Denoising technique for partial discharge signal : A comparison performance between artificial neural network, fast fourier transform and discrete wavelet transform

Abstract

This paper presents de-noising of PD signal using three different techniques; ANN, FFT and DWT. The objective of this paper is to yield the PD signal from the disturb signal which is the combination of PD and noise signal. These signals are generated using EMTP-ATP simulation environment. This research used the straightforward procedure in the de-noising technique. The accuracy of the de-noising is based on the calculation of SNR. The result of this research shows ANN is the best de-noising technique as the calculated SNR is the highest with 0.635938, followed by FFT technique with SNR of 0.452903 and lowest SNR is DWT with -0.154054.