Remaining useful life prediction of individual units subject to hard failure

Abstract

To develop a cost-effective condition-based maintenance strategy, accurate prediction of the Remaining Useful Life (RUL) is the key. It is known that many failure mechanisms in engineering can be traced back to some underlying degradation processes. This article proposes a two-stage prognostic framework for individual units subject to hard failure, based on joint modeling of degradation signals and time-to-event data. The proposed algorithm features a low computational load, online prediction, and dynamic updating. Its application to automotive battery RUL prediction is discussed in this article as an example. The effectiveness of the proposed method is demonstrated through a simulation study and real data.