Spectral features for the classification of partial discharge signals from selected insulation defect models

Time-domain features of partial discharge (PD) signals are often used to classify PD patterns. This paper proposes spectral features that are extracted using a filter bank, consisting of band-pass filters. By applying the fast Fourier transform to the PD signal, the resulting frequency bins are grouped into L octave frequency sub-bands. Two new features called the octave frequency moment coefficients (OFMC) and octave frequency Cepstral coefficients (OFCC) are defined in this paper. In addition, time-frequency domain coefficients (TFDC) obtained via wavelet analysis are also analysed. A PD signal can now be represented as an L-dimensional feature vector of OFMC, OFCC or TFDC. These features are compared with discrete wavelet transform-based higher-order statistical features (HOSF) using three different classifiers: probabilistic neural network, support vector machine and the recently emerged sparse representation classifier. Results show that the proposed spectral features are robust and provide a better classification accuracy of PD signals, compared with HOSF.