A Study of Online Inspection for Multi-level Prognostics

Abstract A system’s degradation behavior is often correlated with internal and external covariates which are usually difficult to access owing to expensive measurement cost. This paper presents a Particle Filtering based multi-level prognostics approach to predict the Remaining Useful Life of a system based on its State of Health degradation estimation with online inspections of covariates. A degrading system is simulated with covariates at different level. By investigating the covariate online, the degradation estimation shows a better prediction and lower cost than the estimation without inspection.