應用Fuzzy c-Means演算法之物流中心位址決策模式研究

A Fuzzy c-Means Based Model for Determining the Locations of Distribution Centers

鍾武勳(Wu-Hsun Chung)

指導教授 ： 何應欽

國立中央大學/管理學院/工業管理研究所碩士在職專班/碩士(2006年)

摘要

在現今全球化的世界經濟活動中，供應鍊管理一直是一個極重要的議題。而在供應鍊當中，物流中心（Distribution Center）更扮演了重要角色。其中物流中心的位址對運作成本有極大的影響。本論文即是提出一應用「Fuzzy c-Means 演算法」之物流中心位址決策模式，用以解決多設施位址之決策問題。此決策模式首先採用Fuzzy c-Means 群聚演算法（Fuzzy c-Means），將所有地理上相近之需求點加以分群，形成數個預先決定數量之群集（Cluster）。而在每一個群集中，僅有一個物流中心供應其群集中之需求點。接著採用「重心法」（The Exact Center of Gravity）求取每一個群集所在區域成本最低之最佳位址（Optimal Location）。若「重心法」求取之最佳位址（Optimal Location）因種種環境限制下不可行，則使用模擬退火法（Simulated Annealing）加以修正改善，以求取新的最佳位址。

關鍵字

倉庫位置 ； 位址決策 ； 模糊群集演算法 ； 倉庫 ； 物流中心 ； 群集演算法

並列摘要

Supply chain management is a critical issue in the integrated world economy. Further, distribution center plays a key role in supply chain as the location of distribution centers has a significant impact on the operation cost. In this thesis, a Fuzzy c-Means based model to deal with the multi-facility problem is proposed. First, a clustering algorithm, Fuzzy c-Means, is used to classify demand points with highly similar geographic features to obtain several clusters in a predetermined number. Each cluster has a distribution center supplying all its demand points. Next, the exact center of gravity approach is applied to optimize the location of the distribution center with the minimum cost in each cluster. Finally, if the location obtained from the exact center-of-gravity approach is not infeasible (in the areas which cannot satisfy the basic requirements of a distribution center), a heuristics optimization technique, simulated annealing (SA), is used to improve the optimal solution.

並列關鍵字

Warehouse ； Distribution Center ； Cluster Algorithm ； Fuzzy c-mean ； Location Decision ； Warehouse Location

參考文獻

1. Armour, G. C., and Buffa, E. S., 1963, “A Heuristic Algorithm and Simulation Approach to Relative Location of Facilities,” Management Science, Vol. 9, No. 2, pp. 294-299.

3. Baxter, J., 1984, “Depot Location: A Technique for the Avoidance of Local Optima,” European Journal of Operation Research, Vol. 18, No.2, pp. 208-214.

4. Bezdek, J. C., 1981, Pattern Recognition with Fuzzy Objective Function Algorithms, New York: Plenum Press.

6. Brandeau, M. L., and Chiu, S. S., 1989, “An Overview of Representative Problems in Location Research,” Management Science, Vol. 35, No. 6, pp. 645-674.

7. Cavinato, J. L., 1989, Transportation-Logistics Dictionary, 3rd, ed., Washington: International Thomson Transport Press.