Harmonic detection using feed forward and recurrent neural networks for active filters

Abstract

In this study, the methods to apply the feed forward and Elman's recurrent neural networks for harmonic detection process in active filter are described. Generally, Fourier transformation is used to analyze a distorted wave from power line, and a low pass filter is used to eliminate the fundamental wave before each harmonic component is detected. Due to this complicated process, the behaviour of active filter is delayed such that it is difficult to compensate harmonic in real time. In order to improve the processing speed and simplify harmonic detection process, the feed forward and Elman's recurrent neural networks are used to detect harmonics from distorted wave instead of Fourier transformation and low-pass filter. We simulated the distorted wave including the 5th, 7th, 11th, 13th harmonics and used these neural networks to recognize each harmonic. The results show that these neural networks are applicable to detect each harmonic effectively. (C) 2004 Elsevier B.V. All rights reserved.