台灣TFT-LCD產業在政府政策扶植下，平面顯示器的總產值逐年升高，中小型尺寸面板製造為積極發展的產業項目。面板製造屬於資金密集投資的產業，大型生產系統的運作需投入高額設備成本，致使產能擴充受限於特定工作站的機台，當該工作站之工件的到達率隨時間變動時，現場排程人員因過度依賴經驗選擇派工法則，使得加工順序之決定缺乏客觀考量，以致機台無法立即提供足夠的產能處理等待加工的在製品，造成工件堆積等候線之停滯問題，此瓶頸現象將影響工廠的績效衡量。週期時間是常見的重要性指標，縮短其值即代表著產品能快速完成加工製程，並提供顧客滿意的需求服務水準；於生產流程上，降低週期時間的變異數，能有效控制製造系統的動態環境，減少因生產變異造成的波動影響。本研究以面板製造為實際案例，利用系統模擬進行關鍵資料的收集，整合人工智慧方法與本論文發展之資料精煉配適法，建立知識型派工法則資料庫構成專家建議，提出合適的派工策略進行實驗，藉由與現實資訊相互驗證，確立本研究所建構的方法，有效掌控生產活動使其維持穩定，且針對現場的情境變化快速反應，達到最小化週期時間變異的目標，提高製造系統的生產績效。

Taiwan TFT-LCD industry is under the circumstances that the government policy is fostered. The gross output value of flat panel displays rises year by year. The medium and small size panels are positive development category. The flat panel industry is fund intensive investment. It invests great amount of equipment cost to extensive production systems causing the limited capacity on specific machines of workstations. As inter arrival of entities varying randomly, machines don’t have enough capacities to operate waiting work-in-process（WIP）immedately and entities in queue are heaped. Because scheduled managers of shop floor control lacks of objective thought and rely on experience unduly to select dispatching rules. It cause to decide the sequence of the process inaccurately. The bottleneck phenomenon impacts the factory performance.
Cycle-time is a common importance index. To shorten its value represents products finish whole production procedure fastly and provide a satisfactory service level. Reducing cycle-time variance of production process can control the dynamic environment of the manufacturing system effectively. It also decreases fluctuation caused by the production variation.This paper is made with the actual case in the flat panel manufacturing. Using simulation approach collects significant data. Combining artificial intelligence method（AI）and data refinement approach（DRA）developed in this paper sets up the dispatching rule database which means “knowledge” like an expert opinion. It practice dispatching strategies to verify the actual information to establish the methodology of the research. To control production activities and to act according to shop floor quickly, the manufacturing system can be robustness. It will improve production performance and minimize cycle-time variability to achieve the goal.

6. 參考文獻
Industrial Economics and Knowledge Center, 2007, Available: http://www.iek.itri.org.tw
Industry & Technology Intelligence Services, 2007, Available: http://www.itis.org.tw
The MathWorks, 2007, Available: http://www.mathworks.com
Abou-Ali, M.G. and Shouman, M.A., 2004, Effect of dynamic and static dispatching strategies on dynamically planned and uplanned FMS, Journal of Materials Processing Technology, 148, 132-138.
Akcalt, E., Nemoto, K. and Uzsoy, R., 2001, Cycle-time improvements for photolithography process in semiconductor manufacturing, IEEE Transactions on Semiconductor Manufacturing, 14, 48-56.
Buzzacott, J.A. and Shanthikumar, J.G., 1993, Stochastic Models of Manufacturing Systems, Prentice-Hall, Englewood Cliffs.
Cardin, O. and Castagna, P., 2006, Handling uncertainty in production activity control using proactive simulation, 12th IFAC Symposium on Information Control Problems in Manufacturing INCOM’2006 , 579-584.
Chong, S.C. and Sivakumar, A.I., 2003, Simulation-based scheduling for dynamic discrete manufacturing, Proceedings of the 2003 Winter Simulation Conference, 1465-1473.
Cochram, J.K. and Horng, H.C., 1999, Dynamic dispatching rule-pairs for multitasking workers in JIT production systems, International journal of Production Research, 37, 2175-2190.
Cowling, P. and Johansson, M., 2002, Using real time information for effective dynamic scheduling, European Journal of Operational Research, 139, 230-244.
Delp, D.R., 2004, A new X-factor contribution measure for identitying machine level capacity constrains and variability, Advance Semiconductor Manufacturing, 2004, ASMC’04, IEEE Conference and Workshop, 334-338.
Delp, D., Si, J. and Fowler, J.W., 2006, The development of the complete X-factor contribution measurement for improving cycle time and cycle time variability, IEEE Transactions on Semiconductor Manufacturing, 19, 352-362.
Gajpal, Y. and Rajendran, C., 2006, An ant-colony optimization algorithm for minimizing the completion-time variance of jobs in flowshops, International Journal of Production Economics, 101, 259-272.
