A Method for Performance Degradation Assessment of Wind Turbine Bearings Based on Hidden Markov Model and Fuzzy C-means Model

Bearings used in the wind turbine generators (WTGs) will subject to different degrees of damage during operation, including all kinds of vibration and shock. In this paper, a vibration-based performance degradation assessment method for high-speed shaft wind turbine bearings is proposed using fusion of Hidden Markov Model (HMM) and Fuzzy C-means Model (FCM). The wavelet packet decomposition is used to extract the energy of the wavelet packet nodes of the whole life cycle vibration signal. The autoregressive model (AR) extracts the coefficients and residual of the wavelet packet nodes, and takes the two features as the combined features. The FCM is established using the normal and failure samples and the HMM is established using the normal samples. The two degradation indicators which was obtained by imputing the under test data to FCM and HMM model are input to the FCM model as the input characteristic. Then the performance degradation curve is obtained. Finally, Mahalanobis distance (MD) and FCM models are combined to compare and illustrate. The method combines the advantages of spatial statistical distance model and probabilistic statistical model. Then the WTG bearing's experimental data are used and the experimental results of AR model combined with FCM model are compared to verify the conclusions of this paper. The experimental analysis shows that the method is consistent with the performance degradation trend of rolling bearings and has certain adaptability.