基于混合需求的二级库存系统协同订货模型

在一般的二级库存优化模型均做如下假定：供应链的每一级节点面临的需求都是独立需求。但在实际中,只有最下游的节点面临的需求是独立需求,而其上游节点面临的需求都是与之相关的相关需求。因此,建立了基于混合需求的协同订货模型。将面临独立需求的最下游节点的订货合并为一个虚拟节点的订货策略,再对二级节点采用相关需求策略进行协同订货,从而构建使整体最优的模型。并给出了模型求解的遗传算法,最后对模型进行了实例演算。     

基于第三方的易变质产品库存决策

针对需求受价格影响和需求受价格、库存量共同影响的两种情况,考虑销售商允许缺货且缺货期间出现短缺量部分拖后,研究多个供应商、多个销售商情况下,供应商库存外包于第三方的易变质产品库存联合决策模型.对比分析两模型的结论表明,需求依赖当前销售价格和库存量情况下,考虑易变质产品库存问题更贴近实际,存在最优订货周期、最优销售价格使得供应链整体利益最大化,此时,供应链整体利润并不随着缺货率的增加而单调减小.     

一类考虑机器可靠性的变质性物品供应商管理库存

在考虑机器可靠性和通货膨胀的情形下,建立一个供应商和一个订货商,在允许订货商缺货且缺货量部分拖后的易变质产品的供应商管理库存(VMI,Vendor Managed Inventory)模型,给出了数值算例、最优解及主要参数的图形分析,结果表明参数对供应链库存成本均有一定程度的影响,为VMI模式下的库存管理系统提供一些理论依据.     

两级供应链联合成本三角模糊需求随机过程模型

根据影响两级供应链系统库存控制及决策过程的随机与模糊特性,基于联合成本提出两级供应链三角模糊需求随机过程模型。对两级供应链系统进行研究,给出其联合成本优化模型。针对交货时间和需求率的模糊特性,分情况利用三角模糊函数设计缺货数量模糊模型,基于此对两级供应链联合成本优化模型进行改进,建立三角模糊需求随机过程模型,并给出该模型的求解过程。通过模型参数敏感性实验以及算法对比实验,验证了所提模糊随机过程模型的有效性。     

供应链中控制多级存储的射频辨识Push/Pull混合策略设计与仿真

由于射频辨识(radio frequency identification,RFID)激励的电子看板系统能够从远端看见供应链节点企业库存的状况,使得广域分布的供应链多级存储能够实现RFID激励的Pull控制.本文根据供应链分销网络多级存储的结构特点,以及系统运作期间各阶段节点企业的功能,在不同阶段采用不同的控制策略.因此,设计了多种不同的RFID激励的Push/Pull混合控制策略.为了比较和验证各混合策略对多级存储的控制性能,建立了以总库存成本、总缺货损失、总运行成本和库存周转率作为评价策略性能的指标体系.由于供应链系统的动态性与随机性,难以进行数学建模和精确求解,因此基于离散事件系统仿真原理,设计并实现了仿真模型.通过对各策略下多种结构的供应链分销网络多级存储的仿真,验证并分析了制造商阶段采用Push控制,分销商和零售商阶段采用Pull控制的策略的有效性和最优性.     

考虑保质期的两级供应链MTS-MTO提前期优化研究

在具有保质期特性的快消品行业中,供应商在面向订单(MTO)生产策略下较长的订货提前期会给零售商带来高库存以及高运作成本,削弱供应链的快速响应能力.对比原来的MTO生产策略,提出一种面向库存-面向订单(MTS-MTO)混合生产策略.首先,基于产品保质期的特点建立MTO生产策略下的供应链成本模型,并给出供应链成本最优的经济订货批量;其次,根据MTO求出的最优经济订货批量,建立MTS-MTO生产策略下的供应链成本模型,并确定供应商的应持有库存M,求出供应商在MTS-MTO生产时的充要条件,为供应链决策提供依据;再次,给出一种基于满意度的Nash协商模型以确定零售商应给予供应商的补偿H;最后,通过数值分析验证并讨论符合MTS-MTO生产的产品特征.     

随机需求下提前期可控的生产-库存联合优化模型

考虑单供应商和单采购商的生产-库存联合优化问题.假设采购商面临正态需求,供应商的提前期可以控制,并基于此建立供应商与采购商联合期望总成本最小化模型.在所建立的模型中允许采购商缺货,且部分缺货可延期交付,部分缺货发生销售损失;同时考虑运输成本,并假设运输成本依赖于订货量和提前期.给出了求解最优生产批量、最优提前期、最优再订货点和订货量的算法,并通过数值算例进行了说明.     

