發展基因模擬退火K-means演算法於供應商集群分析

Developing Genetic Simulated Annealing K-means Algorithm for Suppliers Cluster Analysis

巫國槐(Kuo-Huai Wu)

指導教授 ： 王河星

國立臺北科技大學/管理學院/工業工程與管理研究所/碩士(2007年)

https://doi.org/10.6841/NTUT.2007.00088

摘要

隨著產品應用與發展日趨廣泛且呈現多元化，使得產品逐漸走向多樣少量之客製化生產型態。然而企業為了滿足多樣化之客戶需求並同時兼顧本身之競爭優勢，不得不重視供應鏈管理與整合，以期生產出符合客戶需求的產品。為有效地進行供應商管理與區隔，本研究提出一套結合基因演算法(GA)、模擬退火演算法(SA)與K-means演算法的基因模擬退火K-means演算法(GSKA)。在產品透過物料清單零件展開，確認零組件的所有供應商後，利用此演算法將供應商依照客戶需求之特性包含產品成本、產品品質與製造時間進行集群分析。為了證明所建構的分群模式具有良好的績效，本研究將導入筆記型電腦案例進行零件供應商評選程序，並利用田口方法實驗設計演算法最佳參數。根據分析其執行結果，證明本研究所提出之GSKA集群分析模式的求解品質優於K-means、SKA與GKA模式。因此，透過此集群分析能夠有效剔除不需要的候選供應商，有利於進行供應商管理活動，達到企業獲利的目標。

關鍵字

供應鏈管理 ； 集群分析 ； 基因演算法 ； 模擬退火演算法

並列摘要

The manufacturing industry is shifting to make-to-order pattern with the increasingly widened and diversified product application. To effectively segment and select suppliers, genetic algorithm (GA) was utilized to search for global solution and simulated annealing algorithm (SA) for local solution, so as to enhance the defective clustering results due to the randomly produced center of gravity by K-means, a genetic simulated annealing K-means algorithm (GSKA) was developed. After identifying all suppliers, then suppliers were clustered according to the characteristics in respect to customer needs using GSKA, and each cluster was then denominated in accordance to the characteristics in respect to customer needs. To prove the efficiency of this model, a case with desk computers was introduced, where GSKA and Taguchi method were utilized to cluster parts suppliers, and prove that the GSKA is superior to the K-means, SKA and GKA model in clustering results.

並列關鍵字

Supply chain Management ； Cluster Analysis ； Genetic Algorithm ； Simulated Annealing algorithm

參考文獻

[32] S. H. Chen and S. C. Lo, “Using SOFM-based of Two-phase Segment Method to RFM Variables,” Electronic Commerce Studies, vol. 4, no. 3, 2006, pp. 265-284.

[1] A. L. Chen, “Genetic Algorithm Solution for Partner Selection and Optimization in Virtual Enterprise,” Journal of Jiangsu Polytechnic University, vol. 17, no. 3, 2005, pp. 49-52.

[3] A.K. Jain, M.N. Murty and P. J. Flynn, “Data Clustering: A Review.” ACM Computing Surveys, vol. 31, no. 3, 1999, pp. 264-323.

[4] B. Eleonora and R. Antonio, “An adapted multi-criteria approach to suppliers and products selection - An application oriented to lead-time reduction,” International Journal of Production Economics, vol. 27, 2007.

[5] B. Suman, “Study of simulated annealing based algorithms for multiobjective optimization of a constrained problem,” Computers and Chemical Engineering, vol. 28, no. 9, 2004, pp. 1849-1871.