A multicriteria model for supporting setup reduction investment decisions

One critical manufacturing challenge of the 1990s is for firms to effectively apply new operations management techniques while embracing wider philosophies such as total quality management (TQM) and computer integrated manufacturing (CIM), etc. Setup cost and/or time reduction is one such technique capable of producing many benefits for manufacturing firms, including reduced inventory, better equipment utilization, and improved quality. It is thereby viewed as an important component of just-in-time (JIT) manufacturing practice. Existing problems with the setup reduction decision include the many factors that must be considered, as well of an absence of validated and usable models for estimating potential benefits from setup reduction investment made in different contexts. This paper discusses the attainment of gains from setup reduction mainly by improving existing equipment and work practices rather than purchasing new equipment or technology. The model proposed in this paper is based on the application of the analytic hierarchical process (AHP) on seven weighted factors to obtain a preliminary indication as to whether investment in setup reduction is desirable in a given manufacturing context, and the expected benefits of such investment. A flexible scaling system, thus obtained, allows the model to handle a wide range of managerial predispositions to setup reduction.     

The Development Manager's Advisory System: A Knowledge-Based DSS Tool for Project Assessment*

This research investigates whether the knowledge-based decision support system (KBDSS) paradigm provides the necessary supporting structure and developmental framework for product development evaluation. To address the research questions posed in this study, it is necessary to develop and implement KBDSS's at specific decision points along the product development cycle. This paper describes the design, development, and implementation of a KBDSS to support a product development manager's decision concerning full-scale development of a new product. From the systems design perspective, this paper addresses the integration and innovative use of a variety of techniques for knowledge acquisition, modeling, and processing. The approach utilized obtains the benefits of normative modeling as well as the flexibility and developmental advantages of knowledge-based systems. Since its implementation, the system has been successfully used by a development manager to support his recommendation for an ongoing project. His complete satisfaction with this system served as the impetus for the design and development of a multi-expert system which was implemented at the strategic level.     

OPTIMAL AND NEAR OPTIMAL CONTROL OF A TWO-PART-TYPE STOCHASTIC MANUFACTURING SYSTEM WITH DYNAMIC SETUPS

This paper deals with a manufacturing system consisting of a single machine subject to random failures and repairs. The machine can produce two types of parts. When the production is switched from one part type to the other, a random setup time is incurred at a constant cost rate. The objective is to track the demand, while keeping the work-in-process as close as possible to zero for both products. The problem is formulated as an optimal stochastic control problem. The optimal policy is obtained numerically by discretizing the continuous time continuous state opti-mality conditions using a Markov chain approximation technique. The discretized optimality conditions are shown to correspond to an infinite horizon, discrete time, discrete state dynamic programming problem. The optimal setup policy is shown to have two different structures depending on the parameters of the system. A heuristic policy is proposed to approximate the optimal setup policy. Simulation results show that the heuristic policy is a very good approximation for sufficiently reliable systems.     

Optimizing lot size and setup time in a JIT environment: a multiple objective application

The just-in-time (JIT) system has been studied extensively and implemented by a number of US firms as an ell'ective production system. The core of JIT involves determination of lot size and setup time reduction so as to increase manufacturing flexibility while minimizing the inventory level. This decision problem usually involves multiple conflicting objectives and mixed-model production. In this paper, goal programming (GP) is applied to a real-world JIT problem involving fabrication of different automotive and industrial rubber composite belts. The model results provide new insights concerning the conflicting nature of several goals, especially between meeting demand and reducing setup or idle time. Also, the GP solution is superior to the current JIT practice of the company.     

Automating Knowledge Acquisition and Refinement for Decision Support: A Connectionist Inductive Inference Model*

An important application of expert systems technology is to provide support for nonstructured decision making. Usually, nonstructured decision making is characterized by heavy reliance on heuristic knowledge, which is very difficult to articulate or document, and therefore traditional knowledge acquisition approaches are not very successful. The quality and effectiveness of an expert system supporting unstructured decision making is affected when traditional knowledge acquisition approaches are used. To alleviate this problem a model is proposed that combines inductive inference and neural network computing, and an example is presented that illustrates the potential of this model in unstructured decision support.     

