A Hybrid Prognostics Technique for Rolling Element Bearings Using Adaptive Predictive Models

Rolling element bearings cause the largest number of failures in induction motors. Predicting an impending failure and estimating the remaining useful life (RUL) of a bearing is essential for scheduling maintenance and avoiding abrupt shutdowns of critical systems. This paper presents a hybrid technique for bearing prognostics that utilizes regression-based adaptive predictive models to learn the evolving trend in a bearing's health indicator. These models are then used to project forward in time and estimate the RUL of a bearing. The proposed algorithm addresses some key issues in existing methods for bearing health prognosis that affect their prognostic performance, specifically determining the time to start prediction (TSP), handling random fluctuations in a bearing's health indicator, and setting a dynamic failure threshold. The proposed algorithm is validated on publicly available bearing prognostics data from the Center for Intelligent Maintenance Systems. Experimental results show that the proposed approach is effective in determining an accurate TSP and failure threshold, as well as handling random fluctuations. Moreover, this approach achieves excellent prognostic performance and estimates the RUL of bearings within the specified error bounds, even at points very close to the TSP, where traditional methods yield relatively poor RUL estimates.