An integrated optimal design of attributes sampling and proactive maintenance for a discrete manufacturing system is studied in this paper. In the system, the failure of a critical component causes the process to shift. The new mathematical model for online sampling of the discrete manufacturing system is based on the binomial and truncated negative binomial distributions. In addition to performing scheduled maintenance and unscheduled corrective maintenance at the time of a true alarm, an additional maintenance opportunity when a false alarm occurs is also considered. The optimal scheduled maintenance time and sampling parameters are determined by solving a mixed integer nonlinear programming problem to minimise the long-run cost rate. A numerical example is provided to illustrate the proposed integrated attributes sampling and maintenance plan. The results show that the integrated approach outperforms the alternatives that consider different models separately. More importantly, showing the benefit of doing maintenance upon a false alarm provides a stakeholder with a new idea in managing a deteriorating manufacturing system.

本文研究了离散制造系统的属性采样和主动维护的集成优化设计。在系统中，关键组件的故障会导致流程发生变化。离散制造系统在线采样的新数学模型基于二项式和截断负二项式分布。除了在真正警报发生时执行计划维护和计划外纠正性维护之外，还考虑了在发生错误警报时的额外维护机会。通过求解混合整数非线性规划问题来确定最佳计划维护时间和采样参数，以最小化长期成本率。提供了一个数值例子来说明建议的集成属性采样和维护计划。结果表明，集成方法优于单独考虑不同模型的替代方法。更重要的是，展示在误报时进行维护的好处为利益相关者提供了管理不断恶化的制造系统的新想法。