A prognostic model for degrading systems with randomly arriving shocks

Abstract

Remaining useful life (RUL) has been attached great importance for the health management of stochastic degrading systems. However, current studies place main focus on continuous degradation processes of systems without the consideration of randomly arriving shocks from changes in inner conditions or external environments. In this paper, we present a new prognostic model to characterize the continuous degradation and randomly arriving shocks. Specifically, we first adopt a Wiener process with a linear drift to characterize the continuous dynamics of the degradation process. In order to model randomly arriving shocks, we propose to use a compound Poisson process to model the impacts on the system's continuous degradation. Under the proposed modeling framework, the probability density function of the estimated RUL is derived and can be updated with the measured degradation data. Finally, a numerical example is provided to illustrate the results of the presented method.