Flashover pattern recognition by HMM based on spectrum characteristics of leakage current on HV insulators

With the increase of voltage grade in power transmission system and the aggravation of industrial pollution, flashover of contaminated insulators in HV and UHV system is more and more serious, threatening the security of power transmission severely. The key of improving the security of system is exploring the methods of monitoring and recognizing states of insulator´s surface by some character values. In this paper, multi-characteristic Hidden Markov Model is founded with spectrum and bispectrum characteristics of leakage current(LC), through which the flashover patterns are recognized during the developing stages. The results show that spectrum characteristics HMM recognized flashover pattern efficiently and successfully, and that is useful to help related stuff to make correct decision and ensure the security of power delivery.