透過您的圖書館登入
IP:3.144.27.148
  • 學位論文

雙不確定性穩健最佳化模式建置應用在供應商評選

Development of Robust Optimization Model with Two Uncertainties in Supplier Selection

指導教授 : 車振華
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


隨著產業競爭越來越激烈,決策者不只要確保能快速生產出消費者所需要的產品,還要盡量地壓低所付出的成本,因此在供應鏈管理中供應商評選成為一個重要的環節。成本包含了購買與製造時的固定成本,以及因不確定性而造成的浪費成本;值得注意的是,由於不確定性是無法避免,且是影響決策者的一個重要因素,固許多文獻都在探討如何控制一個不確定性或將其影響減至最低。然而,在現實生活中,有許多不確定性會同時影響,且彼此之間有交互作用而造成連動的衝擊,因此本研究希望藉由改良舊有的穩健最佳化的方法,來控制兩個不確定性在交互作用時所造成的影響。 本研究在考量供應商生產及運輸可靠度評選問題的背景下,欲發展出一個穩健最佳化模式;此外,以非支配解基因演算法作為決穩健最佳化問題的研究方法。透過穩健代價的分析,探討其與保護程度之間的關係,並將穩健最佳化模式與確定性模式的結果,提供決策者是否有需執行穩健規劃之必要性。

並列摘要


As the industrial competition become increasingly intense, decision makers must not only ensure that products required by consumers can be quickly produced, but also try to drive down the production costs. As a result, the supplier selection in supply chain management becomes an important factor. The production costs include both the fixed costs in the purchase and manufacture process and idling costs caused by the uncertainty involved in the production process. Uncertainty has always been an important factor affecting decisions for the decision makers. Due to the uncertainty is unavoidable, so many researches have been devoted in discussing how to control an uncertainty or minimize their impacts. However, in reality, there are many uncertainties cause effects simultaneously, and the interactions between the uncertainties often caused serial impacts consequentially. The purpose of this study is to control the impacts of interactions caused by two uncertainties by improving the traditional robust optimization method. Therefore, this study aims to develop a robust optimization model to deal with uncertainties in supply chain management, in particular the vendor production reliability and transportation supplier reliability upon supplier selection. In addition, this study used non-dominated sorting genetic algorithms in aid of solving robust optimization problem. Finally, by analyzing robust optimization, this study discuss the relationship between the degree of protection and consideration of sound and robust optimization model; and further inquire the results of the deterministic model in order to provide the decision-makers necessary references in deciding whether to perform robust planning.

參考文獻


1. A. Ben-Tal and A. Nemirovski, “Robust solutions of Linear Programming problems contaminated with uncertain data” Mathematical Programming, vol. 88, 2000, pp. 411-424.
2. A. Ben-Tal and A. Nemirovski, “Robust solutions of uncertain linear programs, “Operations Research Letters, vol. 25, no. 1, 1999, pp. 1-13.
3. A. L. Soyster, “Convex programming with set-inclusive constraints and applications to inexact linear programming, ”Operation Research, vol. 21, no. 5, 1973, pp. 1154-1157.
4. A. R. Rahimi-Vahed, S. M. Mirghorbani and M.Rabbani, “A new particle swarm algorithm for a multi-objective mixed-model assembly line sequencing problem,” Soft Computing - A Fusion of Foundations, Methodologies and Applications, vol. 11, no. 10, 2007, pp. 997-1012.
6. C. Bohle, S. Maturana and J. Vera, ”A robust optimization approach to wine grape harvesting scheduling,” European Journal of Operational Research, vol. 200, 2010, pp. 245-252.

延伸閱讀