Fast Spectral Correlation Based on Sparse Representation Self-Learning Dictionary and Its Application in Fault Diagnosis of Rotating Machinery

Abstract

Rolling element bearing and gear are the typical supporting or rotating parts in mechanical equipment, and it has important economy and security to realize their quick and accurate fault detection. As one kind of powerful cyclostationarity signal analyzing method, spectral correlation (SC) could identify the impulsive characteristic component buried in the vibration signals of rotating machinery effectively. However, the fault feature such as impulsive characteristic component is often interfered by other background noise, and the situation is serious especially in early weak fault stage. Besides, the traditional SC method has a drawback of low computation efficiency which hinders its wide application to some extent. To address the above problems, an impulsive feature-enhanced method which combines fast spectral correlation (FSC) with sparse representation self-learning dictionary is proposed in the paper. Firstly, the sparse representation self-learning dictionary method-K-means singular value decomposition (KSVD) is improved and the improved KSVD (IKSVD) method is used to denoise the original signal, and the periodic impulses are highlighted. Then, the FSC algorithm is applied on the denoised signal and spectral correlation image could be obtained. Finally, the calculated enhanced envelope spectrum (EES) of the denoised signal is obtained by using the spectral correlation image to identify the accurate fault position. The feasibility and superiority of the proposed method is verified through simulation, experiment, and engineering application.