Abstract
Singular value decomposition (SVD) methods have aroused wide concern to extract the periodic impulses for bearing fault diagnosis. The state-of-the-art SVD methods mainly focus on the low rank property of the Hankel matrix for the fault feature, which cannot achieve satisfied performance when the background noise is strong. Different to the existing low rank-based approaches, we proposed a simultaneously low rank and group sparse decomposition (SLRGSD) method for bearing fault diagnosis. The major contribution is that the simultaneously low rank and group sparse (SLRGS) property of the Hankel matrix for fault feature is first revealed to improve performance of the proposed method. Firstly, we exploit the SLRGS property of the Hankel matrix for the fault feature. On this basis, a regularization model is formulated to construct the new diagnostic framework. Furthermore, the incremental proximal algorithm is adopted to achieve a stationary solution. Finally, the effectiveness of the SLRGSD method for enhancing the fault feature are profoundly validated by the numerical analysis, the artificial bearing fault experiment and the wind turbine bearing fault experiment. Simulation and experimental results indicate that the SLRGSD method can obtain superior results of extracting the incipient fault feature in both performance and visual quality as compared with the state-of-the-art methods.
Highlights
Rolling element bearings (REB) are key components in the industrial mechanical systems such as wind turbine, high speed railway, aeroengine, etc., which are designed for long-term safe working-corrosion, some potential failures might occur on the rolling bearing surface [1]
The Hankel matrix was reconstructed from the original vibration signal to performance the Singular value decomposition (SVD), where the relative change rate of singular value kurtosis was adopted to determine the reconstructed order of singular values
One possible reason isofthat the low rank appears propertywith is suppressed while the group maximum, the performance degradation method the further increasing of the short analysis, it is not hard for us to find that the maximum autocorrelation impulses harmonic to noise (AIHN) equals to 0.2614 when the sparse property leadingisrole the regularization model of simultaneously low rank and group sparse decomposition (SLRGSD)
Summary
Rolling element bearings (REB) are key components in the industrial mechanical systems such as wind turbine, high speed railway, aeroengine, etc., which are designed for long-term safe working. The kurtosis was employed to identify the periodic impulsive feature Followed by this idea, Li and Liu et al [38] presented a combined approach that integrate the singular value decomposition, singular value kurtosis and optimized frequency band entropy, named as SVD-SVK-OFBE, for bearing fault diagnosis. Li and Liu et al [38] presented a combined approach that integrate the singular value decomposition, singular value kurtosis and optimized frequency band entropy, named as SVD-SVK-OFBE, for bearing fault diagnosis In this context, the Hankel matrix was reconstructed from the original vibration signal to performance the SVD, where the relative change rate of singular value kurtosis was adopted to determine the reconstructed order of singular values. Different from the current low-rank oriented fault diagnosis approach, the new diagnostic framework is proposed to prompt SLRGS property for the Hankel matrix of the fault feature pattern.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have