倉儲是物料、零件所存放的地方，提供物料進、出貨的暫存區。若能有效地規劃倉儲儲位，則可以減少庫存空間、降低運送成本及增加作業流程效率。因此，在安排倉儲的空間規劃上，根據現有倉庫的場地特性、設備條件與倉庫的貨物種類進行規劃，使倉庫的每一個空間都可以得到充分的利用，是一個重要的倉儲管理議題。本研究為了能夠有效規劃倉儲的空間，針對所收集之倉儲貨物及成品或半成品的資料進行分析，並以資料分群法將需要儲放之倉儲系統的物件進行分群，期能依分群結果來規劃倉儲空間。此外，由於倉儲貨物管理上，為了儲存空間或工作的需要，必須將所有的倉儲物件依其特性或工作需求事先限制其群組，因此在運用資料分群法時，本研究參考限制分群方法的完整必連（Complete Must-Link, CML）限制，將所收集的資料依CML限制條件進行分群。同時為因應CML資料間的高度重疊性，本研究以加入主成份資訊之完整必連分群 Principal Component Analysis with CML (簡稱PCA-CML)的演算法，將分析之結果應用於倉儲規劃中。本研究之案例公司為一家中小型的模具業公司，利用該公司所提供的倉儲資料，將資料篩選與整理後，加入在倉儲規劃中的限制條件至資料中。再利用PCA-CML分群演算法將其資料進行分群，並利用驗證分群的指標來評估分群結果的優劣。在將分群結果分析後，其結果可提供倉儲之儲位的規劃，並針對新規劃的儲位與原始儲位進行作業距離的比較，其比較結果顯示新儲位的規劃在作業上更有效率。

Warehouse is a common facility in a factory or a supply chain to store the inventory and control the stock flow. In order to increase the space utilization and enhance the efficiency of the stock transportation, how to arrange the warehouse storage to fit the inventory product or stock’s characteristics is an important issue. Besides, due to the special needs of operating or storing criteria, the stocks are usually pre-clustered to multiple groups. Considering the operating and storing criteria is also critical to meet the managerial requirement. In this research, we used one dataset containing the type of manufacturing, their shipping frequency, material, package size, and other relevant information regarding the stock, collected from a warehouse of a mold manufacturer in Taiwan to represent the generality of stock data of warehouse. A data clustering method called Principal Component Analysis with Complete Must-Link (PCA-CML) was applied on the stock dataset to group the stocks. The CML constraints were constructed to meet the operating and storing criteria. Then, the hierarchical clustering method with PCA data was applied to cluster the pre-defined groups. The clustering result was used to study the stock information and then re-arrange the warehouse storage. The clustering result shows that the clustering method with PCA-CML is able to group the stocks based their criteria and also provide the better compactness within the clusters. The clustering result is expected to provide better efficiency of the warehouse management.

Bowersox, D. J. (1996). Logistical Management: The Integrated Supply Chain Process: McGraw-Hill Companies.
Calinski, R. B., & Harabasz, J. (1974). A Dendrite Method for Cluster Analysis.
Combes, C., & Azema, J. (2013). Clustering using principal component analysis applied to autonomy–disability of elderly people. Decision Support Systems, 55(2), 578-586. doi: http://dx.doi.org/10.1016/j.dss.2012.10.016
Davidson, I., & Ravi, S. S. (2005). Agglomerative Hierarchical Clustering with Constraints: Theoretical and Empirical Results. In A. Jorge, L. Torgo, P. Brazdil, R. Camacho & J. Gama (Eds.), Knowledge Discovery in Databases: PKDD 2005 (Vol. 3721, pp. 59-70): Springer Berlin Heidelberg.
Davies, D. L., & Bouldin, D. W. (1979). A Cluster Separation Measure. 224-227.
Dunn, J. C. (1974). Well-Separated Clusters and Optimal Fuzzy Partitions. Journal of Cybernetics 95-104.
Frazelle, E. (2001). Supply Chain Strategy: McGraw-Hill.
Halkidi, M., & Vazirgiannis, M. (2001). Clustering Validity Assessment: Finding the Optimal Partitioning of a Data Set. San Jose, CA.
Halkidi, M., Vazirgiannis, M., & Batistakis, Y. (2000). Quality Scheme Assessment in the Clustering Process. Paper presented at the Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery.
Hein, M., & Buhler, T. (2010). An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA. Paper presented at the Advances in Neural Information Processing Systems 23.
Irfana, M. S. (2013). Data Clustering with Complete Must-Link Constraints. (Master Master's Thesis), National Taiwan University of Science and Technology, Taipei.
Jain, A. (2008). Data Clustering: 50 Years Beyond K-means. In W. Daelemans, B. Goethals & K. Morik (Eds.), Machine Learning and Knowledge Discovery in Databases (Vol. 5211, pp. 3-4): Springer Berlin Heidelberg.
Law, M. C., Topchy, A., & Jain, A. (2004). Clustering with Soft and Group Constraints. In A. Fred, T. Caelli, R. W. Duin, A. Campilho & D. de Ridder (Eds.), Structural, Syntactic, and Statistical Pattern Recognition (Vol. 3138, pp. 662-670): Springer Berlin Heidelberg.
Liu, Y., Li, Z., Xiong, H., Gao, X., Wu, J., & Wu, S. (2012). Understanding and Enhancement of Internal Clustering Validation Measures. IEEE Trans Syst Man Cybern B Cybern. doi: 10.1109/TSMCB.2012.2220543
Rousseeuw, P. J. (1987). Silhouettes: A Graphical aid to the Interpretation and Validation of Cluster Analysis. Journal of Computational and Applied Mathematics, 53-65.
Sharma, S. (1995). Applied Multivariate Techniques (1 edition ed.): Wiley.
Tan, P.-N., Steinbach, M., & Kumar, V. (2005). Introduction to Data Mining (1 edition ed.): Addison-Wesley.
Wagstaff, K., Cardie, C., Rogers, S., Schr, S., #246, & dl. (2001). Constrained K-means Clustering with Background Knowledge. Paper presented at the Proceedings of the Eighteenth International Conference on Machine Learning.
Yang, C. L. (2009). Adaptive Clustering Model for Improving Color Consistency. (Doctor of Philosophy), Purdue University.
Yang, C. L., & Irfana, M. S. (2013). Cooperative Team Building by Data Clustering with Constraints. Paper presented at the IEEE 18th International Conference on Computer Supported Cooperative Work in Design National Tsing Hua University, Hsinchu, Taiwan. http://digilib.its.ac.id/cooperative-team-building-by-data-clustering-with-constraints-29724.html
池麗香. (2002). 電子商務環境下物流中心商品補貨模式. (master), Fu Jen Catholic University, Taipei.
何應欽. (2012). 物流與供應鏈管理：理論與實務 (2 ed.). 台灣: 高立圖書有限公司.
梅藝華. (2010). 倉儲管理實務. 大陸: 北京理工大學出版社.
陳順宇. (2004). 多變量分析: 華泰文化事業股份有限公司.
葉清江, & 賴明政. (2009). 物流與供應鏈管理(第四版). 台灣: 全華圖書.