An improved feature extraction method for rolling bearing fault diagnosis based on MEMD and PE

The health condition of rolling bearing can directly influence to the efficiency and lifecycle of rotating machinery, thus monitoring and diagnosing the faults of rolling bearing is of great importance. Unfortunately, vibration signals of rolling bearing are usually overwhelmed by external noise, so the fault frequencies of rolling bearing cannot be readily obtained. In this paper, an improved feature extraction method called IMFs-PE, which combines the multivariate empirical mode decomposition with the permutation entropy, is proposed to extract fault frequencies from the noisy bearing vibration signals. First, the raw bearing vibration signals are filtered by an optimal band-pass filter determined by SK to remove the irrelative noise which is not in the same frequency band of fault frequencies. Then the filtered signals are processed by the IMFs-PE to get rid of the relative noise which is in the same frequency band of fault frequencies. Finally, a frequency domain condition indicator FFR(Fault Frequency Ratio), which measures the magnitude of fault frequencies in frequency domain, is calculated to compare the effectiveness of the feature extraction methods. The feature extraction method proposed in this paper has advantages of removing both irrelative noise and relative noise over other feature extraction methods. The effectiveness of the proposed method is validated by simulated and experimental bearing signals. And the results are shown that the proposed method outperforms other state of the art algorithms with regards to fault feature extraction of rolling bearing.