Abstract
It is common to assume that there is only one degradation mechanism in the system in recent works on prognostics focusing on estimation of the remaining useful life (RUL) of an electromechanical system. However, there are cases in which the system may be subjected to more than one failure (degradation) mechanisms due to different stress factors, types of components and their interactions with one another. Recently, we proposed an approach for estimation of RUL of the system with multiple failure mechanisms using the particle filter algorithm and Akaike Information Criteria (AIC). However, it is well known that standard particle filter suffers from sample degeneracy and impoverishment. In this study, we introduce the Heuristic Kalman algorithm (HKA), a metaheuristic optimization approach, in combination with particle filtering to tackle sample degeneracy and impoverishment issues and use it for improved prediction / estimation the RUL distribution of any system with multiple failure (degradation) mechanisms.