Simultaneous Power Quality Disturbances Analysis Using Modified S-Transform and Evolutionary Approach

Abstract

This chapter proposes a hybrid technique based on modified S-transform (ST) and Differential Evolution (DE) algorithm for the visual detection and pattern classification of different nonstationary power quality (PQ) events. The presence of Gaussian window in ST provides a high time resolution in low-frequency bands. The modified Gaussian window in modified ST is capable of depicting a high-resolution time–frequency representation (TFR) for different simultaneous PQ disturbance signals. Further, the modified ST is used for extraction of relevant features from the available PQ disturbance waveforms. Then, the features obtained by modified ST are clustered by using a fuzzy C-mean (FCM)-based DE algorithm. The analysis and experimental results show that the proposed hybrid technique provides a considerable improvement in PQ detection and classification.