Experimental analysis of AI based pollution severity classification scheme for high voltage insulators

Abstract

The reliable and uninterrupted operation of a modern power system depends on the satisfactory performance of insulators. Insulators are one among the key devices of electric power transmission systems. Porcelain insulators are mostly used in power transmission and distribution lines. Flashover of contaminated porcelain insulator in polluted areas has proven to be one of the most significant factors influencing the operation of high voltage power transmission lines and substations. When these insulators are installed near industrial, agricultural or coastal areas, airborne particles are deposited on these insulators and the pollution builds up gradually, which results in the flow of Leakage Current (LC) during wet weather conditions such as dew, fog or drizzle. Thus in turn, the LC density is non-uniform over the insulator surface and it leads to formation of dry bands. Voltage redistribution along the insulator causes high electric field intensity across dry bands which leads to the formation of partial arcs.Partial arcs are initiated if the electric field intensity across the dry band exceeds the withstand value. When the surface resistance is adequately low, these partial arcs will elongate along the insulator profile which may ultimately cause flashover. Contamination flashover of porcelai n insulator results in power outages and equipment damage. Hence in order to overcome this problem, various studies are carried out to enumerate the pollution severity and to predict the flashover of porcelain insulators. Conventionally Equivalent Salt Deposit Density (ESDD) method was used, but it is a time consuming process and is difficult to automate. newline