Fault Diagnosis of Rolling Bearing Based on Improved Independent Component Analysis and Cepstrum Theory
Based on the advantages of independent component analysis (ICA) and cepstrum, this paper adopts a novel feature extraction scheme for rolling bearing fault diagnosis utilizing improved independent component analysis and cepstrum analysis. Firstly, the fast fixed-point algorithm (FastICA) based on negative entropy was used here as the ICA approach to separate the mixed observation signals of rolling bearing vibration. Then, the largest spectral kurtosis value was used to confirm the characteristic separated signal associated with the Rolling bearing faults. Finally, cepstrum analysis was employed to deal with the selected signal to extract the original fault feature. The experimental results show that sensitive fault feature can be extracted prominently after the presented processing, and the proposed diagnostic method is effective for the fault diagnosis of rolling bearing. In addition, the proposed method provides an effective technical means for weak fault diagnosis.