Automated classification of power quality disturbances using the S-transform

With the wide application of sensitive power electronic devices in industry, the power quality (PQ) disturbance problems become more concerned. The S-transform is a time-frequency localization technique that bridges the gap between the short-time Fourier transform and wavelet transform. A new PQ disturbances identification method based on S-transform time-frequency analysis and fuzzy expert system is proposed in this paper. Through S-transform time-frequency analysis, a set of feature components are extracted for identification of PQ disturbances. The fuzzy expert system is also used to identify PQ disturbances. Finally, the paper shows the simulation results which present that the proposed method possesses high identification rate and strong rejection to noises, so it is suitable for monitoring and classification of PQ disturbances.