臺灣博碩士論文加值系統

使用機器學習為基礎，即時派工選擇機制設計生產管制系統(PCS)之知識庫在近年已經有顯著的研究成果。然而目前在晶圓製造廠PCS設計相關研究文獻，則較少使用此一即時派工策略以提升生產績效。此外由於晶圓廠具有短生命產品週期及必須時常變更產品生產組合比例的特性，以往有關機器學習為基PCS在面臨此問題的方法，使用加入新的訓練樣本並且週期性的更新知識庫。因此以機器學習為基PCS會面臨訓練樣本溢位及增加建構派工選擇機制知識庫時間的問題，因此不適合進行即時生產管制。
為解決上述問題，本研究之PCS知識庫經由以下兩個階段來設計：支援向量機(Support Vector Machine)為基礎之知識庫類別選擇機制及支援向量機(Support Vector Machine)為基礎之即時派工分類器。因此本研究提出整合資料探勘技術其內容包含資料探勘過程(Knowledge discovery in databases)如下六個單元：模擬為基礎訓練樣本產生機制、資料正規化機制、經由SVM分類器之基因演算法為基礎之屬性選擇機制、以二階段自我組織映射類神經網路(two-level SOM)建立知識庫類別、SVM為基礎之知識庫類別選擇機制及SVM為基礎之即時派工分類器以達成本研究之目標。
在知識庫類別選擇階段以本研究所提出two-level SOM，將訓練樣本依其相似特質進行群聚分析，將具有類似性質的訓練樣本歸類於同一類別並給予相同知識庫類別標籤。使用SVM對已經賦予知識庫類別標籤的訓練樣本進行學習以建構知識庫類別選擇機制，然後使用SVM以個別地學習不同知識庫類別的訓練樣本以產生即時派工分類器。以提出的整合資料探勘技術為基礎之生產管制系統，相對於經典的機器學習為基礎所建立派工選擇機制及啟發式單一派工法則，長期而言在各種生產績效指標，對晶圓廠之生產績效提升具有更顯著的成效。

Using machine learning-based real time dispatching rule selection mechanism to develop knowledge bases (KBs) for production control system (PCS) has shown encouraging results in recent research. However, there is still little research focusing on employed real time dispatching rule selection mechanism to improve production performance in semiconductor wafer fabri-cation factories PCS. Moreover, due to short product life cycles, most actual FABs produce multiple products and the product mix changes from time to time. All of earlier work of machine learning-based real time PCS must add new training sample and regenerate KBs periodically. Hence, the machine learning-based PCS is confronted with training data overflow problem and increase dispatching rule selection mechanism KB building time and is not suited for on-line production control.
To resolve discussed above problems, the PCS KBs are developed by two phase: SVM-based KB category selection mechanism and SVM-based real time dispatching rule classifier. Therefore, this investigate develops hybrid data mining-based approach includes overall knowledge discovery in data-bases (KDD) processes that comprise six key components: simulation-based training example generation mechanism, data normalization mechanism, GA-based feature selection through SVM classifier, build KB category by two-level self-organizing map (SOM) approach, SVM-based KB category selec-tion mechanism and SVM-based real time dispatching rule classifier to achieve these research goals.
At the KB category selection phase, is applied by two-level SOM ap-proach clustering of the unclassified training data such that data with a similar characteristic which is defined as system attribute fall into the same class. Us-ing SVM learning algorithm learn the whole set of training examples with KB class label to construct KB category selection mechanism. The proposed SVM classifier using the hybrid data mining-based approach yields a better system performance than those obtained with a classical machine learning-based dis-patching rule selection mechanism and heuristic individual dispatching rules under various performance criteria over a long period in FABs.

