Virtual Power Quality Disturbance Classifier using Knowledge-based Neural Network

Abstract

This paper develops a LabVIEW based instrumentation for the classification of power quality (PQ) disturbances. Initially, the wavelet packet transform (WPT) is employed for the extraction of the 50 Hz component and decomposition of a distorted voltage signal into uniform bands. Then seven essential features are extracted from the decomposed signal coefficients. The knowledge-based neural network (KBNN) is a combined model of neural network and rule-based approach. This paper explores the potential of the KBNN for the classification of the most common power quality disturbances. The efficacy of the KBNN approach is evaluated on a wide range of time-varying signals with noise, fundamental frequency deviation, and variation in signal parameters. The implementation in LabVIEW and experimental results elucidate the efficiency and robustness of the proposed PQ disturbance classifier using KBNN.