自适应控制对多级库存延迟问题的优化研究

针对在随机需求下交货延迟所导致供应链多级库存系统库存积压、缺货和牛鞭效应等问题,建立了基于自适应控制算法的多级库存动态优化模型。通过泰勒展开和拉布拉斯变换建立了基于APIOBPCS策略考虑延迟的动态多级库存控制模型;由Lyapunov渐进稳定性定理设计了一种适用于多级库存的模型参考自适应控制算法,其中以无交货延迟的参考库存模型作为目标,通过调节线性补偿函数和自适应控制率,逐渐缩小实际库存模型与参考库存模型间的输出误差,以此削弱交货延迟对多级库存模型的影响;通过实证数据验证了模型参考自适应控制对一个三级供应链库存系统的动态优化效果。仿真结果表明,自适应控制下的无信息共享多级APIOBPCS库存系统缺货全部归零,牛鞭效应下降40.7%。在不增加企业运营投入的前提下,通过自适应控制算法,优化资源配置,动态削弱了交货延迟对多级库存的影响,提升了供应链运营效率。     

连锁零售供应链多级库存协同决策研究

针对连锁零售供应链多级库存资源的动态优化配置问题,提出了在上层对库存策略和下层对物流分配方案协同寻优的多级库存双层规划模型。借鉴细粒度模型遗传算法的遗传操作具有局部性的特点,模拟微观群体交互作用的局部性,基于细粒度模型遗传算法的Agent群体行为优化算法和基于复杂适应系统涌现机理的协同决策机制,进行连锁零售供应链多级库存协同决策研究。通过算例实验对模型的有效性进行了验证。仿真实验结果表明,通过连锁零售供应链微观个体Agent的群体行为优化,从系统工程的角度,实现了连锁零售供应链多级库存的动态资源优化配置和信息共享,降低了多级库存管理与运营的总成本。     

具有时变需求的配送型多级库存优化研究

考虑到战术仓库的需求率具有时变性的特点,应用供应链管理的思想研究了一个战役仓库、多个战术仓库组成的配送型多级库存优化问题,建立了战役仓库采用等量订货策略,战术仓库分别采用等间隔、等量订货策略时的模型,并采用自适应遗传算法实现了模型的求解,实例验证了模型及算法的有效性.实例表明：战役仓库采用等量订货策略,战术仓库采用等间隔订货策略时总费用最低.     

A hybrid genetic algorithm for two-stage multi-item inventory system with stochastic demand

We study a two-stage, multi-item inventory system where stochastic demand occurs at stage 1, and nodes at stage 1 replenish their inventory from stage 2. Due to the complexity of stochastic inventory optimization in multi-echelon system, few analytical models and effective algorithms exist. In this paper, we establish exact stochastic optimization models by proposing a well-defined supply–demand process analysis and provide an efficient hybrid genetic algorithm (HGA) by introducing a heuristic search technique based on the tradeoff between the inventory cost and setup cost and improving the initial solution. Monte Carlo method is also introduced to simulate the actual demand and thus to approximate the long-run average cost. By numerical experiments, we compare the widely used installation policy and echelon policy and show that when variance of stochastic demand increase, echelon policy outperforms installation policy and, furthermore, the proposed heuristic search technique greatly enhances the search capacity of HGA.     

The replenishment policy of agri-products with stochastic demand in integrated agricultural supply chains

Market demand of agri-products is influenced by uncertain factors, such as weather, temperature, and customer preferences. In integrated agricultural supply chains, traditional inventory models are useless because of the stochastic demand and deteriorative characteristic of agri-products. This paper provides a method to determine the optimal replenishment policy of integrated agricultural supply chains with stochastic demand. In these EOQ/EPQ models, shortages are allowed and are backlogged if market demand is stochastic. The objective function is to minimize the total cost of the supply chain in the planning horizon. The total cost includes the ordering cost, the holding cost, the shortage cost and the purchasing cost. Thinking of the nonlinear relationship and dynamic forces in models, a system dynamic (SD) simulation model is constructed to find the optimal lot size and replenishment interval. Finally, an example is given to make a sensitivity analysis of the simulation model. Compared to traditional methods (such as equalize stochastic demand), the total cost decreases by 16.27% if the supply chains adopt the new replenishment policy. The results illustrated that the new replenishment policy (with intelligent method) is beneficial to help supply chain make decision scientifically. Moreover, the intelligent method can simulate stochastic demand perfectly, and it is effectively for solving the complicated and mathematically intractable replenishment problem.     

