Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Identification method of various partial discharge source types in gas insulated substation (GIS)

A technology of gas insulation and identification method, applied in the direction of testing dielectric strength, etc., can solve the problems of no longer applicable, reduced identification accuracy, easy to fall into local minimum, etc., to achieve the effect of improving accuracy

Active Publication Date: 2013-10-02
TSINGHUA UNIV +1
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These feature quantities can accurately describe the discharge characteristics of a single discharge source, but if there are multiple discharge sources in the GIS, these feature quantities will no longer be applicable
Artificial neural network is widely used as a classifier for partial discharge pattern recognition, but artificial neural network often has the problem of over-training and easy to fall into local minimum, and when there are few training samples, its recognition accuracy is greatly reduced

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification method of various partial discharge source types in gas insulated substation (GIS)
  • Identification method of various partial discharge source types in gas insulated substation (GIS)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The method for identifying the types of multiple partial discharge sources in a gas-insulated substation proposed by the present invention includes the following steps:

[0019] (1) Within the set time period, collect the partial discharge signal in the gas-insulated substation to obtain the first discharge signal sequence u(i) (i=1,2,...N); (the set time period of the present invention is 40-60 milliseconds, and the time period in one embodiment of the present invention is 50 milliseconds).

[0020] (2) Extract the UHF discharge signal from the first partial discharge signal sequence u(i) collected in step (1). The extraction process includes the following steps:

[0021] (2-1) Extract the partial discharge signal from the first partial discharge signal sequence u(i) with a set step size L to obtain the second discharge signal sequence u'(j), (j=1,2,...N / L);

[0022] (2-2) Perform peak extraction on the second discharge signal sequence u'(j), and determine the time ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an identification method of various partial discharge source types in a gas insulated substation (GIS), and belongs to the electrical equipment technology field. In the method, a data acquisition card with a high sampling rate and a long record length is utilized to record long time partial discharge signals; a wavelet denoising method is used for a noise reduction treatment of the partial discharge signals, and then the discharge signals are extracted to obtain a frequency spectrum energy distribution of the discharge signals; and finally, a support vector machine is used to distinguish discharge types to realize the partial discharge source identification in the GIS. The method of the invention utilizes the acquisition card with the long record depth and the high sampling rate, so that the identification time for different discharge sources is reduced; according to an ultrahigh frequency signal energy ratio, a least square support vector machine is trained; according to an ultrahigh frequency signal in the long time record data, various discharge source types are identified; and the accuracy of the discharge source identification is improved.

Description

technical field [0001] The invention relates to a method for identifying multiple types of partial discharge sources in a gas-insulated substation, and belongs to the technical field of electrical equipment. Background technique [0002] There are many types of partial discharge sources in a gas insulated substation (GIS for short), and different partial discharge sources have different hazards to equipment. Therefore, when detecting partial discharge in GIS, it is necessary to carry out pattern recognition on partial discharge sources. Partial discharge pattern recognition includes discharge feature extraction and classifier selection. The currently used feature quantities usually use the three-dimensional PRPD (Phase Resolved Partial Discharge) diagram of multiple cycles of partial discharge, which are mostly statistical parameters describing the distribution of discharge times, discharge phases, and discharge amplitudes, while the time domain of the original UHF signal of...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01R31/12
Inventor 高文胜丁登伟
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com