Power quality disturbance classification utilizing S-transform and binary feature matrix method

This paper presents new features and a novel decision-making system for automated classification of power quality disturbances. The most common types of disturbances including flickers, harmonics, impulses, notches, outages, sags, swells, and switching transients are studied. Disturbances consisting of both sag and harmonic, or both swell and harmonic are also considered. It is assumed that the analyzed waveforms are available in sampled form. The signal processing techniques utilized to extract the distinctive features of the waveforms are Fourier and S-transform. A new method based on binary feature matrix is designed for making a decision regarding the disturbance type. Evaluation studies for verifying the accuracy of the method are presented.