Abstract
As a critical part of prognostics and health management (PHM), remaining useful life (RUL) prediction can provide manufacturers and users with system lifetime information and improve the reliability of maintainable systems. Particle filters (PFs) are powerful tools for RUL prediction because they can represent the uncertainty of results well. However, due to the lack of measurement data, the parameters of the measurement model cannot be updated during the long-term prediction process. Additionally, for complex systems, the measurement model of a system often cannot be obtained in an analytical form. In this paper, a fusion prognostic method based on an extended belief rule base (EBRB) and a PF is designed to solve these problems. In the proposed framework, a double-layer maximum mean discrepancy-extended belief rule base (DMMD-EBRB) model with time delay is adopted to estimate and predict the hidden behavior of a degrading system. The unknown parameters of the degradation model are identified by the PF using the output of the EBRB. Afterwards, the system state is further predicted by the PF. The effectiveness of the proposed method is validated with the NASA-PCoE and CALCE lithium-ion battery degradation experiment datasets. In addition, several other related fusion methods are investigated for comparison with the proposed method. The experiments show that the proposed method yields better performance than the existing methods.
Highlights
Prognostic methods aim to provide reliable remaining useful life (RUL) predictions for critical components and systems with degrading processes
To address the problems of the existing fusion methods, a novel double-layer maximum mean discrepancy-extended belief rule base (DMMD-EBRB)-based fusion prognostic framework is proposed in this article for RUL prediction
DMMD-EBRB MODEL CONSTRUCTION 1) SELECTION OF THE RULE DATA Because the effect of EBRB is restricted by the rule activation mode, this paper proposes a structure and parameter optimization method based on MMD
Summary
Prognostic methods aim to provide reliable remaining useful life (RUL) predictions for critical components and systems with degrading processes. Zhang et al [17] proposed the combination of relevance vector machines (RVMs) and particle filtering, and proposed a fusion prediction method under the condition of small samples Another approach is based on neural networks, such as ANNs [11], adaptive neuro fuzzy (ANF) systems [12]. To address the problems of the existing fusion methods, a novel double-layer maximum mean discrepancy-extended belief rule base (DMMD-EBRB)-based fusion prognostic framework is proposed in this article for RUL prediction. On this basis, the RUL prediction of the lithium-ion battery is studied. According to the calculated rule activation weight, this paper uses the evidence reasoning method to obtain the belief distribution of the result. This paper uses the MMD to calculate the similarity of two feature matrices and the KTST to test whether they obey the same distribution
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have