Revenue management in single-stage CONWIP production systems

We study a joint admission/inventory control problem for a manufacturing system producing one product to meet random demand. The system employs a constant work- in-process policy (CONWIP) whereby the total inventory of raw material and finished items is kept constant, and accepts orders only as long as the backlog is below a certain level. The objective is to determine the CONWIP and backlog levels that maximize the mean profit rate of the system. The system is modelled as a single server with a finite queue. It turns out that the mean profit rate is either concave or decreasing in one control parameter and also decreasing for large values of the other control parameter. A simple algorithm is developed which tracks down the globally optimum design in finite time. Numerical results show that the joint admission/inventory control policy achieves higher profit than other production control policies that have been examined in the literature.     

A note on evaluating the risk in continuous review inventory systems

This paper is an attempt to evaluate the long term risk of stock-out and obsolescence in continuous review inventory systems, typically of slow-moving but very critical items. Inventory decisions depend very much on the goodness of the estimates of the input parameters like the holding, ordering and stock-out costs. It is a well-known fact that stock-out cost is a very difficult parameter to estimate. The lower it is the lower the quality of service will be while the higher it is the higher the inventory cost would be and possibly higher obsolescence rate too. In this paper, we develop a framework to evaluate the risks, in the long term, of stock-out and obsolescence, especially for inventory of critical spares whose demand rate is not high. For this purpose, we propose the use of quasi-stationary distributions for continuous review (r, Q) inventory systems with the condition that the Laplace transforms of functions of interest are rational algebraic functions. We relate the quasi-stationary distribution to the conditional tail expectation which is a coherent risk measure used in finance and actuarial studies. Numerical illustration is also provided.     

Life-cycle inventory analysis of concrete production: A critical review

Concrete is one of the most widely used building materials with a global consumption rate approaching 25 gigatonnes per year. Consequentially, its environmental burden is significant in terms of resource use and environmental emissions. There is a diverse audience of decision makers and manufacturers who are interested in understanding and lowering the environmental impact of concrete and other buildings materials, which requires a life-cycle assessment (LCA) approach. A critical first step in any LCA is the compilation of a credible life-cycle inventory (LCI), upon which subsequent life-cycle impact assessment (LCIA) can be based. This article reviews the strengths and weaknesses of concrete LCIs to date, and offers a research roadmap to improve the quality of future cement and concrete LCIs and meet the needs of major LCA users.     

Integrated inventory models with fuzzy annual demand and fuzzy production rate in a supply chain

The successful implementation of Just-in-time (JIT) production in today's supply chain environment requires a new spirit of cooperation between the buyer and the vendor. An integrated inventory model with such a consideration is based on the total cost optimization under a common stock policy and business formula. However, the supposition of known annual demand in most related literature may not be realistic. This paper proposes the inclusion of fuzzy annual demand and/or the production rate, and then employs the signed distance, a ranking method for fuzzy numbers, to find the estimate of the common total cost in the fuzzy sense, and subsequently derives the corresponding optimal buyer's quantity and the integer number of lots in which the items are delivered from the vendor to the purchaser. Numerical examples are provided to illustrate the results of proposed models.     

Decentralized inventory control in a two-stage capacitated supply chain

This paper investigates a two-stage supply chain consisting of a capacitated supplier and a retailer that faces a stationary random demand. Both the supplier and the retailer employ base stock policies for inventory replenishment. All unsatisfied demand is backlogged and the customer backorder cost is shared between the supplier and the retailer. We investigate the determination of decentralized inventory decisions when the two parties optimize their individual inventory-related costs in a noncooperative manner. We explicitly characterize the Nash equilibrium inventory strategies and identify the causes of inefficiency in the decentralized operation. We then study a set of simple linear contracts to see whether these inefficiencies can be overcome. Finally, we investigate Stackelberg games where one of the parties is assumed to be dominating.     

Multi-echelon service models for inventory systems under different rationing policies

In this paper we model the service performance of two-echelon divergent production networks consisting of one central stock-point feeding a number of end stock-points where the external demand is realized. The systems we consider allow all stock-points to hold inventory and use periodic review ordering policies at all levels. Whenever the lower echelon has insufficient inventory to cover all upper echelon requisitions some policy to ration the available material is needed. Concentrating on one push and one pull rationing policy, we explore the system dynamics and develop models for three popular measures of the system service performance. All models make use of non-dimensional ratios which drastically reduce the number of parameters involved. Although these models are only approximate, numerical and simulation results demonstrate the adequacy of the approximations involved.     

