Research on the fault diagnosis of rotating machinery based on wavelet analysis and fuzzy cluster

The three common faults of rotating machinery, that is, imbalance, misalignment and rubbing, were simulated on Bently, vibration displacements at every sampling time have been measured according to a certain time interval by using eddy current displacement sensor, then the time-vibration displacements of the three faults have been got, and the corresponding figures of time-displacement were drawn by using matlab 7.0. On the basis of wavelet analysis of vibration displacement signal, a feature extraction method based on scale-energy modulus was introduced and the fault type of extracted characteristic vector was identified by fuzzy cluster. The results show that this method is effective for common fault recognition of rotating machinery, and also have a certain reference value for maintenance of rotating machinery. This method can also be extended to other mechanical fault diagnosis.