Unlock instant, AI-driven research and patent intelligence for your innovation.

Recognition Method of AC Cable Insulation Defects Based on Partial Discharge Image Features

An identification method and technology for insulation defects, applied in image analysis, image data processing, character and pattern recognition, etc., can solve the problem of ineffective identification of insulation defects of XLPE cables, effective identification of insulation defects of XLPE cables, and inability to effectively extract local parts. Discharge characteristics and other issues, to achieve the effect of high recognition result accuracy and intelligent level

Active Publication Date: 2022-02-25
SHANGHAI JIAOTONG UNIV +2
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the prior art, there is no effective identification of insulation defects of XLPE cables, and the prior art cannot effectively identify the identification of insulation defects of XLPE cables, especially the partial discharge characteristics under partial discharge cannot be effectively extracted

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
  • Recognition Method of AC Cable Insulation Defects Based on Partial Discharge Image Features
  • Recognition Method of AC Cable Insulation Defects Based on Partial Discharge Image Features
  • Recognition Method of AC Cable Insulation Defects Based on Partial Discharge Image Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The method for identifying insulation defects of XLPE AC cables based on partial discharge image features according to the present invention will be further described according to specific embodiments and accompanying drawings, but this description does not constitute an improper limitation to the technical solution of the present invention.

[0050] In order to verify that the identification method of XLPE AC cable insulation defects based on partial discharge image features in this case can better identify different typical defects of DC cables, four types of insulation defects of DC cables were selected and simulated on DC cables. The four types of insulation defects are subjected to DC partial discharge test and connected to the circuit for testing.

[0051] figure 1 Schematically shows the circuit wiring diagram for the DC partial discharge test of the insulation defect under one implementation of the method for identifying the insulation defect of the XLPE AC cabl...

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 method for identifying insulation defects of XLPE AC cables based on partial discharge image features, which comprises the steps of: (1) acquiring several insulation defect discharge models of XLPE AC cables; (2) generating various insulation defect discharge models Applying voltage to collect the partial discharge signals to form respective signal diagrams, in which the power frequency phase is represented, Q represents the discharge amount, and n represents the number of partial discharges that occur in each of the several small intervals in which the plane is divided into several small intervals; (3) Perform wavelet transform on the signal graph to obtain and extract the energy entropy value distribution graph of several subgraphs; (4) Based on the energy entropy value distribution graph, select the two subgraphs with the largest energy proportion as the feature extraction objects, and extract the feature extraction (5) input the above features into the classifier for training and testing; (6) input the partial discharge signal to be identified into the trained and tested classifier, and the classifier outputs the recognition result.

Description

technical field [0001] The invention relates to a method for identifying defects in electric equipment, in particular to a method for identifying insulation defects in AC cables. Background technique [0002] In recent years, the proportion of cross-linked polyethylene (XLPE) AC cables with excellent performance in electrical, mechanical and thermal stability has been increasing in power lines, and it is very suitable for the distribution and transmission of high-power electric energy. However, due to the complex and even harsh environment of cable laying, in all links and processes of power engineering, cables may fail, and even in severe cases, it will greatly affect production and life, and a large amount of additional resources will be consumed for failure. Find and fix power outages. Since the partial discharge of the XLPE cable is closely related to its insulation condition, the fault analysis can be carried out through the partial discharge signal of the XLPE cable. ...

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): G06T7/00G06V10/56G06V10/54G06V10/422G06V10/764G06K9/62G01R31/12
CPCG06T7/0004G01R31/1272G06V10/56G06F18/241
Inventor 钱勇张悦许永鹏秦雪舒博陈孝信李嫣然盛戈皞江秀臣
Owner SHANGHAI JIAOTONG UNIV