本研究為利用AutoMod模擬薄膜電晶體液晶顯示器 ( TFT-LCD ) 彩色濾光片 ( CF ) 6代廠。首先必須蒐集廠內相關資料，包含客戶訂單資訊，生產設備，原料機具，和倉儲系統等，以上述條件為基礎上，此模擬系統才能得到驗證。
台灣為薄膜電晶體液晶顯示器 ( Thin Film Transistor - Liquid Crystal Display, TFT-LCD ) 的重要產地，彩色濾光片 ( Color Filter, CF ) 是TFT-LCD中不可或缺的關鍵零組件。本研究以CF廠的投料與在製品控制為主題，應用系統模擬方法進行研究。面對產線在生產過程中可能因投料之問題及在製品無法有效管制，而造成產出績效不佳或成本提高之問題。本研究以Constant WIP (CONWIP)的概念進行生產規劃，在有限的生產資源下提升績效，並利用AutoMod模擬軟體進行系統化的流程方法建構及分析模擬模式。藉由模擬產出的數據，計算較佳的投料及在製品控制的方式，探討其生產績效。研究結果顯示本研究發展之模式可有效提升產出量及降低在製品量與生產週期時間，並提供管理者作為決策參考之依據，也可提供其他生產相關問題進行模擬分析。
此外，加入類神經網路加以預測，結合AutoMod和類神經網路做比較，達到增加預測系統的精確度，並取代AutoMod模擬的方式，並證實達到時間成本的減少。

This study develops order release planning on the basis of AutoMod simulation of 6th-generation Thin Film Transistor - Liquid Crystal Display (TFT-LCD), color filter (CF) fab. Order assignment to fabs needs to take into account each order’s quantity, type, specification, as well as each fab’s and its downstream fab’s capacity and capability.
Order release and Work-in-Process (WIP) control are two important issues in production management. Too much order release results in both high WIP and long cycle time. To control order release and WIP level, several Constant WIP (CONWIP) control policies for color filter fabs are proposed. An AutoMod simulation model is developed based on real fabs and used to evaluate the performance of these CONWIP alternatives. On the basis of experimental design, simulation results indicate that Multi-CONWIP can increase throughput and decrease both cycle time and WIP. The best CONWIP policy is then applied to real fab for performance improvement.
Moreover, the ANN system was integrated with Artificial Neural Network and AutoMod Software has showed good results in save time to experiment and what-if analyses. But in the forecasting accuracy is not enough. In the future, the method is explored to replace the AutoMod Software and increase the forecasting system accuracy becomes an important issue.

[1] Agrawal, N., 2010. “Review on just in time techniques in manufacturing systems,” Advances in Production Engineering & Management, 5 (2), 101-110.
[2] Cardarelli, G., Palumbo, M., and Pelagagge, M., 1996. “Use of Neural Networks in Modeling Relations between Exposure Energy and Pattern Dimension in Photolithography Process,” IEEE Transactions on Components, Packaging, and Manufacturing technology-Part C, 19 (4), 290-299.
[3] Cao, D., and Chen, M., 2005. “A mixed integer programming model for a two line CONWIP-based production and assembly strategy,” International Journal of Production Economics, 95 (3), 3317-326.
[4] Chambers, M., and Mount-Campbell, C. A., 2002. “Process Optimization via Neural Network Metamodeling,” International Journal Production Economics, 79, 93-110.
[5] Chen, S. H., Chang, C. K., and Kuo, C. L., 2005. “Optimal scheduling in color filter manufacturing,” Journal of Chinese Institute of Industrial Engineers, 22 (4), 301-308.
[6] Chen, J. C., and Chen, C. W., 2010. “Capacity planning of serial and batch machines with capability constraints for wafer fabrication plants,” International Journal of Production Research, 48 (11), 3207-3223.
[7] Chen, W. L., Huang, C. Y., and Lai, Y. C., 2009. “Multi-tier and multi-site collaborative production: Illustrated by a case example of TFT-LCD manufacturing,” International Journal of Computers & Industrial Engineering, 57 (1), 61-72.
[8] Chen, J. C., Chen, C. C., Mo, C. N., Peng, T. W., Chao, G. C., Sun, C. J., Chao, K. J., Chien, J. W., Wei, Y. Y., Feng, C. H., Liu, Y. C., and Chiang, M. T., 2009. “Effective order release and dispatching for color filter fabs.” Society for Information Display International Symposium (SID), San Antonio, Texas, USA.
[9] Chen, J. C., Huang, P. B., Sun, C. J., Chao, K. J., Chao, G. C., Chien, J. W., Chen, C. C., Mo, C. N., Peng, T. W., Wei, Y. Y., Feng, C. H., Liu, Y. C., and Chiang, M. T., 2009. “Simulation modeling of TFT-LCD color filter fab,” International Display Workshops (IDW 2009), Miyazaki, Japan.
