Multiobjective optimization of redundancy allocation in systems with imperfect repairs via ant colony and discrete event simulation

Redundancy Allocation Problems (RAPs) are among the most relevant topics in reliable system design and have received considerable attention in recent years. However, proposed models are usually built based on simplifying assumptions about the system reliability behavior that are hardly met in practice. Moreover, the optimization of more than one objective is often required as, for example, to maximize system reliability/availability and minimize system cost. In this context, a set of nondominated solutions-system designs with compromise values for both objectives-are of interest. This paper presents an ACO approach for multiobjective optimization of availability and cost in RAPs considering repairable systems Subjected to imperfect repairs handled via Generalized Renewal Processes. The dynamic behavior of the system is modeled through Discrete Event Simulation. The proposed approach is illustrated by means of an application example involving repairable systems with series-parallel configuration.