An enhanced Hilbert–Huang transform technique for bearing condition monitoring

A new technique, enhanced Hilbert–Huang transform (eHHT), is proposed in this work for fault detection in rolling element bearings. It includes two processes: firstly, the collected vibration signal is denoised to highlight defect-related impulses; and secondly the denoised signal is further processed by the use of the proposed eHHT technique to identify the defect features for bearing fault detection. Signal denoising is carried out by the use of the minimum entropy deconvolution filter to reduce impedance effect of the transmission path of the measured signal. In the proposed eHHT, a novel strategy is proposed to enhance feature extraction based on the analysis of correlation and mutual information. The effectiveness of the proposed eHHT technique in feature extraction and analysis is verified by a series of experimental tests corresponding to different bearing conditions. Its robustness is examined by using data sets from a different resource.