APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR OPTIMIZATION OF ELECTRODE CONTOUR

In this paper artificial neural networks (NN) with supervised learning are proposed for HV electrode optimization. To demonstrate the effect iveness of artificial NN in electric field problems, a simple cylindri cal electrode system is designed first where the stresses can be compu ted analytically. It is found that once trained, the NN can give resul ts with mean absolute error of approximately 1% when compared with ana lytically obtained results. In the next section of the paper, a multil ayer feedforward NN with back-propagation algorithm is designed for el ectrode contour optimization. The NN is first trained with the results of electric field computations for some predetermined contours of an axisymmetric electrode arrangement. Then the trained NN is used to giv e an optimized electrode contour in such a way that a desired stress d istribution is obtained on the electrode surface. The results from the present study show that the trained NN can give optimized electrode c ontours to get a desired stress distribution on the electrode surface very efficiently and accurately.