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

Method and device for detecting power transmission line defects

A technology of transmission lines and detection methods, which is applied in the directions of measuring devices, optical testing of flaws/defects, and material analysis through optical means, and can solve the problems of low recognition accuracy of power components, insufficient judgment accuracy of transmission lines, misjudgment rate, etc. problems to achieve the effect of improving the accuracy of judgment

Inactive Publication Date: 2016-12-07
ELECTRIC POWER RESEARCH INSTITUTE, CHINA SOUTHERN POWER GRID CO LTD +2
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the actual use environment, due to the influence of the complex environment on the characteristics of the equipment on the transmission line, the images obtained by infrared detection technology contain a lot of noise and complex background information, which leads to the detection method based on image recognition technology. Accurate recognition of power components The rate is low, and there is a serious misjudgment rate, so the accuracy of the judgment of transmission line defects is insufficient

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
  • Method and device for detecting power transmission line defects
  • Method and device for detecting power transmission line defects
  • Method and device for detecting power transmission line defects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0019] Embodiments of the present invention provide a detection method for transmission line defects, combining figure 1 shown, including the following steps:

[0020] 101. Determine a feature extractor through unsupervised learning.

[0021] The feature extractor is a mapping function between the infrared image and the data features of the infrared image.

[0022] Set a set of infrared image training samples without class labels X={x a ,x b ,x c ,…}, train through this set to complete the unsupervised learning process.

[0023] The unsupervised learning process can include the following sub-steps:

[0024] 101-1. Divide the unlabeled image into blocks, and randomly extract at least one sub-image block from it.

[0025] 101-2. Perform preprocessing on data of at least one sub-image block.

[0026] The overall brightness of the image does not affect the analysis of objects in the image, that is, the average brightness value of the image block can be ignored, so the avera...

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

An embodiment of the invention provides a method and device for detecting power transmission line defects and relates to the field of power component detection. By the method and device for detecting the power transmission line defects, the judging accuracy of the power transmission line defects can be increased. According to the technical scheme, the method includes: determining a feature extractor, which is a mapping function between an infrared image and the data feature of the infrared image, through unsupervised learning; acquiring a target infrared image, and extracting the data feature of the target infrared image through the feature extractor, wherein the target infrared image is the infrared image of a power transmission line; using a classifier to perform classification detection on the data feature of the target infrared image so as to identify the positive sample of the target infrared image, wherein the positive sample is the infrared image sample of a power component on the power transmission line; performing temperature analysis on the positive sample, and outputting a defect judging result.

Description

technical field [0001] The invention relates to the field of power component detection, in particular to a detection method and device for transmission line defects. Background technique [0002] The electric power industry is an important foundation of the national economy, it provides the basic impetus for the national economy and other sectors, and is the focus of the national economic development strategy. The geographical environment that the transmission line crosses is complex, far away from the main traffic arterial road, and the transmission line is easily affected by factors such as natural disasters and man-made damage during long-term operation, resulting in defects such as broken wires, dirty insulators, and corrosion of towers. It is often accompanied by partial discharge, local temperature rise, and other phenomena, which will seriously affect the operation safety of the power grid. Therefore, it is necessary to inspect the line to find and eliminate line def...

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 Applications(China)
IPC IPC(8): G01N21/88
CPCG01N21/8851G01N2021/8854G01N2021/8887
Inventor 吴新桥王晓婧张静张巍周筑博张贵峰陈晓陈艳芳赵克杨鹤猛龚博黄增浩
Owner ELECTRIC POWER RESEARCH INSTITUTE, CHINA SOUTHERN POWER GRID CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More