The pollution flashover, observed on insulators used in high voltage transmission is one of the most important problems for power transmission. It is very complex problem due to several factors such as the modeling difficulties of complex shapes of the insulators, different pollution different regions, non-homogeneous pollution distribution on the insulation surface and unknown effect of humidity on the pollution. In the literature, some static and dynamic models were developed by making some assumptions and omission to predict the flashover voltages of polluted insulators. In this paper, an artificial neural network (ANN) model was built with limited number of measurement for the prediction of the critical flashover voltage of polluted insulator. Multilayer fully connected feed forward neural network (FFNN) with Back propagation algorithm has proposed for the assessment of critical flash over in artificially polluted porcelain insulators The comparisons indicate the proposed ANN model gives better results compared to the analytical model suggested earlier.
Keywords—Pollution Flashover, Flashover Voltage, Artificial Neural Networks, Laboratory Measurements