Method for automatically detecting failure of insulator

Abstract

The invention discloses a method for automatically detecting the failure of an insulator. The method comprises the following steps: establishing positive and negative sample banks of insulator images, training an insulator classifier by a convolutional neural network algorithm, and splitting a collected image by utilizing the image salient area detection algorithm to split an equipment area and a background area in the image so as to obtain an insulator searching candidate area; training the insulator classifier by utilizing the convolutional neural network algorithm to locate the insulator, and controlling image collection equipment according to the location information of the insulator string in a current image to complete the image collection of the insulator string; and carrying out insulator surface stain detection, insulator string cracking detection and insulator string breakage or mixed foreign substance detection by utilizing an image identification technology so as to determine abnormal insulators. According to the method, insulator stains, cracking and breakage can be detected by adopting different image processing algorithms, insulator states can be comprehensively detected, and potential safety hazards of the insulators in transformer substations / converter stations can be reduced.

Description

technical field [0001] The invention relates to an insulator fault automatic detection method. Background technique [0002] Insulators are widely used in substations / converter stations and are of various types. They are one of the key components of power equipment in the substation and occupy a very important position, which is directly related to the safe and stable operation of the substation / converter station. At present, the on-line detection method of insulators mainly adopts manual inspection, which has many problems. Manual inspection and maintenance is mainly to observe the status of the insulators in the substation / converter station on a regular basis or to detect the state of the insulators with human eyes or special testing equipment. Human eye observation has certain subjectivity and there are certain potential safety hazards, so special testing equipment is required The method of this method is complex in operation, high in cost, slow in detection speed, and c...

AI Technical Summary

Problems solved by technology

[0005] First, the automatic detection function of the current intelligent inspection robot is limited. Most of the images taken by inspections require manual observation and analysis, and the state analysis of insulator strings still requires manual participation;

[0006] Second, at present, intelligent inspection robots carry cameras to take pictures of power equipment, which requires prior information to configure fixed robot stops, and set the shooting angle and focal length of the camera in advance. In order to obtain a larger field of view, the obtained insulators are often taken The resolution of the string image is not high, and it is impossible to clearly observe the surface condition of the insulator;

[0007] Third, relying on the machine learning method to locate the electrical equipment in the image, the algorithm is time-consuming, and is affected by the background, which is prone to false detection;

[0008] Fourth, there are few image-based insulator defect diagnosis algorithms, and the speed and accuracy of the algorithms need to be further improved

Images