Integrated Production/Inventory and Condition-Based Maintenance Control of a Multi-Item Production System Under Stochastic Demand

This paper studies the joint production/inventory and condition-based maintenance control for a multi-product manufacturing system with setup times under stochastic product demands. The problem is modelled as semi-Markov decision process (SMDP). objective to find production policy that minimizes long run expected discounted cost including setup, holding, lost sales, preventive corrective costs. A Q-learning method state aggregation (QLA) proposed near-optimal policies large-scale problems cannot be solved optimality due curse of dimensionality. numerical results show QLA provides well-performing in reasonable computational time.