A hybrid knowledge discovery model using decision tree and neural network for selecting dispatching rules of a semiconductor final testing factory

One of the most challenging production decisions in the semiconductor testing industry is to select the most appropriate dispatching rule which can be employed on the shop floor to achieve high manufacturing performance against a changing environment. Job dispatching in the semiconductor final testing industry is severely constrained by many resources conflicts and has to fulfil a changing performance required by customers and plant managers. In this study we have developed a hybrid knowledge discovery model, using a combination of a decision tree and a back-propagation neural network, to determine an appropriate dispatching rule using production data with noise information, and to predict its performance. We built an object-oriented simulation model to mimic shop floor activities of a semiconductor testing plant and collected system status and resultant performances of several typical dispatching rules, earliest-due-date (EDD) rule, first-come-first-served rule, and a practical dispatching heuristic taking set-up reduction into consideration. Performances such as work-in-process, set-up overhead, completion time, and tardiness are examined. Experiments have shown that the proposed decision tree found the most suitable dispatching rule given a specific performance measure and system status, and the back propagation neural network then predicted precisely the performance of the selected rule.     

A new MRP/GT lot sizing heuristic: A simulation study

This paper studies the lot-sizing problem in Material Requirements Planning/Group Technology (MRP/GT) systems. A GT production cell is designed to produce many families of components. A major setup is required when switching from manufacturing one family of components to another family, and a minor setup is needed when switching from manufacturing a component type to another component type within the same family. Inventory holding cost is incurred if inventory level is positive, and inventory shortage cost is incurred if inventory level is negative, that is, backordering. The objective of the proposed lot-sizing problem is to minimize the sum of major and minor setup costs, holding and shortage costs, and regular production cost, and to meet simultaneously the demand requirements. The proposed problem is modelled into a linear integer program, a heuristic method to solve the problem is proposed, and a simulation experiment conducted to evaluate the performance of the proposed heuristic and some existing heuristics. The computational results show that the proposed heuristic is useful to reduce the total cost significantly over a wide variety of simulated environments.     

A flexibly structured lot sizing heuristic for a static remanufacturing system

An effective planning of lot sizes is a key strategy to efficiently manage a combined manufacturing/remanufacturing system in the presence of substantial setup costs. Due to its complex interdependencies, optimal policies and solutions have not been identified so far, but several heuristic approaches have been analyzed in recent contributions. The main heuristic shortcuts are forcing equally sized lot sizes over the planning horizon as well as imposing a specific cycle structure, i.e., a sequence of manufacturing batches is followed by a sequence of remanufacturing batches. We are instead proposing a flexibly structured heuristic that allows for differently sized remanufacturing batches. We show in a comprehensive numerical study that our approach outperforms other existing approaches in more than half of all instances by up to 17%.     

Energy-oriented bi-objective optimization for the tempered glass scheduling

This paper investigates a real life bi-objective hybrid flow shop scheduling problem in an energy-intensive manufacturing system, in which glass is produced successively in cutting, printing and tempering stages. The problem aims to simultaneously optimize makespan and the total electricity cost under a time-of-use electricity pricing policy. The glass production has to respect the following environments: (i) the cutting and printing operations are processed in parallel machine environments; (ii) the tempering operation is processed on a batch machine; (iii) machine eligibility and setup time have to be considered in the cutting and printing stages; (iv) the whole manufacturing system is under a time-of-use electricity pricing policy. For the problem, an integer programming model is firstly proposed and shown to be strongly NP-hard. Then a model-based heuristic is adopted and a bi-objective differential evolution algorithm (BODE) is devised based on problem features. Computational experiments on randomly generated instances demonstrated that the BODE outperforms the model-based heuristic in terms of computation time and solution quality. Moreover, with mild increase on computation burden, the BODE significantly outperforms the classic NSGA II in terms of solution quality.     

基于资金供应链价值视角的最优现金持有方案研究

内部资金的配置不当常常引发公司高层的控制权争夺而损害公司利益。在投资项目中如何设计包含预期投资收入和现金分红比例组合要素在内的最优现金持有方案以提升公司价值成为公司所有者和高管共同面临的问题。本文借鉴报童模型,以公司所有者为先行者,建立了两者之间的斯塔克伯格博弈模型,分析最优现金持有方案的设置及其对公司所有者和高管的影响。研究发现:风险中性的公司所有者总会接受高管内部参股投资,并设置行业现金分红比例以给予高管资金使用方便;最优现金持有方案下,高管总会倾向于选择内部参股而不选择外部投资;此时,公司所有者的收益和资金供应链的效率都会提高,而高管选择外部引资是否能提高收益则取决于已有的薪酬合同水平。研究结论既支持了内部资金市场的"收集有利信息"假说,同时也对公司所有者在控制权私利倾向较强的职业经理人市场中如何科学决策有着重要的借鉴意义。     

Optimal batch size and investment in multistage production systems with scrap

In this paper, we study the problem of selecting the optimum production batch size in multistage manufacturing facilities with scrap and determining the optimal amount of investment. We analyse the effect of investment for quality improvement on the reduction of the proportion of defectives, and the effect of this reduction on processing cost, setup cost, holding cost, and profit loss. The quality characteristic of the product manufactured is assumed to be normally distributed with a mean equal to the target value. The purpose of the investment is to reduce the variance of the quality characteristic and hence the proportion of defectives. The model assumes known demand, which must be satisfied completely, scrappage at each stage and profit loss due to scrap. Using this model, the optimal values of the production quantity and the proportion of defectives for minimizing the total cost are obtained. The optimal investment is then obtained using the relationship between the investment and the proportion of defectives.     

LOGISTICS MANAGEMENT SYSTEM: AN ADVANCED DECISION SUPPORT SYSTEM FOR THE FOURTH DECISION TIER DISPATCH OR SHORT-INTERVAL SCHEDULING

The Logistics Management System (LMS) is a real-time transaction-based system combining decision technologies from AI, MS/OR, and decision support system that serves very successfully as a dispatcher or short-interval scheduler by monitoring and controlling the manufacturing flow of IBM's semiconductor facility near Burlington, Vermont. LMS coordinates the actions and decisions of several logically isolated participants in a serially dependent system of activities. Therefore, it balances the requirements of several goals (cycle time, output, serviceability, and inventory management) that compete for the same resource, exploits emerging opportunities on the manufacturing floor, and reduces the distortion from unplanned events. This paper provides an overview of the LMS application, the concept of interrelated decision tiers in manufacturing decision making, and the need for the dispatch decision tier to successfully reduce apparent randomness. Historically, production and operations management has ignored this decision tier. This has significantly limited our ability to make an impact on the performance of the manufacturing operation.     

An Investigation of Scheduling Policies in a Dual-Constrained Manufacturing Cell*

In previous group scheduling studies, labor has essentially been ignored by assuming that enough labor is assigned to each machine in the cell. In reality, however, management usually does not have the resources to employ a laborer at each machine in the cell (i.e., machines need to share labor). Both labor scheduling and group scheduling heuristics need to be administered to manage the cell effectively. This study develops and examines scheduling procedures for a dual-constrained (i.e., machine and labor) manufacturing cell. Eleven decision rules are developed and tested under 16 different experimental conditions. The experimental factors used are interarrival time distribution, cell load, setup-to-run-time ratio, and transfer-to-run-time ratio. Results show that interarrival time distribution and cell load have the greatest impact on the performance of the cell. This suggests that effective production planning aimed at reducing job arrival variation and leveling the cell load can substantially improve cell performance. Among the experimental factors, setup and transfer-to-run-time ratio factors had the strongest influence on the rankings of the decision rules. These rankings were fairly robust across all experimental conditions and performance measures. The results also indicated that the inclusion of labor as a contraint in the cell had a significant impact on the performance of several group scheduling heuristics. Finally, it was shown that the best performing decision rules consider both transfer time and subfamily setup times.     

