An Application of Elman’s Recurrent Neural Networks to Harmonic Detection

Abstract

In this study, the method to apply the Elman’s recurrent neural networks for harmonic detection process in active filter is proposed. The feed forward neural networks were also used for comparison. We simulated the distorted wave including 5th, 7th, 11th, 13th harmonics and used them for training of the neural networks. The distorted wave including up to 25th harmonics were prepared for testing of the neural networks. Elman’s recurrent and feed forward neural networks were used to recognize each harmonic. The results show that these neural networks are applicable to detect each harmonic effectively.KeywordsBack PropagationRecurrent Neural NetworkPower QualityTotal Harmonic DistortionDistorted WaveThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.