Discrimination of partial discharge patterns using a neural network

The application of the neural network algorithm to the perception of partial discharge patterns is described. Needle shaped void samples, made from epoxy resin, were used to generate an electrical tree under AC voltage. The partial discharge patterns before and after the tree initiation were learned by the neural network using the back-propagation method. After the learning process was over, unknown discharge patterns were put into the network. It was shown that the network discriminates the tree initiation well. For the stable discrimination of tree initiation, it was required that the tree length be larger than the length of the void.<
>