Research on Diagnosis Device of Insulator Pollution Degree Based on BP Neural Network

Abstract

In order to realize the real-time diagnosis of local insulator pollution, a kind of local insulator pollution diagnosis device is designed based on BP (Back Propagation) neural network prediction and classification algorithm, which can communicate with domestic ultraviolet imager in real time. According to the obtained photoelectron number, apparent discharge, detection distance and gain from ultraviolet imager, the insulator pollution grade is evaluated by BP neural network algorithm. The research results lay a foundation for the practical engineering application of the local insulator pollution diagnosis device.