Multiple power quality event detection and classification using a modified S-transform and WOA tuned SVM classifier

In this paper, a novel method for classification of power quality events is illustrated. 15 types consisting single and multi-stage disturbances are considered study. A database the synthetic PQ generated in MATLAB using mathematical models. The signals passed through Modified Stockwell transform second order gaussian window which provides ST matrix. From matrix various statistical features such as energy standard deviation magnitude phase contour extracted given input to Support Vector Machine (SVM). Furthermore, improve performance SVM, meta-heuristic technique called Whale Optimization Algorithm (WOA) used tune hyper parameters SVM classifier. proposed analyzed under noisy noiseless conditions. It observed that WOA tuned improved accuracy than other widely optimization algorithms Particle Swarm (PSO) Genetic (GA) SVM. Further, two circuits generation sag, swell interrupt developed validated on real time obtained from circuits.