Economic consequences of a production and inventory control policy

The economic performance of a generalized Order-Up-To policy is investigated in response to an Auto Regressive stochastic demand process. Focus is on the case where the physical production/distribution lead time is one period and where demand is forecasted with simple exponential smoothing. Two sets of convex piece-wise linear costs are considered. The first set is the traditional inventory holding and backlog costs. The second set of costs is piece-wise linear and increasing convex costs associated with the production order rate within and above a capacity constraint. Numerical investigations reveal that the classical Order-Up-To policy is no longer optimal when a broader range of costs is considered in the objective function.     

Optimal production and inventory decisions under demand and production disruptions

Unanticipated events may take place and disrupt demand and/or production in a supply chain. Conditional on the type, magnitude and duration of disruptions, changes may be called to revise the original production plan. We analyse different disruption scenarios and propose optimal production–inventory models for products facing demand and production disruptions. To lower the cost, we optimise the production run time, purchasing times and order quantity for the manufacturer. Numerical experiments are conducted to examine the influences of disruption time and magnitude on optimal production and purchasing decisions.     

Integrated inventory valuation in multi-echelon production/distribution systems

The pressure to reduce inventory has increased as competition expands, product variety grows, and capital costs increase. This investigation addresses the problem of inventory quantification and distribution within multi-echelon supply chains under market uncertainty and management flexibility. This approach is based on an optimisation model emphasising demand uncertainty and the relevant dimensions of network design as number of echelons, lead time, service level, and cost of processing activities. Overstock quantification enables the understanding of inventory level sensitivity to market uncertainty. A comparison among production sites and storage facilities revealed that higher downstream overstock levels decrease upstream echelons of uncertainty exposition. The contribution of this study relies on management's ability to establish inventory targets for each stocking point according to risk exposure and to promote the optimisation of working capital. Overall, this investigation increases knowledge related to the treatment of demand uncertainty in flexible and integrated supply chains     

Sensor-driven prognostic models for equipment replacement and spare parts inventory

Accurate predictions of equipment failure times are necessary to improve replacement and spare parts inventory decisions. Most of the existing decision models focus on using population-specific reliability characteristics, such as failure time distributions, to develop decision-making strategies. Since these distributions are unaffected by the underlying physical degradation processes, they do not distinguish between the different degradation characteristics of individual components of the population. This results in less accurate failure predictability and hence less accurate replacement and inventory decisions. In this paper, we develop a sensor-driven decision model for component replacement and spare parts inventory. We integrate a degradation modeling framework for computing remaining life distributions using condition-based in situ sensor data with existing replacement and inventory decision models. This enables the dynamic updating of replacement and inventory decisions based on the physical condition of the equipment.     

Cooperative inventory planning in a distribution network

This study addresses the problem of optimal ordering and collaborative inventory management in a distribution network as a two-stage decision problem. In the first stage, when demand is uncertain, the retailers (sellers) order the products from a warehouse. Then, when demand becomes known with certainty, retailers may exchange their products to better match local demands. Sellers should determine their optimal order quantities for the first stage, and quantities and prices of products exchanged in the second stage. This paper proposes to build sellers’ coalitions and solve the two-stage decision problem as a cooperative game. Stability of a sellers’ coalition can be achieved only if the benefits resulting from collaboration are maximised and distributed according to an allocation policy that is both efficient and rational. The profit maximisation problem is formulated as a stochastic optimisation problem with recourse. Using the scenario method, this problem is approximated by a deterministic linear problem for which the existence of a solution is guaranteed. The proposed pricing policy guarantees the rational allocation of benefits under the scenario approximation. An industrial example supports the modelling approach and is used to evaluate the profitability of the exchange practice in the case of real data.     

An integrated robust replenishment/production/distribution policy under inventory inaccuracy

In this paper, a centralised production/distribution system is studied, in which the manufacturer controls the processes of raw material ordering, production and final goods distribution. The inventory records of raw materials, work-in-process, final goods in the manufacturer and the retailers are inaccurate. The objective of this research is to develop an integrated policy that can hedge against the negative impact of inventory inaccuracy at all stages of a supply chain. To achieve this aim, a backward recursive integrated robust policy is constructed. First, the time, quantity and vehicle route of the next distribution are forecasted by a distribution sub-policy; then the forecasted distribution time and quantity are used as the objective of the production process control, which is implemented by a production control sub-policy. Raw materials are ordered by a replenishment sub-policy according to the forecasted raw materials consumption in the production process. Numerical experiments are conducted to verify the feasibility and robustness of the proposed policy, which shows that besides of deploying radio frequency identification (RFID) devices in inventory management systems for raw materials, WIPs, final goods of the manufacturer and the retailers, integrated robust policies also can be employed to hedge against the impact of inventory inaccuracy.     

