Incipient Fault Feature Extraction of Rolling Bearing Based on Optimized Singular Spectrum Decomposition

Abstract

The incipient fault feature of rolling bearing is difficult to extract from vibration signals for the weak energy and nonstationarity. A method of extracting incipient bearing fault features was proposed in this paper, which based on the optimized singular spectrum decomposition (OSSD) with 1.5-dimensional symmetric differential energy operator (1.5D-SDEO) demodulation. First, the slime mould algorithm (SMA) is used to optimize the input parameter of the singular spectrum decomposition (SSD). Second, the bearing vibrational signal is decomposed into different singular spectrum components (SSC) by the proposed OSSD, and the SSC selected with the largest syncretic impact index (SII). Finally, the selected SSC is demodulated with 1.5D-SDEO, which uses symmetric differential energy operator (SDEO) instead of teager energy operator (TEO) in 1.5-dimensional TEO (1.5D-TEO). Simulation and experimental analysis were conducted to verify the validity of the proposed method. Results demonstrate that the proposed method could provide a new thought on the incipient fault feature extraction of rolling bearings.