Empirical Wavelet Transform and Its Application in Fault Feature Extraction of Rolling Bearings

Rolling bearing is one of the most widely used rotating machinery. For easy damage, it is a main problem in its fault diagnosis. Proposed in 2013, The Empirical Wavelet Transform (EWT), an adaptive signal decomposition method combining theoretical background of wavelet transform and the adaptivity of EMD. The theory of EWT is introduced in this essay and EWT is used in the fault feature extraction of rolling bearings for the decomposition of original signal. With kurtosis criterion, desired results are got. Compared with EMD, problems in mode mixing and illusive components is solved by EWT, which has fewer components and better efficiency in analysis.