Fault diagnosis of rolling element bearing based on a new noise-resistant time-frequency analysis method

When fault arises in the rolling element bearing, the time-domain waveform of fault vibration signal will take on the characteristic of cyclostationarity, and the spectral correlation (SC) or spectral correlation density (SCD) basing on second order cyclic statistic is an effective cyclostationarity signal processing method. However, when the fault signal is surrounded by strong background noise, the traditional signal processing methods such envelope demodulation analysis and SC would not work effectively. The paper improves the SC method and a new time-frequency analysis method naming improved spectral correlation (ISC) is proposed. The proposed method is much more noise-resistant than SC through the verification of simulation analysis results. Besides, it takes on modulation phenomenon usually when fault arises in the rolling element bearing and the aim of fault feature extraction is to extract the fault characteristic frequency only or cyclic modulation frequency and the modulated frequency or carrier frequency buried in the object vibration signal is neglected. So, the paper improves the ISC further and the improved ISC (IISC) is proposed. The IISC will extract the modulation frequency only and it has the advantages of much clearer expression effect and better extraction effect. The effectiveness and feasibility of the proposed method are verified through the three kinds of fault (inner race fault, outer race fault and rolling element fault) of rolling element bearing. Besides, the advantages of the proposed method over the other relative time-frequency analysis methods such as ensemble empirical mode decomposition (EEMD) and spectral kurtosis (SK) are also presented in the paper.