基于随机动态规划的有限库存ATO系统优化控制  

A Stochastic Dynamic Programming for Assemble-To-Order System Optimization with Capacitated Inventory

作　　者：李稚[1] 谭德庆[2] LI Zhi TAN De-qing(School of Management, Tianjin Polytechnic University, Tianjin 300387, China School of Economics ＆ Management, Southwest JiaoTong University, Chengdu 610031, China)

机构地区：[1]天津工业大学管理学院,天津300387 [2]西南交通大学经济管理学院,四川成都610031

出　　处：《运筹与管理》2017年第7期21-28,共8页Operations Research and Management Science

基　　金：国家自然科学基金资助项目(71602143);教育部第49批留学回国人员科研启动基金项目(教外司留[2015]311号)

摘　　要：本文研究n维组件单一产品,有限库存的ATO系统。通过建立马尔可夫决策过程模型(MDP),构造优化算法,研究组件生产与库存的最优控制策略。最优策路可以表示为状态依赖型库存阈值,系统内任一组件的控制策略受其它组件库存状态的影响。利用最优控制理论动态规划方法和数值计算方法对最优控制策略的存在性、最优值的数值计算进行研究,建立更符合实际生产的ATO系统决策模型,进行相应的理论和实验验证,研究系统参数对最优策略的影响。This paper considers an Assemble-To-Order （ATO） system with capacitated inventory that produces n components with a single assembled product. Based on Markov Decision Process（MDP）framework, we create optimization algorithm to study the optimal production and inventory policy of ATO system. The results show that the optimal policy is state dependent, and the strategy of one component depends on the inventory of others. That is, the optimal production policy can be described as a series of base-stock levels, and optimal allocation policy can be described as a series of rationing levels. Both these two types of levels are increasing with the on hand in- ventory of other components. The dynamic programming theory, optimal control theory and numerical calculation method are used to study the existence of the optimal control strategy, and optimal value calculation. The project will build the decision model that corresponds better to the practical ATO system, establish the theory and carry out the experimental validation. The influence of system parameters on optimal policy is also proposed in this work.

关 键 词：按订单装配(ATO) 优化控制 马尔可夫决策过程(MDP) 

分 类 号：F273[经济管理—企业管理]