A Fault Diagnosis Approach for Rolling Element Bearings Based on RSGWPT-LCD Bilayer Screening and Extreme Learning Machine

The faults of rolling element bearings can result in the deterioration of machine operating conditions; how to assess the working condition and identify the fault of the rolling element bearing has become a key issue for ensuring the safe operation of modern rotating machineries. This paper presents a novel hybrid approach that detects bearing faults and monitors the operating status of rolling element bearings in modern rotating machineries. Based on redundant second-generation wavelet packet transform and local characteristic-scale decomposition, this method is implemented to extract the fault features, the vibration signal is adaptively decomposed into a number of desired intrinsic scale components by two-step screening processes based on the energy ratio, and reduce random noises and eliminate the pseudofrequency components. The fault features are then used to implement the identification classification of faults using singular value decomposition and extreme learning machine. The approach is evaluated by simulation and practical bearing vibration signals under different conditions. The experiment results show that the proposed approach is feasible and effective for the fault diagnosis of rolling element bearing.