Study on Fault Detection of Rolling Element Bearing Based on Translation-Invariant Denoising and Hilbert-Huang Transform

In order to detect rolling element bearing faults from strong background noise, a new method based on translation-invariant denoising (TID) and hilbert-huang transform (HHT) is proposed. Firstly, the original vibration signals are preprocessed using TID to suppress abnormal interference of noise to improve the decomposition quality of HHT. Secondly, the denoised signals are decomposed into a set of intrinsic mode functions (IMFs) during empirical mode decomposition (EMD) process of HHT. Hilbert spectral analysis is further played on IMFs to capture the bearing defect frequencies. The performance of the proposed method is tested, and the experiment results show that this method can effectively extract the fault features of bearing and recognize the faults successfully. So the proposed method is a good-suited technique for bearing fault detection.