Power quality disturbance waveform recognition using wavelet-based neural classifier - Part 1: Theoretical foundation

Existing techniques for recognizing and identifying power quality disturban ce waveforms are primarily based on visual inspection of the waveform, It i s the purpose of this paper to bring to bear recent advances, especially in wavelet transforms, artificial neural networks, and the mathematical theor y of evidence, to the problem of automatic power quality disturbance wavefo rm recognition. Unlike past attempts to automatically identify disturbance waveforms where the identification is performed in the time domain using an individual artificial neural network, the proposed recognition scheme is c arried out in the wavelet domain using a set of multiple neural networks. T he outcomes of the networks are then integrated using decision making schem es such as a simple voting scheme or the Dempster-Shafer theory of evidence . With such a configuration, the classifier is capable of providing a degre e of belief for the identified disturbance waveform.