Answers are grounded in this paper and cite their sources.
This paper presents a simulation based optimization framework for the joint determination of preventive maintenance intervals and spare parts replenishment policies in a heterogeneous multi component industrial system. The decision vector of each component includes the preventive maintenance interval, the reorder point, and the replenishment quantity. The simulator represents weekly operation over a 52 week horizon, Weibull deterioration affected by effective age and seasonal loading, random lead time disruptions, preventive and corrective maintenance, emergency procurement, inventory costs, downtime penalties, and near service continuity requirements. Five population based metaheuristics, particle swarm optimization, genetic algorithm, grey wolf optimizer, multi verse optimizer, and black widow optimization, were calibrated through Bayesian optimization and assessed over 30 independent matched runs. The results show that all optimized policies reduce the mean fitness by more than 32% with respect to a differentiated conservative baseline while maintaining average service levels above 0.997. GA obtained the best mean fitness and best average rank, whereas PSO achieved the best single run and remained statistically competitive. Additional replication, horizon, supply disruption, safety penalty, and scalability analyses were conducted to clarify estimator stability, the interpretation of zero reorder points, and the computational behavior of the simulation layer.
No takes yet. Share an insight, caveat, or question.
Sanin-Villa et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: