Analysis of Power Quality Disturbances using Wavelet Transform

Power quality is under the influence of the variety of small or large disturbances during operating conditions. Any type of disturbance has almost a specific pattern. Any pattern which can be classified possesses a number of distinguishing features. Thus, the first step in any classification process is to consider the problem of what discriminatory features to select and how to extract these features from the patterns. It is quite clear that the number of features needed for prosperous classification depends on the distinguishing quality of the chosen characteristic. Over the recent decades, several different techniques have been adopted for the choice of features in power quality pattern recognition. The power quality disturbances like voltage sag, swell, notch, spike, transients etc can be analyzed using various transform techniques such as Fourier transform, Chriplet transform, S-transform and Wavelet transform. Wavelet transform has received greater attention in power quality as this is well suited for analyzing certain types of transient waveforms. In this seminar, Energy Difference Multi-Resolution Analysis technique (EDMRA) is used to decompose the power quality disturbances. This Paper discusses an appropriate type of features be identified then suitable features be extracted. For this purposes, for extracting of discriminative features of power quality by using MRA, at first an appropriate wavelet must be identified respect to each of the input sampled window. To improve the time resolution of faulty waveforms, the waveform must be broken into a set of sub-waveforms by using of MRA. Then classification of PQ disturbances is performed using pattern recognition.