Prediction of polluted insulators characteristics using artificial neural networks

In this paper, we propose three prediction algorithms using the artificial neural networks to generalise some characteristics describing the electrical arc propagation on polluted insulators. For that purpose, three Radial Basis Function Gaussian (RBFG) networks with one output have been elaborated. The difference between these configurations consists in the nature of the input and output units. The chosen networks are trained by Random Optimisation Method (ROM). A discussion to determine the best configuration is presented.