Power Quality Disturbance Detection and Classification using Stockwell Transform and Pattern Recognition Techniques

Abstract

This work presents a simple approach for the automatic recognization of power quality (PQ) disturbances using stockwell transform (ST). In general, 18 variety of PQ disturbance signals consisting of simple and complex nature are studied in view of the IEEE-1159 standard. Here, 3.2kHz sampling frequency is used on fifteen cycles of the distorted waveform for the features extraction by ST. To increase the classifier strength, the sequential forward selection (SFS) is used for optimal feature selection. The selected features are input to different classifiers and their outputs are compared to find the best classifier. The classification techniques included in this work are random forest (RF), artificial neural network (ANN), k-neighbor neural network (KNN), support vector machine (SVM), extreme learning machine (ELM), and probabilistic neural network (PNN).