Neural Network and Daubechies Wavelet in Power System Protection.

Abstract

Wavelet theory is a mathematical tool which has been developed independently for various signal processing applications: multiresolution signal processing, subband coding and wavelet expansion. The Wavelet Transform (WT) has become an important tool for power engineering, because it is an alternative to classical methods (the Fourier Transform). This form of signal analysis is far more efficient than Fourier in cases where a signal is dominated by transient behaviour or discontinuities. Neural networks are appropiate and especially powerfull when they are used to find such relationships that are difficult to describe explicity. This work explains a neural network-wavelet based protection relay.