Multiple power quality event detection and classification using a modified S-transform and WOA tuned SVM classifier. (4th August 2021)

• Record Type: Journal Article
• Authors: Dash, Sambit; Subudhi, Umamani
• Is Part Of: International journal of power and energy conversion. Volume 12:Number 4(2021)
• Page Start: 338
• Page End: 363
• Publication Date: 2021-08-04
• Subjects: power quality -- PQ -- modified S-transform -- MST -- whale optimisation algorithm -- WOA -- support vector machine -- SVM -- classification; Energy conversion -- Periodicals; Power resources -- Periodicals; Electric power production -- Periodicals; 621.31205
• Languages: English
• ISSNs: 1757-1154

Abstract

In this paper, a novel method for the classification of power quality events is illustrated. Fifteen types of power quality events consisting of single and multi-stage disturbances are considered for the study. A database of the synthetic PQ events is generated in MATLAB using mathematical models. The generated signals are passed through a novel modified Stockwell transform consisting of a second-order Gaussian window that provides the ST matrix. From the ST matrix, various statistical features such as energy and standard deviation of the magnitude and phase contour are extracted and given as input to support vector machine (SVM). Furthermore, to improve the performance of SVM, a novel meta-heuristic technique called whale optimisation algorithm (WOA) is used to tune the hyperparameters of the SVM classifier. The performance of the proposed method is analysed under noisy and noiseless conditions. It is observed that WOA tuned SVM provides improved classification accuracy than other widely used meta-heuristic optimisation algorithms such as particle swarm optimisation (PSO) tuned SVM and genetic algorithm (GA) tuned SVM. Further, two novel circuits for the generation of sag, swell, and interrupt are developed and the proposed technique is validated on real-time signals obtained from the circuits.