Quantifying reliability uncertainty from catastrophic and margin defects: A proof of concept

We aim to analyze the effects of component level reliability data, including both catastrophic failures and margin failures, on system level reliability. While much work has been done to analyze margins and uncertainties at the component level, a gap exists in relating this component level analysis to the system level. We apply methodologies for aggregating uncertainty from component level data to quantify overall system uncertainty. We explore three approaches towards this goal, the classical Method of Moments (MOM), Bayesian, and Bootstrap methods. These three approaches are used to quantify the uncertainty in reliability for a system of mixed series and parallel components for which both pass/fail and continuous margin data are available. This paper provides proof of concept that uncertainty quantification methods can be constructed and applied to system reliability problems. In addition, application of these methods demonstrates that the results from the three fundamentally different approaches can be quite comparable.

► We develop three distinct methods for quantifying reliability uncertainty for complex systems.
► We illustrate our three methods using a system of mixed series and parallel components.
► We show that the methods (Method of Moments, Bayesian, and Bootstrap) are comparable.
► We provide a proof-of-concept for quantifying uncertainty about system reliability.