A Time Frequency Analysis and Classification of Real Time Power Quality Disturbances via Signal Processing Techniques and Back-Propagation Algorithm

Abstract

This paper develops a real time solution for detecting the Power Quality events. By a voltage Data Acquisition Card, NI DAQ-9225, fourteen Power Quality events are acquired by the Virtual Instrument software package. The acquired data in time domain is transformed into frequency domain by Stockwell Transform and Wavelet Packet Transform. The features extracted from the transformation are fed into the Back Propagation Neural Network for training which aids in automatic classification of Power Quality Events. A combination of the signal processing techniques and Neural Networks are employed to detect and characterize the real time Power Quality Disturbances. The result obtained shows the effectiveness of the Stockwell Transform based Back Propagation algorithm over the Wavelet Transform based Back Propagation Algorithm in classifying the Power Quality Disturbances. The result produced by the proposed methodology is validated with the Power Quality Analyser.