Insulator fault detection method based on machine vision

A technology of fault detection and machine vision, which is applied in the direction of instruments, image data processing, calculation, etc., can solve the problems of low detection efficiency, high risk factor, high work intensity, etc.

Active Publication Date: 2019-09-20
CENT SOUTH UNIV
View PDF13 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Damage to the ceramic body of the insulator will reduce its insulation strength. If it is not found and replaced for a long time, it will cause the porcelain bottle to break and cause other unpredictable failures in the circuit
At present, the tradition

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
  • Insulator fault detection method based on machine vision
  • Insulator fault detection method based on machine vision
  • Insulator fault detection method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0091] In order to make the technical solutions and implementation steps of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0092] refer to figure 1 As shown, in this embodiment, the steps of the catenary key component target detection method are as follows:

[0093] 1. Obtain a sample image

[0094] Obtain the images of catenary support devices collected by high-definition cameras during train running, screen out those with insulators in the images as research samples, and make these images into labeled data. The size of the collected sample image is 4000*6000.

[0095] 2. Insulator target detection and classification

[0096] In order to detect the fault of the insulator, the target detection of the insulator must be realized firstly. At present, the method with the best application effect is the target detection network based on deep ...

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 an insulator fault detection method based on machine vision. The method comprises the following steps: preprocessing a to-be-processed image; detecting the edge of the insulator; extracting effective edges by using a machine learning classification method; and determining a fault by detecting the shape characteristics of the insulator area and the edge, and carrying out fault rating. According to the method, fault detection can be effectively carried out on the catenary insulator, the calculation amount of the algorithm is small, the effective insulator edge is screened out in a targeted mode through the decision tree algorithm, and therefore various noise interferences are avoided, and the fault detection accuracy is guaranteed. The omission factor is 1.4% or below, the fault detection accuracy is 98% or above, and the actual engineering requirements are met. The invention particularly provides a feasible scheme for machine vision-based fault detection with insufficient negative samples, provides an index for judging the fault level, and is helpful for making reasonable response to consideration of factors of comprehensive safety and economy in engineering.

Description

technical field [0001] The invention belongs to the technical field of image processing and analysis, and in particular relates to a catenary insulator fault detection and fault method. Background technique [0002] Catenary is an important part in the construction of electrified transmission lines. It is erected along the railway line through the pillar equipment along the line. The electric locomotive mainly obtains the electric energy required for operation through catenary transmission, so it is very important to ensure the good working condition of the catenary at all times. In the catenary system, the insulator is one of the important parts of the suspension device except the mechanical support. On the one hand, there is a sufficient distance between the live conductors of the catenary, and on the other hand, the insulation between the live conductors and the earth is ensured. Since the working environment of insulators needs to be exposed to the atmosphere for a long...

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): G06T7/00G06T7/13G06T5/20G06T5/00
CPCG06T5/002G06T5/20G06T7/001G06T2207/20032G06T2207/20081G06T2207/20084G06T7/13
Inventor 王春生郭煊烽刘子建
Owner CENT SOUTH UNIV
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