Selective Maintenance under Uncertainty

Abstract

In this paper, a new multi-objective robust selective maintenance model is formulated by considering the uncertainties produced by imperfect inspections. The resulting optimization problem aims at maximizing the expectation of the probability of a repaired system completing a mission and simultaneously minimizing its variance. A multi-objective particle swarm optimization algorithm in introduced to identify the Pareto front, which offer a set of non-dominated selective maintenance strategies. An illustrative example shows that the selective maintenance strategy with the maximum expectation of the probability of a repaired system completing a mission may not be desirable as it usually possesses a huge variance. Several comparative studies are also conducted to examine the effect of observation accuracy and maintenance budget on the results. It concludes that the proposed approach can effectively improve the robustness of the probability of a repaired system completing a mission.