Periodic-review inventory systems with random yield and demand: Bounds and heuristics

We revisit the infinite-horizon decision problem of a single-stage single-item periodic-review inventory system under uncertain yield and demand. It is known that under some mild conditions the optimal replenishment policy is of the threshold type: an order is placed if and only if the starting inventory is below a threshold value. Although the structure of the optimal policy is well known, there has been little discussion about the optimal order quantities and the order threshold. In this paper, we construct upper and lower bounds for the optimal threshold value and the optimal order quantities through solving one-period problems with different cost parameters. These bounds provide interesting insights into the impact of yield uncertainty on the optimal policy. Heuristics are developed based on these bounds. Detailed computational studies show that, under some conditions, the performance of the heuristics is very close to that of the optimal solution and better than that of existing heuristics in the literature.     

Inequalities on convolutions and their application in acceptance sampling

Summary LetX be a random variable with an unknown distribution functionF. Suppose that we are given a random samplez ₁,...,z _n from the convolutionsF*G ₁,...,F*G _n ofF with known distribution functionsG ₁,...,G _n. We are interested in tolerance intervals forX or in the probability thatX takes values in some intervalI. Simple inequalities are proved, which permit the estimation of lower bounds for the desired probabilities. In a typical application in statistical quality control, prior information on the fraction defective may be obtained from repeated inspection of lots of the same production.     

Managing information and supplies inventory operations in a manufacturing environment. Part 1: An action research study

In the first part of this research study, we describe the application of the action research method in the nuclear fuel manufacturing industry to process information and to develop a lean operating supplies inventory program. The motivation for our work stems from the interaction we had with AREVA Richland, the nuclear reactor fuel production site located in the state of Washington to investigate the important role that information processing and maintenance inventory play in keeping the production process functioning on schedule. AREVA's data systems are not well documented. Hence, designing a methodology to obtain good data and perform any validity checks was critical for the company. Additionally, the importance of meeting delivery schedules to nuclear power plants throughout the world cannot be overestimated. Late deliveries of fuel can easily destroy the precise schedules for power plant outages designed to minimise plant downtime and maximise electric power output. Therefore, AREVA cannot tolerate significant production schedule deviations. Maintenance items play a key role in ensuring that production schedules are met. AREVA has about $700,000 tied up in maintenance inventory at their Washington state plant. Hence driving this investment down, while maintaining a high fill-rate, is crucial. Through the deployment of process maps, failure mode effect analysis and cause-and-effect diagram, we managed an action research project that helped process information flow along the company's supply chain and generated a 27% reduction in inventory relative to the system that was currently in place at AREVA.     

A neuroevolutionary approach to stochastic inventory control in multi-echelon systems

Stochastic inventory control in multi-echelon systems poses hard problems in optimisation under uncertainty. Stochastic programming can solve small instances optimally, and approximately solve larger instances via scenario reduction techniques, but it cannot handle arbitrary nonlinear constraints or other non-standard features. Simulation optimisation is an alternative approach that has recently been applied to such problems, using policies that require only a few decision variables to be determined. However, to find optimal or near-optimal solutions we must consider exponentially large scenario trees with a corresponding number of decision variables. We propose instead a neuroevolutionary approach: using an artificial neural network to compactly represent the scenario tree, and training the network by a simulation-based evolutionary algorithm. We show experimentally that this method can quickly find high-quality plans using networks of a very simple form.     

基于供应链的企业库存成因及优化控制研究（二）

基于企业全面库存的管理思想,对库存成本、库存控制、库存系统优化等管理经验与前人研究成果进行分析,借鉴先进企业的库存管理理念和方法,以大型制造企业为核心研究对象,在集供应商、制造商、经销商为一体的供应链作为研究框架的基础上,运用供应链系统理论作为研究方法,分析了库存管理现状、影响因素及产生原因,从优化生产管理、整合企业内部供应链和跨企业供应链的角度提出了库存控制的相应对策,以实现全面库存优化,提高经营效益.     

Preventive maintenance and optimal buffer inventory for products sold with warranty in an imperfect production system

This paper deals with an imperfect production system with allowable shortages due to regular preventive maintenance for products sold with free minimal repair warranty. Preventive maintenance is an essential factor of the just-in-time structure that results in a shutdown of the production process for a certain period of time. During such an interruption, a buffer stock is needed to adjust the market demand. The study includes the possibility of imperfect production and determines the optimum buffer level and production run time by trading off the holding cost, shortage cost, rework cost, repair cost for warranty, labour/energy costs, material cost and cost for maintenance so that the cost per unit product is minimised.     

On deficiencies of common ordering policies for multi-level inventory control

We consider two common types of ordering policies for multi-level inventory control: installation stock (R,Q)-policies and echelon stock (R,Q)-policies. The batch quantities are assumed to be given, but each policy is optimized with respect to its reorder point R. We demonstrate that there is no bound for the worst case performance ratio of these policies when applied to distribution inventory systems with a central warehouse and a number of retailers.