سیستم پشتیبانی تصمیم گیری مبتنی بر بهینه سازی برای برنامه ریزی استراتژیک در صنعت پردازش: مورد یک شرکت داروسازی در هند
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|28297||2007||12 صفحه PDF||سفارش دهید||6270 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : International Journal of Production Economics, Volume 106, Issue 1, March 2007, Pages 92–103
We describe how a generic multi-period optimization-based decision support system (DSS) can be used for strategic planning in process industries. Built on five fundamental elements — materials, facilities, activities, storage areas and time periods — this DSS requires little direct knowledge of optimization techniques to be used effectively. It is user friendly and requires little knowledge of optimization. Results based on real data from a pharmaceuticals company in India demonstrate significant potential for improvements in revenues and profits.
The primary motivation for this work comes from previous work done by the authors (Dutta and Fourer, 2004, Dutta and Fourer, 2000), in which a generic optimization based decision support system was developed for strategic planning in process industries. This was then customized for an integrated steel plant in North America. The result was a potential increase of 16–17% in the bottom-line of the company. It was claimed that the same approach, being generic, could be applied to various other process industries. In this paper, we demonstrate the application of the same decision support system (DSS) to a Pharmaceutical Company in India. The applications of linear programming based techniques to a process industry (specially the steel industry) have been many. A series of publications (Dutta et al., 1994; Sinha et al., 1995; Dutta and Fourer, 2000) report the conceptualization, development and implementation of a mixed integer linear programming model for optimal power distribution that took about 20 person years. This work resulted in a 58% increase in profitability (or a direct financial benefit of 73 million dollars) during the last six months of the fiscal year 1986–1987, and accrued similar benefits in later years. However, in both of the above cases, the models were customized only for the steel industry. The production system of a pharmaceutical industry is an intermittent one. It produces several types of drugs in varying quantities, which are routed through several machines and share a common set of resources. This leads to an inherently large number of constraints, making the determination of optimality go well beyond the scope of human comprehension and intuition and too complex to be attained manually. We therefore present this optimization based DSS which is aimed at providing strategic support to the pharmaceutical industry. In Section 2, we give a brief account of previous attempts at applying OR/MS concepts in a pharmaceutical setup. In Section 3, we discuss the basic approach of modeling in a process industry. The elements of the database required to define the mathematical model and the optimization steps are discussed in 4 and 5, respectively. In Section 6, we discuss the application of the model in a pharmaceutical company in India. The paper concludes by describing some of the experiments made on the model using real time data from the company and their results, illustrating the possible impact on the bottom-line in Section 7. The mathematical formulation of our model is provided in the Appendix A.