Application of improved wavelet total variation denoising for rolling bearing incipient fault diagnosis

2018 International Conference on Material Strength and Applied Mechanics

材料科学;力学

Zhang, W.^1 ; Jia, M.P.^1

School of Mechanical Engineering, Southeast University, Nanjing

211189, China^1

关键词: Alternating direction method of multiplier (ADMM);    Bearing fault diagnosis;    Control parameters;    Incipient fault diagnosis;    Joint optimization;    Optimal wavelets;    Rolling bearings;    Time-frequency planes;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/372/1/012030/pdf
DOI  :  10.1088/1757-899X/372/1/012030

来源: IOP

【 摘 要 】

When incipient fault appear in the rolling bearing, the fault feature is too small and easily submerged in the strong background noise. In this paper, wavelet total variation denoising based on kurtosis (Kurt-WATV) is studied, which can extract the incipient fault feature of the rolling bearing more effectively. The proposed algorithm contains main steps: a) establish a sparse diagnosis model, b) represent periodic impulses based on the redundant wavelet dictionary, c) solve the joint optimization problem by alternating direction method of multipliers (ADMM), d) obtain the reconstructed signal using kurtosis value as criterion and then select optimal wavelet subbands. This paper uses overcomplete rational-dilation wavelet transform (ORDWT) as a dictionary, and adjusts the control parameters to achieve the concentration in the time-frequency plane. Incipient fault of rolling bearing is used as an example, and the result shows that the effectiveness and superiority of the proposed Kurt- WATV bearing fault diagnosis algorithm.