Study on Denoising Method of Surface Defect Signal of Rail Based on CEEMD and Wavelet Soft Threshold

Abstract

Laser ultrasonic detection of rail defects has become a new method of rail nondestructive testing. Obtaining accurate rail defect signal is a prerequisite to judge the size of defects and avoid train accidents and ensure driving safety. In order to effectively improve the SNR of defect echo, a denoising algorithm combining CEEMD and wavelet soft threshold was proposed. First, CEEMD decomposition was performed on the signal to determine the demarcation point k of IMF components by autocorrelation function. The signal after k + 1 component was reconstructed. Then, the reconstructed signals were decomposed by wavelet transform. The high frequency coefficients after soft threshold processing and the low frequency coefficients of wavelet transform were reconstructed to complete the denoising of rail surface defect signals. The rail with defect of a depth of 0.5 mm and a width of 0.5 mm was tested and verified by laser ultrasonic experiment. By experiment the denoising method combining CEEMD and wavelet soft threshold suppressed effectively the noise. It retained the detailed characteristics of the defective reflected waves. It achieved the good denoising characteristics. It improves the signal-to-noise ratio by 7.12 and 0.77 dB, respectively, over the EMD denoising algorithm and CEEMD denoising algorithm at 1 dB noise intensity and improves the signal-to-noise ratio by 3.37 and 1.23 dB, respectively, over the EMD denoising algorithm and CEEMD denoising algorithm at 20 dB noise intensity.