变换核估计在未知需求分布函数条件下多阶段库存控制策略中的应用研究

传统的多阶段库存控制主要致力于库存持有以及过多库存的经济性研究.随机库存模型经常假定需求分布已知,这样可以产生容易解决的方案.但随着销售信息的不断更新,需求分布函数的参数常常未知.这样传统的多阶段库存模型很难产生最优的库存控制策略.当前文献对未知需求分布函数条件下的多阶段库存管理问题研究得不多,当需求分布函数随时间变化,是个多阶段随机规划问题,通常情况难以直接进行求解.针对一般非平稳需求,还缺少有效的库存管理方法.本文致力于变换核估计和优化理论相结合的方法研究未知需求分布函数条件下多阶段库存控制策略,提供一条多阶段库存控制的新思路.可以很好地确定各阶段的最优订货点、最高库存、最低库存等来达到整个系统的最优,从而节省更多的成本,达到营运资本的永久性减少、更高的销售量和客户满意度,从而增加企业的竞争力.

Research on Multi-stage Inventory Control under Unknown Demand Distribution Function by Transform Nuclear Estimates

The traditional multi-stage stochastic inventory control mainly devotes the stock efficient research;The stochastic inventory model often supposes the demand distribution function known,so can produce the scheme apt to solve.But along with sales message unceasing renewal, demand distribution function parameter frequently change.Such traditional multi-stage inventory model is very difficult to have the most superior inventory control strategy.Under the current literature′s studies not many to unknown demand distribution function condition multi-stage inventory management question,each issue of demand distribution function along with the time variation,is the stage stochastic programming question,usually the situation carries on the solution directly with difficulty,the effective stock management method is lacked in view of general non-steady demand. This research applies statistics and the optimization theory studying the multi-stage inventory control strategy under unknown demand distribution function condition,provides multi-stage inventory control the new mentality,and may determine well the most superior order point,the highest stock,the lowest stock and so on at various stages,achieves the overall system most superior,thus saves more costs,achieves the working capital to reduce,a higher sales volume and the customer degree of satisfaction,thus increases enterprise′s competitive power.