Classification of arrester defects based on Naive Bayesian inference

Abstract

Under the special environment of high temperature, high humidity and high salt, the development of the deterioration or latent defects of the arrester is accelerated. It is difficult to identify the abnormal state of arrester in special environment, only relying on the monitoring index of arrester. Therefore, this paper proposes a kind of lightning arrester defect recognition technology based on Naive Bayesian, which extracts the key features that affect the operation state of lightning arrester in special environment, and calculates the prior probability of training samples and the posterior probability of test samples through naive Bayesian algorithm, so as to identify the type of lightning arrester defects. The feasibility and correctness of the proposed method are analyzed and verified by the actual monitoring and detection data.