Classification of partial discharge electrical signals using wavelet transforms

The wavelet transform has been developed for the analysis of PD pulse signals to further progress in the study of insulation degradation. In this paper, the wavelet transform was applied to one fundamental method for feature extraction. To obtain experimental data, a computer-aided partial discharge measurement system with a single acoustic sensor was used. By applying a neural network method to the accumulated data through the extracted feature, it is possible to detect the PD pulse signal in the insulation materials on-line.