The influence of the momentum coefficient and the number of the averaging points of the power spectrum density on the recognition effectiveness of the AE signals generated by basic PD forms by the neuron network

Abstract

The subject matter of this paper refers to the next stage of the research work connected with the improvement of the acoustic emission method (AE) used for the evaluation of partial discharges (PDs) generated in paper-oil insulation systems of high-voltage power appliances. The subject matter discussed here refers to one of the aspects of the analysis of the signals registered - a correct and effective recognition of the AE signals generated by basic PD forms. The paper presents research results of the application of the unidirectional artificial neuron networks (ANN) used for the recognition of basic PD forms that can occur in paper-oil insulation impaired by aging processes.