Single period stochastic inventory problems with ordering or returns policies

In recent years, there has been an increasing adoption of returns policies in the coordination of the supply chain, where market demand is always assumed to be satisfied by manufacturing or by ordering from suppliers. However, many industries face the important decision of how to balance their inventory level. This problem has long been studied in financial institutions such as banks. This study presents an optimal inventory policy under a given stochastic demand such as a uniformly distributed demand, single-item, and single period review inventory system. The optimal inventory control policy obtained in this study is called a four-point policy: that is, when the entity’s inventory level is below a reorder point, the entity must increase his stock level by ordering and order up-to a fixed level (second point); when the entity’s inventory level is over a return point (third point); the stock level must be decreased by returns and decreased to a fixed level (fourth point); otherwise, nothing should be done. We also analyze the (K, S)-convex properties of the inventory cost function.     

The benefit of VMI strategies in a stochastic multi-product serial two echelon system

We consider a multi-product serial two echelon inventory system with stochastic demand. Inventories at the downstream location are replenished periodically using an automatic ordering system. Under vendor managed inventory strategies the upstream stage is allowed to adapt these orders in order to benefit from economies of scale. We propose three different VMI strategies, aiming to reduce the order picking cost at the upstream location and the transportation costs resulting in reduced total supply chain costs. In a detailed numerical study the VMI strategies are compared with a retailer managed inventory strategy for two different demand models suitable for slow moving products. It is shown that if inventory holding costs are low, compared to handling and transportation costs, efficiencies at the warehouse are improved and total supply chain costs are reduced.     

A vendor managed inventory model under contractual storage agreement

Vendor managed inventory (VMI) is a supply chain partnership strategy that allows a supplier to place orders on behalf of its customers. This paper considers a supply chain composed of a single vendor and multiple retailers operating under a VMI contract that specifies limits on retailers' stock levels. We address the problem of synchronizing the vendor's cycle time with the buyers' unequal ordering cycles by developing a mixed integer non-linear program that minimizes the joint relevant inventory costs under storage restrictions. We also propose a cost efficient heuristic to solve the developed optimization problem. We conducted computational experiments to assess the reduction in the total supply chain costs resulting from relaxing the restriction of equal ordering cycles. It is found that the heuristic generates greater cost savings in cases of increased variability in retailers' demand and cost parameters.     

Fuzzy inference systems and inventory allocation decisions: Exploring the impact of priority rules on total costs and service levels

Inventory allocation decisions in a distribution system concern issues such as how much and where stock should be assigned to orders in a supply chain. When the inventory level of an inventory point is lower than the total number of items ordered by lower echelons in the chain, the decision of how many items to allocate to each ``competing'' order must take into consideration the trade-off between cost and service level. This paper proposes a decision-support system that makes use of fuzzy logic to consider inventory carrying, shortage and ordering costs as well as transportation costs. The proposed system is compared through simulation with three other inventory allocation decision support models in terms of cost and service levels achieved. Conclusions are then drawn.     

The impact of information sharing on ordering policies to improve supply chain performances

Bullwhip effect represents the amplification and distortion of demand variability as moving upstream in a supply chain, causing excessive inventories, insufficient capacities and high operational costs. A growing body of literature recognizes ordering policies and the lack of coordination as two main causes of the bullwhip effect, suggesting different techniques of intervention. This paper investigates the impact of information sharing on ordering policies through a comparison between a traditional (R, S) policy and a coordination mechanism based on ordering policy (a combination of (R, D) and (R, S) policies). This policy relies on a slow, easy to implement, information sharing to overcome drawbacks of the effect, in which replenishment orders are divided into two parts; the first is to inform the upstream echelons about the actual customer demand and the second is to inform about the adjustment of the inventory position, smoothing at the same time the orders of the different levels of the supply chain. A simulation model for a multi-echelon supply chain quantifies the supply chain dynamics under these different policies, identifying how information sharing succeeds to achieve an acceptable performance in terms of both bullwhip effect and inventory variance.