目 錄
致謝 I
摘要 II
ABSTRACT II
目 錄 III
表 錄 VI
圖 錄 VII
一、緒論 - 1 -
1.1 研究背景與動機 - 1 -
1.2 研究目標 - 5 -
二、文獻探討 - 10 -
2.1 PCS在FABS中的問題 - 10 -
2.1.1 排程類型 - 10 -
2.1.2 排程之績效目標 - 10 -
2.2 在即時派工選擇機制上的相關工作 - 11 -
2.3 以機器學習為基礎的PCS方法在產品組合變異的問題 - 13 -
2.4 SVM運算法則 - 15 -
2.4.1 線性可分的最佳超平面 - 16 -
2.4.2 線性不可分的最佳超平面 - 18 -
2.4.3 在非線性的高尺度的歸納 - 19 -
2.4.4 多類別分類SVM - 20 -
2.5 自我組織圖SOM - 21 -
三、研究方法 - 24 -
3.1 訓練樣本規格 - 24 -
3.2 方法之架構介紹 - 27 -
3.3 資料正規化機制 - 28 -
3.4 使用GA調整以SVM為基礎的分類器 - 29 -
3.4.1 染色體的表現 - 30 -
3.4.2 GA進展周期 - 32 -
3.5 藉由二階段SOM方式建立KB類別 - 34 -
3.6 以SVM為基礎的KB分類選擇機制 - 38 -
3.7 以SVM為基礎的即時派工規則分類器 - 44 -
四、實證與研究 - 46 -
4.1 問題描述 - 46 -
4.2 建構模擬實驗模型 - 51 -
4.3 知識庫之建構 - 54 -
4.3.1 資料正規化處理 - 54 -
4.3.2 分群建立知識庫類別標籤 - 56 -
4.3.3 以SVM為基礎的KB選擇機制 - 58 -
4.3.4 以SVM為基礎的即時派工法則挑選機制 - 59 -
4.4 實證結果 - 60 -
五、結論與未來研究方向 - 64 -
5.1 結論 - 64 -
5.2 未來研究方向 - 64 -
參考文獻 - 66 -

參考文獻
[1]薛友仁，「整合機器學習方法於決策樹為基智慧型排程系統之研究」，國立交通大學工業工程與管理學系博士論文，民國91年。
[2]Arzi, Y., and Iaroslavitz, L., “Operating an FMC by a decision-tree-based adaptive production control system”, International Journal of Pro-duction Research , 38, 675-697, 2000.
[3]Baker, K. R., “Sequencing rules and due-date assignments in a job shop”, Management Science, 30, 1093-1104, 1984.
[4]Berry, M. J., and Linoff, G., “Data Mining Techniques: For Marketing, Sales, and Customer Support”, 1997 (Wiley: New York).
[5]Blackstone, J. H., Philips, D. T. Jr., and Hogg, G. L., “A state-of-the-art survey of dispatching rules for manufacturing job shop operations”, In-ternational Journal of Production Research, 20, 27-45, 1982.
[6]Burges, C. J. C., “A tutorial on support vector machines for pattern rec-ognition”, Knowledge Discovery and Data Mining, 2, 121–167, 1998.
[7]Chen, C. C., Yih, Y., and Wu, Y. C., “Auto-bias selection for learning-based scheduling systems”, International Journal of Production Re-search, 37, 1987-2002, 1999.
[8]Chen, W. H., and Shih, J. Y., “A study of Taiwan’s issuer credit rating systems using support vector machines”, Expert Systems with Applica-tions, 30, 427-435, 2006.
[9]Cho, H., and Wysk, R. A., “A robust adaptive scheduler for an intelli-gent workstation controller”, International Journal of Production Re-search, 31, 771-789, 1993.
[10]Chung, S. H. and Haung C. Y., “The design of rapid production plan-ning mechanism for the product mix changing in a wafer fabrication”, Journal of the Chinese Institute of Industrial Engineers, 20, 153-168, 2003.
[11]Crone, S. F., Lessmann, S., and Stahlbock, R., “The impact of preproc-essing on data mining: An evaluation of classifier sensitivity in direct marketing”, European Journal of Operational Research, 173, 781-800, 2006.
[12]Davies, F. D., and Bouldin, D. W., “A cluster separation measure”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1, 224–227, 1979.
[13]Dreiseitl, S., Ohno-Machado, L., Kittler, H., Vinterbo, S., Billhardt, H., and Binder M., “A comparison of machine learning methods for the di-agnosis of pigmented skin lesions”, Journal of Biomedical Informatics, 34. 28-36, 2001.
[14]Fargher, H. E., Kilgore, M. A., Kline, P. J. and Smith, R. A., “A planner and scheduler for semiconductor manufacturing”, IEEE Transactions on Semiconductor Manufacturing, 7, 117–126, 1994.
