Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method

Condition assessment is one of the most important techniques to realize the equipment's health management and condition based maintenance (CBM). This paper introduces a preprocessing model of the bearing using wavelet packet-empirical mode decomposition (WP-EMD) for feature extraction. Then it uses self-organization mapping (SOM) for the condition assessment of the performance degradation. To verify the superiority of the proposed method, it is compared with some traditional features, such as RMS, kurtosis, crest factor and entropy. Meanwhile, seventeen datasets from the bearing run-to-failure test are used to validate the proposed method. The analysis results from the bearing's signals with multiple faults show that the proposed assessment model can effectively indicate the degradation state and help us to estimate remaining useful life (RUL) of the bearings.