Knowledge-based production management approaches, results and prospects

Abstract

Puoc reonr,rr burden forgirs -oileton of ,nforrralo-s.' esil-ted to A-eaq I'onur oer rcwn,*."nCludmng the time tor reviewing instrucions. searcmhrnq eiift-ri data sources gathering and maintaining the oata needed. and con'pieting and reviewing h CC. A1BSTRACT WMaxirrnum,10woras) In this paper we provide an overview of research in the field of knowledge-based production management. We begin by examining the important sources of decision-making difficulty in practical production management domains, discussing the requirements implied by each with respect to the development of effective production management tools, and identifying the general opportunities in this regard provided by Al-based technology. We then categorize work in the field along several different dimensions, indicating the principal types of manufacturing domains that have received attention, the particular production management and control activities that have been emphasized, and the various perspectives that have emerged with respect to the tradeoff that must be made in practical production management contexts between predictive decision-making to optimize behavior and reactive decision-making to manage executional uncertainty. The bulk of the paper focuses on summarizing the dominant approaches to knowledge-based production management that have emerged. Here, we identify the general concepts, principles, and techniques that distinguish various paradigms, characterize the strengths and weaknesses of each paradigm from the standpoint of different production management requirements, and indicate the results that work within each paradigm has produced to date. Among the paradigms for knowledge-based production management considered are rule-based scheduling, simulation-based scheduling, constraint-based scheduling, fuzzy scheduling, planning and scheduling, iterative scheduling, and interactive scheduling. We also examine work aimed at integrating heterogeneous planning and scheduling methods (both Al and CIR Lngoj) ,Indi th', rn-nctinn nf z)-wn fcnr mth~ijirv prniutn m neni ind cicnirol, Finalig-we 'in'ev morn. SUBJECT TERMS AbstractOver the past decade, a large (and continually increasing) number of efforts (both research and development) have sought to investigate and exploit the use of Artificial Intelligence (AI) concepts and techniques in production management applications. In some cases, Al-based concepts have provided frameworks for making traditional Operations Research (OR) techniques more accessible and usable in practical production management settings. In others, novel concepts and techniques have been developed that offer new opportunities for more cost-effective factory performance. While this field of "knowledge-based" production management is still fairly young and the literature is still dominated by experimental research systems, results are nonetheless starting to have an impact in actual production environments. In recent years, several systems have made their way into operation, and many have been attributed with substan...

Production/maintenance cooperative scheduling using multi-agents and fuzzy logic

“…In that context, it is paradoxical that even if scheduling has been recognized for a long time as a multi-objective process (Smith 1992), it is seldom admitted that other functions should interfere with production during the schedule elaboration. In practise, the objectives taken into account are usually only related to the customer's satisfaction (`external' or`exogenous' objectives, related to due date, quality or service) or aim at satisfying internal constraints of the production system (`internal' or`endogenous' objectives: minimize work in progress, optimize resource use, etc.)…”

Learning by Objectives for Adaptive Shop‐Floor Scheduling*

“…Scheduling goals vary, and a balance amongst a variety of criteria is often sought in real world scheduling (Rodammer and White, 1988;Smith, 1992).…”

“…Most solution approaches focus on first obtaining a schedule for the production activities and then putting this predetermined schedule through execution. While obtaining master-schedules is important on a larger time-scale, such static schedules rapidly become obsolete in the dynamic environment (McKay, Safayeni and Buzacott, 1988), and in reality scheduling is often carried out through "adhoc fire-fighting by human decision makers when unexpected situations demand change" (Smith, 1992).…”

“…It is emphasized, however, that for maximal benefit, AI and traditional approaches should be utilized in a complementary manner (Bel, Bensana, Dubois, Erschier and Esquirol, 1989). A variety of knowledge-based approaches have been proposed for effective production scheduling (see Smith (1992) for a review).…”

Proposition of New Genetic Operator for Solving Joint Production and Maintenance Scheduling: Application to the Flow Shop Problem

“…The majority of works concerning the interaction between production and maintenance use probabilistic approaches. The aim is to determine the best moment to plan maintenance task according to a compromise between the maintenance cost and the risk of machines unavailability [9,10,11]. Binding together these two functions is natural.…”