Bearing Degradation Evaluation Using Recurrence Quantification Analysis and Kalman Filter

This paper presents an integrated approach, which combines recurrence quantification analysis (RQA) with the Kalman filter, for bearing degradation evaluation. The RQA, a nonlinear signal processing method, is applied to extracting recurrence plot entropy features from vibration signals as input to build an autoregression (AR) model. This AR model is used to estimate parameters of the dynamic model of the bearing, and the Kalman filter is then utilized to obtain optimal prediction results on the bearing degradation state from its dynamic model. Case studies performed on two test-to-failure experiments indicate that the presented approach can predict occurrence of the bearing failure 50 min in advance.