Multiple Faults Detection for Rotating Machinery Based on Bicomponent Sparse Low-Rank Matrix Separation Approach

Multifault detection of rotating machinery at the incipient fault stage presents a challenging issue due to its interaction feature, complexity, and coupling characteristics. Aiming at the concern of identifying the multiple faults pattern of rotating machinery, a novel multiple faults detection approach based on Bi-component sparse low-rank matrix separation is proposed in this paper. The core idea of the proposed method is that the measured vibration signal typically shows as the sum of transient component and oscillatory component, meanwhile, the multi-fault identification problem with regularization terms can be transformed into a sparse optimization formulation that could be solved by the alternating direction method of multipliers algorithm. The proposed approach is applied by simulated synthetic signal, experimental data including rolling bearing and gearbox with weak multiple faults, and its effectiveness and superiority are verified by comparing to some state-of-the-art methods such as L1-norm fused lasso optimization, maximum correlated kurtosis deconvolution, and ensemble empirical mode decomposition.