A fault diagnosis method for roller bearing based on empirical wavelet transform decomposition with adaptive empirical mode segmentation

This paper proposes a fault diagnosis method for roller bearings based on the decomposition of vibration signals using the empirical wavelet transform (EWT) with adaptive empirical mode segmentation and the merging of redundant empirical modes. The proposed method employs scale-space histogram segmentation to determine the boundaries of the empirical modes adaptively, which helps to eliminate the effect of noise and obtain meaningful empirical modes that are more reflective of fault characteristics. In addition, the method merges similar empirical modes to rectify the tendency of conventional EWT to overly decompose empirical modes for fault feature extraction. To this end, an effective merging algorithm based on Pearson's correlation coefficient is developed to divide the empirical modes into groups according to their similarity prior to merging, which avoids a large increase in the amplitude of the signal after merging, and ensures the accuracy of the final result. The performance of the proposed method is first tested using an analytically derived signal. Then, the method is tested using actual vibration signals of roller bearings collected by NASA. The results demonstrate that the proposed method can identify fault information effectively and accurately.