[15]Frawley, W. J., Piatetsky-Shapiro, G., and Smyth, P., “The KDD proc-ess for extracting useful knowledge from volumes of data”, Associa-tion for Computing Machinery. Communications of the ACM, 39 (11), 27-34, 1996.
[16]Goldberg, D. E., Genetic Algorithms in search, Optimization and Ma-chine learning (Addison-Wesley: Reading) , 1989.
[17]Han, J., and Kamber, M., Data Mining Concepts and Techniques 2nd edn. (Morgan Kaufmann: San Francisco) , 2006.
[18]Hsieh, B. W., Chen, C. H., and Chang, S. C., “Scheduling semiconduc-tor wafer fabrication by using ordinal optimization-based simulation”, IEEE Transactions on Robotics and Automation, 17, 599-608, 2001.
[19]Johri, P. K., “Practical issues in scheduling and dispatching in semicon-ductor wafer fabrication”, Journal of Manufacturing Systems, 12, 474–485, 1993.
[20]Kohonen, T., Self-Organizing Map third edition (New York, NY: Springer-Verlag) , 2001.
[21]Kumar, P. R., “Scheduling semiconductor manufacturing plants”, IEEE Control Systems, December, 33–40, 1994.
[22]Li, S., Tang, T. and Collins, D. W., “Minimum inventory variability schedule with application in semiconductor fabrication”, IEEE Transac-tions on Semiconductor Manufacturing, 9, 145–149, 1996.
[23]Li, S. T., Shiue, W., and Huang, M. H., 2006, “The evaluation of con-sumer loans using support vector machines”, Expert systems with appli-cations, 30, 772-782.
[24]Lim, T. S., and Shih, Y. S., “A comparison of prediction accuracy, com-plexity, and training time of thirty-three old and new classification algo-rithms”, Machine Learning, 40, 203-228, 2000.
[25]Lu, S. C. H., Ramaswamy, D., and Kumer, P. R., “Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants”. IEEE Transactions on semiconductor manufac-turing, 7, 374-388, 1994.
[26]Montazeri, M., and Van Wassenhove, L. N., “Analysis of scheduling rules for an FMS”, International Journal of Production Research, 28, 785-802, 1990.
[27]Park, S. C., Raman, N., and Shaw, M. J., “Adaptive scheduling in dy-namic flexible manufacturing systems: a dynamic rule selection ap-proach”, IEEE Transactions on Robotics and Automation, 13, 486-502, 1997.
[28]Sabuncuoglu, I., “A study of scheduling rules of flexible manufacturing systems: a simulation approach”, International Journal of Production Research, 36, 527-546, 1998.
[29]Shiue, Y. R., and Guh, R. S., “Learning-based multi-pass adaptive scheduling for a dynamic manufacturing cell environment”, Robotics and Computer-Integrated Manufacturing, 22, 203-216, 2006.
[30]Su, C. T., and Shiue, Y. R., “Intelligent scheduling controller for shop floor control systems: a hybrid genetic algorithm/decision tree learning approach”, International Journal of Production Research, 41, 2619-2641, 2003.
[31]Sun, J., Rahman M., Wong, Y. S., and Hong, G. S., “Multiclassification of tool wear with support vector machine by manufacturing loss consid-eration”, International Journal of machine tools & Manufacture, 44, 1179-1187, 2004a.
[32]Vapnik, V. N., The Nature of Statistical Learning Theory 2nd edn. (Springer: New York) , 1999.
[33]Vesanto, J., and Alhoniemi, E., “Clustering of the Self-organizing map”, IEEE Transactions on Neural Networks, 11(3), 586-600, 2000.
[34]Wein, L. M., “Scheduling semiconductor wafer fabrication”, IEEE Transactions on semiconductor manufacturing, 1, 115-130, 1988.
[35]Wu, S. D., and Wysk, R. A., “An application of discrete-event simula-tion to on-line control and scheduling in flexible manufacturing”, Inter-national Journal of Production Research, 27, 1603-1623, 1989.
[36]eM-Plant. 2003, Object Manual Version and Reference Manual 7.0 (Tecnomatix Technologies: Stuttgart).