Goldratt, E.M. and Cox, J., 1992, The Goal :A Process of Ongoing Improvement, 2nd edition, North River Press, Great Barrington.
Hagan, M.T., Demuth, H.B. and Beale, M.,1995, Neural Network Design, PWS, Boston.
Hopp, W.J. and Apearman, M.L., 2001, Factory Physics, 2nd edition, McGraw-Hill, New York.
Holthaus, O. and Rajendran, C., 2002, A study on the performance of scheduling rules in buffer-constrained dynamic flowshops, International Journal of Production Research , 40, 3041-3052.
Jacobs, J.H., Etman, L.F.P., van Campen, E.J.J., and Rooda J.E., 2003, Characterization of operational time variability using effective process times, IEEE Transactions on Semiconductor Manufacturing, 16, 511-520.
Joshi, R., 1998, Chip on glass─interconnect for row/column driver packaging, Microelectronics Journal, 29, 343-349.
Kelton, W.D., Sadowski, R.P. and Sturrock, D.T., 2006, Simulation with Arena, 4th edition, McGraw-Hill, New York.
Kim, C.O., Min, H.S. and Yih, Y., 1998, Integration of inductive learning and neural networks for multi-objective FMS scheduling, International Journal of Production Research, 36, 497-509.
Kim, Y.D., Shim, B.C. and Hwang, H., 2003, Simplification methods for accelerating simulation-based real-time scheduling in a semiconductor wafer fabrication facility, IEEE Transactions on Semiconductor Manufacturing, 16, 290-298.
Kohonen, T.,1989, Self-Organization and Associative Memory, Springer-Verlag, Berlin.
Kohonen, T., 1990, The self-organizing map, Proceedings of the IEEE, 78, 1464-1480.
Kumar, P.R., 1994, Scheduling semiconductor manufacturing plants, IEEE Control Systems Magazine, 14, 33-40.
Li, X. and Olafsson, S., 2005, Discovering dispatching rules using data mining, Journal of Scheduling, 8, 515-527.
Lu, S.H. and Kumar, P.R., 1991, Distributed scheduling based on due dates and buffer priorities, IEEE Transactions on Automatic Control, 36, 1406-1416.
Lu, S.C. H., Ramaswamy, D. and Kumar, P.R., 1994, Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants, IEEE Transactions Semiconductor Manufacturing, 7, 374-388.
Min, H.S., Yih, Y. and Kim, C.O., 1998, A competitive neural network approach to multi-objective FMS scheduling, International Journal of Production Research, 36, 1749-1765.
Min, H.S. and Yih,Y., 2003, Development of a real-time multi-objective scheduler for a semiconductor fabrication system, International Journal of Production Research, 41, 2345-2364.
Min, H.S. and Yih, Y., 2003, Selection of dispatching rules on multi dispatching decision points in real-time scheduling of a semiconductor wafer fabrication system, International Journal of Production Research, 41, 3921-3941.
Negnevitsky, M., 2005, Artificial Intelligence, 2ed edition, Addison-Wesley, London.
Rajendran, C. and Holthaus, O., 1999, A comparative study of dispatching rules in dynamic flowshops and jogshops, European Journal of Operational Research, 116, 156-170.
Ribeiro, M.A., Silveria, J. L. and Qassim, R.Y., 2007, Joint optimization of maintenance and buffer size in a manufacturing system, European Journal of Operational Research, 176, 405-413.
Roiger, R. and Geatz, M., 2002, Data Mining: A Tutorial Based Primer, Addison-Wesley, New Jersey.
Sha, D.Y. and Liu, C.H., 2005, Using data mining for due date assignment in a dynamic job shop environment, The International Journal of Advanced Manufacturing Technology, 25, 1164-1174.
Shiue, Y.R. and Su, C.T., 2002, Attribute Selection for neural network-based adaptive scheduling systems in flexible manufacturing systems, International Journal Advanced Manufacturing Technology, 20, 532-544.
Shiue, Y.R. and Su, C.T., 2003, An enhanced knowledge representation for decision-tree based learning adaptive scheduling, International Journal of Computer Integrated Manufacturing, 16, 48-60.
Subramaniam, V. and Raheja, A.S., 2003, mAOR: A heuristic-based reactive repair mechanism for job shop schedules, International Journal of Advanced Manufacturing Technology, 22, 669-680.
Subramaniam, V., Raheja, A.S. and Rama Bhupal Reddy, K., 2005, Reactive repair tool for job shop schedules, International Journal of Production Research, 43, 1-23.
Wong, B.K., Lai, V.S. and Lam, J., 2000, A bibliography of neural network business appliacations research: 1994-1998, Computers and Operations Research, 20, 1045-1076.
Wu, Kan., 2005, An examination of variability and its basic properties for a factory, IEEE Transactions on Semiconductor Manufacturing, 18, 214-221.