Insulator fault detection method based on machine vision

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...

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 traditional manual detection has low efficiency, high work intensity, and high risk factor. The electric field method cannot detect some external insulation defects that do not affect the electric field. These detection methods do not have certain practicability

Images