A prediction method for the development of insulator pollution degree based on long short-term memory neural network

Abstract

The invention discloses a method for predicting the development of pollution degree of insulators based on long-term short-term memory neural network, which includes acquiring hyperspectral images taken in local areas of insulators, and extracting hyperspectral spectral lines of hyperspectral images; Input the hyperspectral regression model of insulator pollution degree of the same pollution type that has been constructed to obtain the pollution degree of insulators; input the pollution degree and forecast time series of insulators into the hyperspectral development of pollution degree of the same pollution type constructed by long-short-term memory neural network algorithm In the prediction model, the predicted pollution degree of insulators required by the project is obtained. This solution can accurately predict the pollution development of insulators through the combination of the hyperspectral development prediction model of pollution degree and hyperspectral image, so as to solve the problems of cumbersome operation, large artificial interference and difficulty in predicting the future development of pollution degree in the existing technology.

Description

Technical field [0001] The invention belongs to the technical field of maintenance and repair of the operating state of power transmission and transformation equipment, and particularly relates to a method for predicting the development of insulator contamination based on a long and short-term memory neural network. Background technique [0002] Transmission line insulators are exposed to the atmosphere for a long time, and pollution gradually accumulates on the surface. With the rapid development of industry and agriculture and the increase of voltage levels, transmission line insulators will face more serious pollution problems. If the insulator is dirty, its electrical performance will be reduced when it is damp in humid weather such as fog, dew, rain, etc., which is prone to flashover accidents. Once the pollution flashover occurs, it will lead to a large-scale blackout accident, and the maintenance and recovery time will be long. It will not only bring inconvenience to peop...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned deficiencies in the prior art, the method for predicting the development of insulator pollution degree based on the long-term short-term memory neural network provided by the present invention solves the problem of difficulty in detecting the pollution degree of insulators in the prior art

Images