A group sparse representation method in frequency domain with adaptive parameters optimization of detecting incipient rolling bearing fault

Abstract

The periodic impulses are the most important signatures of rolling bearing failure, which are often buried by excessive background noise. It is challenging to extract the incipient periodic impulses in the vibration fault signal. In this paper, we propose a group sparse representation denoising method in frequency domain of extracting the incipient periodic impulses for rolling bearings fault diagnosis. First, we reveal the sparsity within and across groups (SWAG) property of the bearing fault signal in frequency domain. Afterwards, a penalty function promoting SWAG is employed to construct the denoising model in frequency domain. To achieve better feature extraction results, a guided periodic information index is proposed to construct the objective function of Moth-Flame optimization (MFO) algorithm for adaptively optimizing regularization parameters of the proposed denoising model. Lastly, simulation and experimental results indicate that the proposed MFO-SWAG method can accurately maintain the weak fault feature while suppressing the noise effectively. Compared with other state-of-art methods, the proposed method shows better performance of extracting the incipient fault feature of rolling bearings.