مدل هایی برای برنامه ریزی تولید تحت عدم قطعیت: بررسی

The consideration of uncertainty in manufacturing systems supposes a great advance. Models for production planning which do not recognize the uncertainty can be expected to generate inferior planning decisions as compared to models that explicitly account for the uncertainty. This paper reviews some of the existing literature of production planning under uncertainty. The research objective is to provide the reader with a starting point about uncertainty modelling in production planning problems aimed at production management researchers. The literature review that we compiled consists of 87 citations from 1983 to 2004. A classification scheme for models for production planning under uncertainty is defined.

Galbraith (1973) defines uncertainty as the difference between the amount of information required to perform a task and the amount of information already possessed. In the real world, there are many forms of uncertainty that affect production processes. Ho (1989) categorizes them into two groups: (i) environmental uncertainty and (ii) system uncertainty. Environmental uncertainty includes uncertainties beyond the production process, such as demand uncertainty and supply uncertainty. System uncertainty is related to uncertainties within the production process, such as operation yield uncertainty, production lead time uncertainty, quality uncertainty, failure of production system and changes to product structure, to mention some. In this paper, we will use this typology of uncertainty. Along the years there have been many researches and applications aimed at to formalize the uncertainty in manufacturing systems (Yano and Lee, 1995; Sethi et al., 2002). The literature in production planning under uncertainty is vast. Different approaches have been proposed to cope with different forms of uncertainty. A brief general classification is shown in Table 1. In an effort to gain a better understanding of the ways of managing uncertainty in production planning, and to provide a basis for future research, a broad review of some existing research on the topic has been presented. In a general way, we have selected papers to include in this survey based on two main criteria: (i) Midterm tactical models are the focus of our work. These models address planning horizons of 1–2 years and incorporate some features from both the strategic and operational models. (ii)It is applied on real-world problems, and mainly, on manufacturing systems. We describe briefly what each paper is but we do not describe with detail or formulate the models that have been considered. The motivation of this work is not to identify every bibliography and extended review of them rather it is intended to provide the reader with a starting point for investigating the literature on how best to manage with uncertainty in different production planning problems. The objective of this paper is to (i) review the literature, (ii) classify the literature based on the production planning area and the modelling approach, and, (iii) identify future research directions. This paper is organized as follows. In next section, a classification scheme for models for production planning under uncertainty is introduced. Then, previous research on incorporating uncertainty in models for production planning is reviewed and classified. Finally, the conclusions and directions for further research are given in Section 4.

This paper has presented an exhaustive literature survey about models for production planning under uncertainty. The production planning area and the modelling approach were the taxonomy criteria used. The analytical modelling approach, in particular stochastic programming was the most frequently encountered. In the case of dynamic programming, few models were found and were mainly theoretical. Most of the analytical models addressed only one type of uncertainty, and assumed a simple structure of the production process. For more complex processes, with many different final products and more than one type of uncertainty, the analytical approach is replaced by methodologies based on artificial intelligence and simulation. Although many works use simulation approaches to model uncertainty, very few studies exist on the comparative evaluation of the advantages and inconveniences of different simulation languages. With respect to artificial intelligence models, those based on fuzzy set theory represent an attractive tool to aid research in production management. Lastly, conceptual models with different approaches complete the taxonomy. Although an extensive literature on models for production planning under uncertainty was reviewed, a need for further research is identified: (1) investigation of new approaches to modelling of uncertainty. Uncertainty is impossible to be completely removed from supply chains, and also from each link of the chain (Mula et al., 2005). Optimization problems in the context of production planning in a supply chain, and hence under conditions of uncertainty, are, in general, very complex. For such reason, new approaches for production planning and control are required to manage the uncertainty within each company of the chain. Moreover, it can help supply chains that operate in uncertain environments to be more agile. In our opinion, artificial intelligence based models have a particular interest to the practitioners in order to address the production planning problems under uncertainty. Our position is that fuzzy set theory is, in general, an appropriate methodology which can suppose a great advance in the current production planning systems (see Mula et al., 2006), (2) development of new models that contain additional sources and types of uncertainty, such as supply lead times, transport times, quality uncertainty, failure of production system and changes to product structure, etc. since models with uncertain demand have received more attention in comparison to other types of uncertainty, (3) investigation of incorporating all types of uncertainty in an integrated manner, (4) development of empirical works that compare the different modelling approaches with real case studies, (5) development of a comparative evaluation of the existent models for the different manufacturing systems.