PROJECT TITLE :

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

ABSTRACT:

The remaining helpful life (RUL) prediction of rolling component bearings has attracted substantial attention recently thanks to its importance for the bearing health management. The exponential model is one of the foremost widely used ways for RUL prediction of rolling part bearings. However, 2 shortcomings exist in the exponential model: one) the first predicting time (FPT) is chosen subjectively; and 2) random errors of the stochastic method decrease the prediction accuracy. To cope with these two shortcomings, an improved exponential model is proposed during this paper. In the improved model, an adaptive FPT selection approach is established primarily based on the interval, and particle filtering is utilised to scale back random errors of the stochastic process. So as to demonstrate the effectiveness of the improved model, a simulation and 4 tests of bearing degradation processes are utilized for the RUL prediction. The results show that the improved model is in a position to pick an acceptable FPT and reduce random errors of the stochastic method. Consequently, it performs higher in the RUL prediction of rolling element bearings than the initial exponential model.