Bearing remaining life prediction using Gaussian process regression with composite kernel functions

There is an urgent demand for life prediction of bearing in industry. Effective bearing degradation assessment technique is beneficial to condition based maintenance (CBM). In this paper, Gaussian Process Regression (GPR) is used for remaining bearing life prediction. Three main steps of prediction schedule are presented in details. RMS, Kurtosis and Crest factor are used for feature fusion by self-organizing map (SOM). Minimum Quantization Error (MQE) value derived from SOM is applied to represent the condition of bearing. GPR models with both single and composite covariance functions are presented. After training, new MQE value can be predicted by the GPR model according to previous data points. Experimental results show that composite kernels improve the accuracy and reduce the variance of prediction results. Compared with particle filter (PF), GPR model can predict the remaining life of bearings more accurately.