operation condition, a simulation experiment platform is built;
and constructing and obtaining an insulator metal particle defect model based on the simulation experiment platform and the condition of the metal particle defects in the GIS.
3. The method according to claim 2, wherein the step of building a simulation experiment platform according to the GIS operation condition specifically comprises the following steps:
constructing and obtaining a sealed GIS test cavity according to an actual GIS cavity structure and an operation working condition; placing the basin-type insulator in a GIS test cavity; the GIS test cavity is filled with SF6A gas;
an armored power frequency experiment transformer is used as a voltage source of the simulation experiment platform; setting a coupling resistor, an impedance box and a pulse current detection device; the coupling resistor is used for coupling pulse current flowing through the GIS test cavity, and the impedance box is used for detecting pulse current signals; the pulse current detection device is used for receiving a pulse current signal.
4. The method of claim 3, wherein the pulse current detection device comprises: a Rogowski coil; the Rogowski coil is arranged on a grounding wire of the GIS test cavity.
5. The method according to claim 3, wherein the step of constructing a model for obtaining the metal particle defects of the insulator based on the simulation experiment platform and the conditions of the metal particle defects in the GIS specifically comprises:
the electrodes of the basin-type insulator are made of aluminum oxide, and the insulating part is made of epoxy resin material; the surface of the basin-type insulator is fixedly provided with aluminum linear metal particles for simulating the defects of the metal particles attached to the surface of the insulator.
6. The method according to claim 1, wherein the step of obtaining the characteristic parameters under different voltage gradients based on the insulator metal particle defect model specifically comprises:
obtaining partial discharge signals and phase resolution spectrograms of the insulator metal particle defect model under different voltage gradients through a pressurization test;
and extracting characteristic parameters under different voltage gradients from the phase resolution spectrogram.
7. The method of claim 6, wherein the step of obtaining the partial discharge signal and the phase resolution spectrum of the insulator metal particle defect model under different voltage gradients through the pressurization test specifically comprises:
pressurizing the insulator metal particle defect model by a step boosting method; firstly, boosting the voltage from zero to a partial discharge starting voltage, maintaining the partial discharge starting voltage constant until the insulator metal particle defect model is stably discharged and the spectrogram does not change any more, stopping boosting and detecting the partial discharge phase resolution spectrogram at the moment; then boosting the voltage until the partial discharge phase resolution spectrogram of the insulator metal particle defect model changes, keeping the voltage unchanged, and detecting the partial discharge phase resolution spectrogram at the moment; and repeating the detection of the partial discharge phase resolution spectrogram until the voltage applied to the insulator metal particle defect model reaches the flashover voltage, and finishing the detection.
8. The method according to claim 1, wherein a K-Means clustering algorithm is adopted, and the obtained characteristic parameters are used as samples to perform clustering algorithm analysis to obtain a clustering result; the steps of characterizing and identifying each development stage of partial discharge based on the clustering result specifically comprise:
drawing an atlas according to the characteristic parameters under different voltage gradients to obtain a sample data set; randomly selecting k points in a sample data set as initial clustering centers, dividing the sample data set into k clusters according to the distance between the remaining points and each clustering center, and finishing clustering to obtain a clustering result when the sample points in the clusters are not changed any more through continuous iteration;
and dividing the partial discharge development process of the defect model into k stages according to the clustering result.
9. The method of claim 8, wherein the maps comprise a partial discharge maximum amplitude-time map, a partial discharge phase width-time map, and a partial discharge number-time map.
