Early faint fault diagnosis of wheelset axlebox bearings in urban rail trains based on ICiSSA-MOMEDA

Abstract

Abstract Circulant Singular Spectrum Analysis (CiSSA) performs well in the decomposition and extraction of the periodic components of nonstationary signals. However, the decomposition of signals in complex environments suffers from spectral aliasing and difficulties in extracting feature information. Therefore, based on CiSSA, an improved CiSSA and multipoint optimal minimum entropy deconvolution adjustment (ICiSSA-MOMEDA) is proposed and applied to the early faint fault diagnosis of axlebox bearings of urban rail train wheelsets. First, the optimal embedding dimension was computed adaptively and accurately using an improved Cao’s method. Then, the initial components obtained from the decomposition were reorganized using the K-ARs method. ICiSSA effectively solves the problems of spectrum confusion and fault-information dispersion. Finally, ICiSSA was combined with MOMEDA to improve its ability to detect weak fault information. The superiority of ICiSSA-MOMEDA was verified based on the analysis of the actual bearing data and comparison with other methods.