LAUSR

Abstract A linear (circular) consecutive-k-out-of-n: F (Con/k/n: F) system consists of n components that are linearly (circularly) arranged such that the system fails if and only if at least k consecutive components fail. The safe design of these systems is to find an optimal arrangement of components to maximize systems’ reliability. Even though, many efforts have been devoted to the optimal arrangement problems for such systems, uncertainties about the reliabilities of components and system structure have never been deeply studied in the optimal arrangement problems before. This paper proposes a heuristic approach using an imprecise probabilistic graphical model called Valuation-Based System (VBS), and imprecise importance measures to perform the safe design of linear Con/k/n: F systems under data uncertainty (related to the failure data of components) and model uncertainty (related to the system structure). Moreover, the proposed approach is applied on the safe design of an oil transportation system.