Suspension insulator discharge severity assessment method based on ultraviolet video and deep learning

Abstract

The invention discloses a suspension insulator discharge severity evaluation method based on an ultraviolet video and deep learning. The method comprises the following steps: collecting and preprocessing an insulator discharge ultraviolet video, synchronously collecting and preprocessing a leakage current and an acoustic emission signal, synthesizing an ultraviolet discharge parameter, a leakage current parameter and an acoustic emission signal parameter to form a three-dimensional sample point, carrying out clustering by using K-means, marking the ultraviolet video according to a clustering result, establishing a discharge ultraviolet video database comprising a training set, a test set and a verification set, sending the ultraviolet video in the training set into a MiCT network for training, obtaining spatial-temporal characteristics of different discharge severity degrees, adjusting network hyper-parameter values according to the expression of the model on the verification set, obtaining an optimal weight file through repeated operation, sending a to-be-tested video to the trained deep learning network, and calling the optimal weight file, so that evaluation of the discharge severity of the suspension insulator is realized.

Description

technical field [0001] The invention relates to the fields of high-voltage test technology, image processing technology and machine learning technology, in particular to a method for evaluating the severity of discharge of suspension insulators based on ultraviolet video and deep learning. Background technique [0002] Insulators are important insulating devices in transmission lines, and it is of great significance to know their insulation status in time for the safe and stable operation of power systems. The traditional insulator inspection method mainly uses hand-held binoculars and infrared imager to inspect insulators manually, which requires high experience of inspectors. In addition, the infrared imager is based on heat accumulation and has low sensitivity to early fault discharge, so it cannot grasp the operating status of insulators in time. [0003] The ultraviolet imaging method is a newly developed discharge detection method in recent years. Compared with the tr...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problems of evaluating the severity of insulator discharge and the popularization and application of ultraviolet imagers, the present invention provides a method for evaluating the severity of discharge of suspended insulators based on ultraviolet video and deep learning, which can realize intelligent diagnosis of external insulation discharge of power equipment, At the same time, it solves the problem that it is impossible to accurately evaluate the discharge severity of insulators only by relying on a single or a few pictures

Images