10. A system for identifying stages of development of partial discharge of a GIS insulation defect, comprising:
the model obtaining module is used for obtaining an insulator metal particle defect model;
the characteristic parameter acquisition module is used for acquiring characteristic parameters under different voltage gradients according to the insulator metal particle defect model; the characteristic parameters comprise a maximum amplitude of partial discharge, a partial discharge phase width, partial discharge times and a partial discharge phase resolution spectrogram pulse point location distribution condition;
the clustering identification module is used for analyzing the clustering algorithm by using the acquired characteristic parameters as samples by adopting a K-Means clustering algorithm to obtain a clustering result; and performing characterization and identification of each development stage of partial discharge based on the clustering result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110580942.1A CN113325281A (en) | 2021-05-26 | 2021-05-26 | Method and system for identifying each development stage of GIS insulation defect partial discharge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110580942.1A CN113325281A (en) | 2021-05-26 | 2021-05-26 | Method and system for identifying each development stage of GIS insulation defect partial discharge |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113325281A true CN113325281A (en) | 2021-08-31 |
Family
ID=77421360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110580942.1A Pending CN113325281A (en) | 2021-05-26 | 2021-05-26 | Method and system for identifying each development stage of GIS insulation defect partial discharge |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113325281A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113702786A (en) * | 2021-09-02 | 2021-11-26 | 华北电力大学 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440497A (en) * | 2013-08-13 | 2013-12-11 | 上海交通大学 | GIS insulation defect partial discharge atlas pattern recognition method |
| CN104198898A (en) * | 2014-08-04 | 2014-12-10 | 西安交通大学 | Local discharge development process diagnosis method based on pulse-train analysis |
| CN107505551A (en) * | 2017-09-21 | 2017-12-22 | 国家电网公司 | Gas-insulated stacked switch equipment superfrequency sensor arrangement experimental rig and application |
| CN207281235U (en) * | 2017-09-09 | 2018-04-27 | 广西电网有限责任公司电力科学研究院 | A kind of partial discharge intensity's detection circuit based on series process |
| CN109298298A (en) * | 2018-11-23 | 2019-02-01 | 中国电力科学研究院有限公司 | A kind of GIS disc insulator shelf depreciation defect diagnostic method and system based on quasi- high frequency pressure resistance |
-
2021
- 2021-05-26 CN CN202110580942.1A patent/CN113325281A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440497A (en) * | 2013-08-13 | 2013-12-11 | 上海交通大学 | GIS insulation defect partial discharge atlas pattern recognition method |
| CN104198898A (en) * | 2014-08-04 | 2014-12-10 | 西安交通大学 | Local discharge development process diagnosis method based on pulse-train analysis |
| CN207281235U (en) * | 2017-09-09 | 2018-04-27 | 广西电网有限责任公司电力科学研究院 | A kind of partial discharge intensity's detection circuit based on series process |
| CN107505551A (en) * | 2017-09-21 | 2017-12-22 | 国家电网公司 | Gas-insulated stacked switch equipment superfrequency sensor arrangement experimental rig and application |
| CN109298298A (en) * | 2018-11-23 | 2019-02-01 | 中国电力科学研究院有限公司 | A kind of GIS disc insulator shelf depreciation defect diagnostic method and system based on quasi- high frequency pressure resistance |
Non-Patent Citations (2)
| Title |
|---|
| 何宁辉 等: "GIS中自由金属颗粒缺陷局部放电严重程度评估", 绝缘材料, no. 12, pages 80 - 88 * |
| 耿弼博: "GIS金属颗粒放电发展的试验研究", 电网与清洁能源, no. 7, pages 107 - 109 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113702786A (en) * | 2021-09-02 | 2021-11-26 | 华北电力大学 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
| CN113702786B (en) * | 2021-09-02 | 2023-09-01 | 华北电力大学 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109116193B (en) | Electrical equipment dangerous discharge distinguishing method based on partial discharge signal comprehensive entropy | |
| Gao et al. | Research on the typical partial discharge using the UHF detection method for GIS | |
| CN108051711B (en) | Solid insulation surface defect diagnosis method based on state feature mapping | |
| CN112014700B (en) | GIS insulator defect identification method and system based on partial discharge multi-information fusion | |
| CN102809718B (en) | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) | |
| CN102539527B (en) | GIS (gas insulated substation) partial discharge mode identification method based on ultrasonic testing | |
| CN103197218B (en) | A kind of high-voltage cable insulation defect partial discharge electrification detection diagnostic method | |
| CN204462312U (en) | GIS partial discharge SF under a kind of surge voltage 6decomposition components analysis mode test unit | |
| CN103558528B (en) | A kind of partial discharge ultrahigh frequency detection system and method | |
| Yao et al. | Feature selection based on random forest for partial discharges characteristic set | |
| CN103645425A (en) | High-voltage cable insulation defect partial discharge on-line monitoring diagnosis method | |
| CN109298298B (en) | GIS basin-type insulator partial discharge defect diagnosis method and system based on quasi-high frequency withstand voltage | |
| CN104237750A (en) | GIS insulation defect partial discharge fault graph drawing method | |
| CN105785236B (en) | A kind of GIS partial discharge detection external interference signals method for removing | |
| CN112149549A (en) | GIS partial discharge type identification method based on depth residual error network | |
| CN103558532A (en) | Partial discharge on-line detection system of high-voltage crosslinked polyethylene power cable | |
| CN113325281A (en) | Method and system for identifying each development stage of GIS insulation defect partial discharge | |
| CN105116201A (en) | Measuring device and method for return voltage parameter | |
| CN113325276A (en) | GIS epoxy insulation surface defect partial discharge detection method and device | |
| Firuzi et al. | A hybrid transformer PD monitoring method using simultaneous IEC60270 and RF data | |
| CN109142995B (en) | Oil paper insulation dielectric tester and method based on dielectric response method | |
| CN116910470A (en) | GIS combined electrical apparatus partial discharge fault mode identification method | |
| CN116992264A (en) | Partial discharge signal processing method and device under high-frequency square wave voltage | |
| CN115327304A (en) | Transformer partial discharge type identification method and system based on deep learning | |
| Li et al. | Partial discharge monitoring system for PD characteristics of typical defects in GIS using UHF method |
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 |