Pollution Severity Analysis of Electric Power Transmission Tower Insulators using K-Means Clustering and Multi Resolution Signal Decomposition Technique

Abstract

Pollution due to various sources deposits on the surface of insulators used in the electric power transmission towers. Under wet and highly polluted conditions, this pollution layer causes the formation of severe arcing on the surface of insulator which in turn leads to flashover of insulator. Failure of insulators due to pollution based flashover is a major issue faced by electrical utilities and hence accurate prediction of pollution on the surface of insulator using advanced techniques is always a hot research area. This paper deals with the development of a high performance diagnostic system to predict the pollution severity of tower insulators based on the multi resolution signal decomposition technique and k-means clustering approach. Laboratory experiments were carried out on porcelain insulators, which are conventionally used in power transmission system, under AC voltages at different pollution conditions and corresponding leakage current signals were measured. Multi resolution signal decomposition technique is employed to extract important features of leakage current signals. Variation of leakage current magnitude and distortion ratio at different pollution levels were analyzed. K-means algorithm is used to cluster the extracted features of the leakage current data. Test results clearly show that the pollution severity of power transmission tower insulators can be effectively realized through k-means clustering technique and it will be useful to carry out preventive maintenance work.