Performance Analysis of Wavelet Thresholding Methods Using DTCWT for Denoising of Vibration Signals

This paper presents a robust technique for denoising of vibration signals corrupted by Additive White Gaussian Noise. The proposed method uses Dual Tree Complex Wavelet Transform (DTCWT) and is very efficient due to its shift invariance property and reduced aliasing effect. While using DTCWT, we are comparing Different Threshold selections. The threshold value is selected using Universal, Rigrsure, Heursure and Minimaxi methods and is level adaptive. The best results are obtained by the threshold value selection using ‘Minimaxi’ threshold at low values of noise standard deviation and using ‘Universal’ threshold at higher values of noise standard deviation. Experiments are carried out on simulated vibration signals as well as on real time faulty signal. The comparison of the results of the proposed methods using DTCWT for synthetic signal is done using the signal to noise ratio (SNR). Higher SNR is gained compared to traditional denoising method. For comparison of results of the real time signal, another statistical parameter ‘Kurtosis’ is chosen.