Fast,flexible and cooperative supply Chains—key issues for the survival of European industry

The future of the European industry is in its capability to innovate and upgrade. This requirement concerns products, manufacturing and the underlying support systems ranging from organizational arrangements down to decision support systems. Europe has a desperate need for effective and flexible innovation, improving industrial infrastructure where the most value-adding nodes of the supply chains are those in the roles of subcontractors on the one hand and distributors on the other. The necessary managerial changes (such as JIT, lean manufacturing and simultaneous engineering) have so far just superficially influenced these crucial nodes. It can be estimated that by responsive customer-driven supply chains the profitability of these chains could be improved drastically. This potential for improvement is based on the reduction of inventory-carrying costs, reduction of indirect and direct labour costs and the increase of sales and sales margins via better delivery performance at the operative level and a reduction in time-to-market at the tactical and strategic levels. As a necessary prerequisite for responsive supply chains in many branches, reorganization of the supply chains in both the manufacturing and distribution ends of these chains is needed.     

基于粗糙集与主成分分析的属性约简的启发式算法研究

信息系统的属性约简反映了一个决策表的本质信息,为信息系统的数据挖掘奠定的基础。生成一个决策表的所有约简或计算出最佳(定义为属性数目最少)的约简都是NP难问题。目前已有的基于粗糙集的属性约简算法由于计算复杂较高,而不适用大规模数据。本文探讨了一种基于区分矩阵和主成分分析的算法,该算法利用属性在区分矩阵中频率及属性贡献率做为启发规则,寻找最小约简,并在海关通关风险评估系统中得到良好的应用。     

Generating Explanations for Goal-Based Decision Making*

As information systems make the transition from decision support to decision making, there will be a concomitant need for the programs to explain or justify their actions. Without such explanations, humans will not readily cede authority to a machine. This paper describes an automated decision-making program, VOTE, which generates natural language explanations for its decisions in both English and French. The program domain is Congressional roll call voting. VOTE simulates voting decisions of specific members of the United States House of Representatives on given bills. VOTE's natural language generation facility is also used by the underlying databases to interpret the knowledge representations. These underlying knowledge representations are described and applications of this decision making model to the general business domains of strategic planning, investment, and marketing are suggested.     

PRODUCTION SCHEDULING OF CONTINUOUS FLOW LINES: MULTIPLE PRODUCTS WITH SETUP TIMES AND COSTS

The problem of production planning and setup scheduling of multiple products on a single facility is studied in this paper. The facility can only produce one product at a time. A setup is required when the production switches from one type of product to another. Both setup times and setup costs are considered. The objective is to determine the setup schedule and production rate for each product that minimize the average total costs, which include the inventory, backlog, and setup costs. Under the assumption of a constant production rate, we obtain the optimal cyclic rotation schedule for the multiple products system. Besides the decision variables studied in the classical economic lot scheduling problem (ELSP), the production rate is also a decision variable in our model. We prove that our solutions improve the results of the classical ELSP.     

SETUP REDUCTION AND MACHINE AVAILABILITY

This paper is an extension of Billington, who used the framework of the economic production quantity (EPQ) to model setup cost reduction. In the present paper, we use the EPQ model as a starting point to investigate the nature of setup costs and the effect of setup time reduction on the increase in available capacity. Reducing setup is vital to a company's success because a lengthy changeover of machinery is expensive: it demands long production runs to justify its cost, and these, in turn, lead to excessive inventory and to a slow response to customer needs. As in Billington, setup reduction is modeled as a function of an annual amortized investment. The paper examines the behavior of the setup time, the inventory cost, the lot size, and the freeing up of machine time in the face of a capacity constraint. A solution algorithm is provided to find setup times that minimize the sum of setup and holding cost, subject to a constraint on machine availability. The analysis sheds light on the true nature of setup cost and on the opportunity cost of not reducing setups. In the constrained optimization, the Lagrangian multiplier gives an estimate of the marginal value of adding one time unit of machine capacity, or, alternatively, of reducing one unit of setup time.