An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings

TLDR

Remaining useful life prediction of rolling element bearings is critical for health management, yet the widely used exponential model suffers from subjective first‑predicting‑time selection and random‑error‑induced inaccuracies. This study proposes an improved exponential model to overcome those two shortcomings. The model incorporates a 3σ‑interval based adaptive FPT selection and particle filtering to mitigate stochastic errors, and its effectiveness is demonstrated through simulation and four bearing degradation tests. Results show the improved model selects appropriate FPT, reduces random errors, and achieves superior RUL predictions compared to the original exponential model.

Abstract

The remaining useful life (RUL) prediction of rolling element bearings has attracted substantial attention recently due to its importance for the bearing health management. The exponential model is one of the most widely used methods for RUL prediction of rolling element bearings. However, two shortcomings exist in the exponential model: 1) the first predicting time (FPT) is selected subjectively; and 2) random errors of the stochastic process decrease the prediction accuracy. To deal with these two shortcomings, an improved exponential model is proposed in this paper. In the improved model, an adaptive FPT selection approach is established based on the 3σ interval, and particle filtering is utilized to reduce random errors of the stochastic process. In order to demonstrate the effectiveness of the improved model, a simulation and four tests of bearing degradation processes are utilized for the RUL prediction. The results show that the improved model is able to select an appropriate FPT and reduce random errors of the stochastic process. Consequently, it performs better in the RUL prediction of rolling element bearings than the original exponential model.