Prediction method of leakage current of insulators on the transmission line based on BP neural network

Abstract

Pollution flashover is a serious threat to the safe and stable operation of power system, and the pollution flashover voltages of insulators on the transmission lines are related to the leakage currents. In this paper, a neural network model was proposed to predict the leakage currents on the insulators, which could provide references for preventing pollution flashover. By the analysis of a large number of leakage current data obtained by the monitoring device on the insulators of operating lines, the characteristics of the leakage current is extracted, and then combined with BP neural network, the prediction model of leakage current based on the actual operation data is established. By adjusting the parameters of the BP neural network, the prediction results can be accords with the actual operation situation. The reliability of the predicted results was verified by the leakage current on the insulator surface.