Rolling Bearing Remaining Useful Life Prediction Based On Wiener Process

Abstract

Rolling bearing is the key part of mechanical system. Accurate prediction of bearing life of can reduce maintenance costs, improve availability and prevent catastrophic consequences. Aiming at solving the problem of the nonlinear, random and small sample problems faced by rolling bearings in actual operating conditions. In this work, the nonlinear Wiener process with random effect and unbiased estimation of unknown parameters are used to predict the remaining useful life of rolling bearings. Firstly, random effects and nonlinear parameters are added to the traditional Wiener process, and a parameter unbiased estimation method is used to estimate the positional parameters of the constructed Wiener model. Finally, the model is validated using a common set of bearing datasets. Experimental results show that compared with the traditional maximum likelihood function estimation method, the parameter unbiased estimation method can effectively improve the accuracy and stability of the parameter estimation results. The model has a good fitting effect, which can accurately predict the remaining useful life of rolling bearing.

Conflict of Interest Statement
The authors declare no conflicts of interest.