Artificial neural network model for analysis of power system harmonics

Harmonic distortion analysis, which is necessary in order to improve the quality of power distributed, is traditionally achieved using fast Fourier transform (FFT) algorithm. FFT procedure is however susceptible to the presence of noise and subharmonics in the distorted signal. Further limitations arise due to the use of Radix-2 based FFT in harmonic analysis of power frequency (50 Hz or 60 Hz) signals. This paper presents a novel technique, based on neural networks, for analysis of power system harmonics.