Optical diagnosis method of gis partial discharge based on multifractal and extreme learning machine

An extreme learning machine and partial discharge technology, which is applied in neural learning methods, testing using optical methods, computer parts, etc., to ensure the efficiency of optical diagnosis, improve the recognition accuracy, and improve the recognition speed.

Active Publication Date: 2022-06-03
ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Establishing the mapping relationship between optical characteristic parameters and partial discharge defect types is a fundamental and key issue in optical diagnosis. At present, there are few related research reports, and in-depth research is needed

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
  • Optical diagnosis method of gis partial discharge based on multifractal and extreme learning machine
  • Optical diagnosis method of gis partial discharge based on multifractal and extreme learning machine
  • Optical diagnosis method of gis partial discharge based on multifractal and extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments of the description.

[0080] 4) Input training and test samples, and test the recognition results.

[0090] n

[0092]

[0094]

[0098] μ

[0099] This probability is also called a singularity measure. If the optical PD map space is divided into N small areas, record the i-th area

[0100]

[0103]

[0105]

[0107]

[0110]

[0111] Then τ(q) is called the quality index, and it can be known from the formula (6) that N(q, L)~L

[0113]

[0115] First, build a framework of an extreme learning machine according to the structure shown in FIG. 6 .

[0116] In the figure, the number n of neurons in the input layer is equal to the number of features, and it can be known from step (2) that n=10. Assuming that the hidden layer has a total of

[0117]

[0119]

[0121] W

[0122] β represents the output weight matrix, with

[0123]

[0125] The number of neu...

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 discloses a GIS optical partial discharge identification method based on multifractal and extreme learning machine. The technical solution adopted in the present invention is: design a variety of GIS typical insulation defect models and build a laboratory optical detection system, collect optical partial discharge signals, and draw gray-scale optical partial discharge maps under different defects in GIS; according to the multifractal theory, extract Gray scale the difference box dimension of the optical partial discharge map and the multifractal feature quantity of the information dimension; construct the extreme learning machine as a classifier, and find the global minimum value through the linear parameter mode; input training and test samples, and test the recognition results. The multi-fractal feature of the present invention can improve the recognition accuracy of the GIS optical partial discharge atlas, the extreme learning machine can improve the recognition speed of the GIS optical partial discharge atlas, and the combination of the two can ensure the optical diagnosis efficiency of the GIS partial discharge.

Description

Optical Diagnosis Method of Partial Discharge in GIS Based on Multifractal and Extreme Learning Machine technical field The invention belongs to GIS insulation defect detection field, relate to a kind of GIS bureau based on multifractality and extreme learning machine Partial discharge optical diagnosis method, which can perform feature extraction and pattern recognition more efficiently and accurately. Background technique [0002] Closed combined electrical appliances (Gas Insulated Switchgear, GIS) is a kind of SF 6 gas as insulating medium Quality gas-insulated metal-enclosed switchgear. Compared with traditional open-type substations, GIS has high dielectric strength, It has the advantages of stability, less floor space and less maintenance workload, so it is widely used in large and medium urban power grids. But from near In the past ten years, there have been many accidents in the use of GIS at home and abroad, among which insulation failures are the main ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G01R31/12G06K9/62G06N3/04G06N3/08
CPCG01R31/1218G01R31/1227G06N3/084G06N3/048G06N3/045G06F18/24Y02E60/00
Inventor 陈孝信邵先军王绍安郑一鸣李晨杨智詹江杨何文林陈珉孙翔王文浩徐华陈梁金王绪军王磊臧奕茗钱勇王辉舒博
Owner ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap