Deteriorated equipment has a significant impact on the product quality and maintenance policies. In this paper, we present a decision-making architecture to determine maintenance and product dispatching policies based on condition-monitoring information and the relationship between machine degradation and associated product quality. We use a Markov decision process for the long-term decision making and integer programming for the short-term decision making with a multi-product, multi-station system. We demonstrate the advantage of the proposed approach by comparing the proposed policy with traditional decision-making approaches. Furthermore, we illustrate the improvement of the proposed policy over the current usage-based maintenance policy with a semiconductor manufacturing process application.