Substation equipment appearance abnormality recognition method based on substation inspection robot

Abstract

The invention relates to a substation equipment appearance abnormality recognition method based on a substation inspection robot. In the method, based on a power inspection robot platform (with a model number of LER-3000), relative technologies such as an image processing technology, a mode recognition technology and the like are utilized to detect images collected by power equipment, judge whether the equipment is in abnormal conditions of fouling, damage, foreign bodies and the like or not, find out a corresponding defect recognition method by analyzing the collected images, accurately and rapidly detect the abnormality of the equipment, timely report and eliminate safety hidden dangers. The substation equipment appearance abnormality recognition method based on the substation inspection robot comprises the following steps of, firstly, collecting an image of each equipment on an inspection route by the power inspection robot; secondly, carrying out registration on a processed image and a corresponding equipment reference image stored in advance; thirdly, after image registration, detecting a region with the abnormality according to a difference of the two images; and fourthly, classifying the abnormality according to characteristic parameters of the detected abnormal region.

Description

technical field [0001] The invention relates to a method for identifying abnormal appearance of substation equipment based on a substation inspection robot. Background technique [0002] The current substation status detection equipment only monitors the current, voltage and other related data collected by the equipment, and cannot detect possible abnormalities in the appearance of the equipment. Such appearance abnormalities, such as oil stains on the surface of the transformer, changes in the shape of the equipment, kites and streamers hanging on the equipment, etc., have great potential safety hazards and should be discovered and eliminated in time; currently such abnormalities mainly rely on Manual on-site inspection, this inspection method has the following two problems: first, it is not safe, because the high voltage and discharge in the substation may cause harm to the human body at any time; second, it is not timely, because the staff cannot patrol the station for a ...

AI Technical Summary

Problems solved by technology

[0002] The current substation status detection equipment only monitors the current, voltage and other related data collected by the equipment, and cannot detect possible abnormalities in the appearance of the equipment.

Such appearance abnormalities, such as oil stains on the surface of the transformer, changes in the shape of the equipment, kites and streamers hanging on the equipment, etc., have great potential safety hazards and should be discovered and eliminated in time; currently such abnormalities mainly rely on Manual on-site inspection, this inspection method has the following two problems: first, it is not safe, because the high voltage and discharge in the substation may cause harm to the human body at any time; second, it is not timely, because the staff cannot patrol the station for a long time, problems occur , it is difficult to be detected in time

[0004] Since the substation is set in an outdoor environment, different lighting effects have a greater impact on the image quality; when the substation inspection robot collects images, there will be errors in the positions of the two stops, which makes the positions of the captured equipment inconsistent in the image; the above two situations are There are two main difficulties faced by anomaly detection, and there is no mature and general method to solve the above problems

Images