Strong interactions between decisions in the maintenance and production scheduling domains, and their impacts on the equipment yield rates necessitate maintenance and production decisions being optimized concurrently, with considerations of yield dependencies on the equipment conditions and production rates. This paper proposes an integrated decision-making policy for production and maintenance operations on a single machine under uncertain demand, with concurrent considerations and learning of yield dependencies on the equipment conditions and production rates. This policy is obtained through a two-stage stochastic programming model, which considers the variable demand, machine degradation, and maintenance times. This model incorporates outsourcing decisions and operational decisions regarding reworking, scraping of imperfect products to ensure the demand is adequately met. A closed-form reinforcement learning method is utilized to learn yield dependencies. Simulations confirm the necessity of yield learning and show the proposed method outperforms the traditional, fragmented approaches where the effects of production rates and machine conditions on the resulting yield rates are not considered. The two-stage stochastic setting is demonstrated by comparing with the traditional one-stage deterministic approach, where decisions are made based on the expected demand and production performance, with scrapping, reworking, and outsourcing decisions established before the demand and production performance are observed.

维护和生产计划域中的决策之间的强大交互，以及它们对设备生产率的影响，使得维护和生产决策必须同时进行优化，同时要考虑产量对设备条件和生产率的依赖性。本文提出了在不确定需求下对单台机器进行生产和维护操作的综合决策策略，同时考虑并学习了产量对设备状况和生产率的依赖性。该策略是通过两阶段的随机编程模型获得的，该模型考虑了可变需求，机器性能下降和维护时间。该模型结合了有关返工的外包决策和运营决策，刮除不完美的产品，以确保充分满足需求。利用封闭形式的强化学习方法来学习屈服相关性。仿真证实了产量学习的必要性，并表明所提出的方法优于传统的，零散的方法，在传统方法中，不考虑生产率和机器条件对所得产率的影响。通过与传统的一阶段确定性方法进行比较来证明两阶段随机性设置，在传统确定性方法中，决策是根据预期需求和生产绩效做出的，在观察需求和生产绩效之前已建立了报废，返工和外包决策。仿真证实了产量学习的必要性，并表明所提出的方法优于传统的，零散的方法，在传统方法中，不考虑生产率和机器条件对所得产率的影响。通过与传统的一阶段确定性方法进行比较来证明两阶段随机性设置，在传统确定性方法中，决策是根据预期需求和生产绩效做出的，在观察需求和生产绩效之前已建立了报废，返工和外包决策。仿真证实了产量学习的必要性，并表明所提出的方法优于传统的，零散的方法，在传统方法中，不考虑生产率和机器条件对所得产率的影响。通过与传统的一阶段确定性方法进行比较来证明两阶段随机性设置，在传统确定性方法中，决策是根据预期需求和生产绩效做出的，在观察需求和生产绩效之前已建立了报废，返工和外包决策。