Identification of faulty insulators by using corona discharge analysis based on artificial neural network

Abstract

It was found from the tests in our laboratory that statistic analysis of insulator corona current pulses could identify the existence of faulty insulators on strings or transmission line towers. Some basic researches on corona discharge characteristics of insulators and insulator strings were investigated hrther in terms of polarity, aniplitude, and pulse count of corona current pulses. Insulator corona characteristics are observed to be different from piece to piece. Therefore, a BP network was developed to classify voltage across an insulator and hrther identify the existence of faulty insulators on towers. It is confirmed that the developed BP network method yields satisfactory performance in terms of training time and quality of classification.Porcelain insulators are main insulators used to transmission lines in china. Electric power utilities in china inspect for low and zero resistance insulators on transmission lines once 2 -4 years. The tools widely used to

Artificial neural networks in high voltage transmission line problems

“…Furthermore the ANNs have applications in the solution of the power flow problem, the effective distance protection of the transmission lines [5] and the prediction of magnetic performance of strip-wound magnetic cores [6]. Finally very interesting ANN applications have been reported in high voltage engineering problems such as the identification of fault insulators using corona discharges [7], the recognition of leakage current wave forms and their harmonic content on several different types of polluted insulators and polymeric surfaces [8,9], the evaluation of lightning overvoltages in distribution lines [10] and the lightning protection of high voltage transmission lines [11].…”