Application of correlation dimension and EMD-based AR model in the fault diagnosis

A fault diagnosis approach for rotor systems based on correlation dimension is proposed.The EMD method is used to decompose the rotor vibration signal into several intrinsic mode functions(IMFs).The AR models of some IMF components which contain main fault information are constructed.Finally,the correlation dimensions of auto-regressive parameters in AR model are calculated and input into the neural network as feature vectors.The working state and fault pattern of the rotor system can be identified by the neural network.The analysis results of the experimental data show that the proposed approach can be applied to the fault diagnosis for rotor system efficiently.