A hybrid prognostic framework for rolling bearings based on health indicator construction and the Wiener process model

Abstract

As a critical component of the rotating machinery, the rolling bearing bears significant responsibility for the stable operation of the machinery. Meanwhile, the hybrid prognostic framework for rolling bearings can integrate the advantages of stochastic process models and deep learning methods. In this paper, a hybrid prognostic framework for rolling bearings based on health indicator construction and the Wiener process model is proposed. Experimental results illustrate that the hybrid prognostic framework can automatically construct the HI of rolling bearings as well as exhibit superior performance on the XJTU-SY bearing dataset.