多机串行系统的生产批量与维护计划集成优化

Integrated optimization of production lot and maintenance planning in multi-machine serial system

在无缓冲串联系统生产环境下,假定设备基于加工失效,系统中存在完美维护和非完美维护两种方式,维护资源有限。在考虑缺货和库存成本的基础上研究生产批量计划与设备预防性维护计划集成决策方法,建立了多机串联系统集成计划数学模型。针对该模型的复杂非线性特征,提出一种分阶段决策求解方法。采用遗传算法高效寻找维护组合来分析模型求解空间巨大的问题。通过数值实验将所提方法与枚举法和经典算法进行了比较,验证了其有效性。

Under the condition of serial system without intermediate buffers, perfect and imperfect preventive mainte-nance ways existed in system by assuming machines were subjected to Operation Dependent Failures （ODF） , which were limited in maintenance resource. On this basis, an integrated production lot and maintenance planning model was presented by considering stockout and inventory cost. An integrated mathematical model of multi-machine serial system was established, and a multi-stage decision solving method was proposed for the complex non-linear charac-teristic of this model. For analyzing the problem of model’s large decision space, the genetic algorithm was used to search the maintenance planning group. By comparing with the enumeration method and the simulated annealing al-gorithm, the effectiveness of the model and the superiority of the proposed algorithm were illustrated with practical experiments.