Application of a Novel Spectral Sparse Adaptive Decomposition for Bearing Fault Diagnosis

The feature mode decomposition (FMD) method has been proven to possess outstanding performance in bearing compound fault diagnosis. Nevertheless, the method exhibits limitations in terms of feature characterization, especially for the cyclostationary characteristic of bearing faults, due to the restrictions of its time-domain indicator, while its suboptimal equal frequency band division strategy may distort signal components during the filter initialization process, degrading the subsequent decomposition performance. To mitigate these constraints, a novel spectral sparse adaptive decomposition (SSAD) method is developed in this article. The method begins by implementing the trend spectrum (TS)-guided strategy for filter initialization, which maintains the intact decomposition of the signal components through intelligent frequency band division. Building upon this foundation, SSAD incorporates square envelope spectral kurtosis (SESK) as its decomposition objective, specifically designed to capture the cyclostationary characteristic of bearing faults. The decomposition process is further enhanced through the application of the eigenvalue algorithm (EVA), enabling precise identification of multiple fault signatures. In the final stage, the envelope spectrum (ES)-domain correlation coefficient (ESCC)-based screening strategy effectively discards redundant modes, ensuring the acquisition of the optimal decomposition results. Simulation and experimental validations confirm that SSAD significantly outperforms conventional methods, demonstrating superior capability in fault feature extraction.