Insulation behavior of SF6 gas in non uniform field under LI and VFT using a neural network

The purpose of this paper is to present, for the first time, a new approach of evaluating the insulation behaviour of SF₆ gas in non uniform field under LI and VFT voltages using a neural network. The objective is to overcome the difficulties associated with using the experimental and numerical methods. In this paper, a multilayer feed forward network is constructed to solve this problem easily. Experimental work was carried out in the high voltage laboratory, some of die obtained results are used in training the proposed NN, and the others are used in testing it. Detailed studies have been carried to determine the NN parameters that give the best results. Studies have also been carried out to assess the effect of the presence of in adequate data, such as, wave shape, polarity, pressure, gap distance and needle radius in the training set on modeling accuracy