Electrical tree tests. Probabilistic inference and insulating material evaluation

Abstract

In this paper the application of neural network (NN) to the probabilistic inference of partial discharge (PD) phenomena generated from electrical tree growth is presented. On the basis of experimental results of measurements of trees occurring in a needle-plane arrangement, stochastic quantities are derived, which are relevant to PD pulse amplitude and phase. The NN trained by these quantities shows the feasibility of evaluations that connect tree-growth stage, i.e. the amount of damage produced by the tree, with a reduced set of these quantities. This set is, in turn, obtained applying a NN operating for data compression. In this framework, the NN can also recognize a material, among those used for training, associating to it the specific tree-growth feature.