A Bayesian inventory model using real-time condition monitoring information

Lack of coordination between machinery fault diagnosis and the inventory management of spare parts can lead to increased inventory costs and disruptions in production activity. To address this gap, we develop a framework for incorporating real-time condition monitoring information into inventory decisions for spare parts. We demonstrate that a dynamic base-stock policy, in which the optimal base-stock level is a function of some subset of the observed sensor information, is optimal. We then propose a myopic critical fractile policy, which captures the essence of the optimal policy, but is much easier to compute. Adaptive inventory policies such as those developed in this research can help manufacturers to increase machine availability and reduce inventory costs.