[10] Chen, J. C., Su, L. H., Chen, C. C., Peng, T. W., and Chao, G. C., 2011. “Release planning for color filter fabs based on iterative simulation,” Journal of the Society for Information Display, 19 (7), 480-487.
[11] Chow et al., 2002. “Global optimization of absorption chiller system by genetic algorithm and neural network,” 34 (1), 103-109.
[12] Fausett, L., 1994. “Fundamentals of Neural Networks: Architectures, Algorithms and Applications,” Prentice-Hall International.
[13] Fredendall, L. D., Ojha, D., and Patterson, J. W., 2010. “Concerning the theory of workload control,” European Journal of Operational Research, 201 (1), 99-111.
[14] Huang, Y. L., Edgar, T. F., Himmelblau, D. M., and Trachtenberg, I., 1994. “Constructing a Reliable Neural Network Model for a Plasma Etching Process Using Limited Experimental Data,” IEEE Transactions on Semiconductor Manufacturing, 7 (3), 333-344.
[15] Kim, B., Jeong, S., Shin, J., Koo, J., Chae, J., and Lee, S., 2009. “A layout- and data-driven generic simulation model for semiconductor fabs,” IEEE Transactions on Semiconductor Manufacturing, 22 (2), 225-231.
[16] Law, A. M., 2003. “Designing a simulation study: how to conduct a successful simulation study,” Winter Simulation Conference, 66-70.
[17] Liao, D. Y., and Wang, C. N., 2004. “Neural-Network-Based Delivery Time Estimates for Prioritized 300-mm Automatic Material Handling Operations,” IEEE Transactions on Semiconductor Manufacturing, 17 (3), 324-332.
[18] Lippmann, R. P., 1987. “An introduction to computing with neural nets,” IEEE Acoustics, Speech and Signal Pcocessing Mag., 4, 4-22.
[19] Liu, Q., and Huang, D., 2009. “Dynamic card number adjusting strategy in card-based production strategy,” International Journal of Production Research, 47 (21), 6037-6050.
[20] Mohandes, M. A., Halawani, T. O., Rehman, S., and Hussain, A. A., 2004. “Support vector machines for wind speed prediction. Renewable Energy,” 29, 939–947.
[21] Natale, C. D., Proietti, E., Diamanti, R., and D’Amico, A., 1999. “Modeling of APCVD-Doped Silicon Dioxide Deposition Process by a Modular Neural Network,” IEEE Transactions on Semiconductor Manufacturing, 12 (1), 09-115.
[22] Pillai, D. D., Bass, E. L., Dempsey, J. C., and Yelling, E. J., 2004. “300-mm full factory simulation for 90- and 65-nm IC manufacturing,” IEEE Transactions on Semiconductor Manufacturing, 17 (3), 292-298.
[23] Roger, R., J. and Geatz, M. W., 2003. Data mining: A Tutorial-based Primer. Addison-Wesley.
[24] Sargent, R. G., 2009. “Verification and validation of simulation models,” 2009 Winter Simulation Conference, 162-176.
[25] Schikora, P. F., and Godfrey, M. R., 2003. “Efficacy of End-user Neural Network and Data Mining Software for Predicting Complex System Performance,” International Journal of Production Economics, 84, 231-253.
[26] Selvaraj, N., 2008. “Simulation modeling and analysis of single line multi stage manufacturing strategy,” Journal of Scientific and Industrial Research, 67 (4), 277–281.
[27] Stokes, D., and May, G. S., 2001. “Indirect Adaptive Control of Reactive Ion Etching Using Neural Networks,” IEEE Transactions on Robotics and Automation, 17 (5), 650-657.
[28] Takahashi, K., and Nakamura, N., 2002. “Comparing reactive kanban and reactive CONWIP,” Production Planning & Control, 13 (8), 702-714.
[29] Wang, F. K., Du, T., and Wen, F. C., 2007. “Product mix in the TFT-LCD industry,” Production Planning and Control, 18 (7), 584-591.
[30] Yang, T., Hsieh, C. H., and Cheng, B. Y., 2011. “Lean-pull strategy in a re-entrant manufacturing environment: a pilot study for TFT-LCD array manufacturing,” International Journal of Production Research, 49 (6), 1511-1529.
[31] Yu, C. Y., and Huang, H. P., “On-Line Learning Delivery Decision Support System for Highly Product Mixed Semiconductor Foundry,” IEEE Transactions on Semiconductor Manufacturing, 15 (2), 274-278.
[32] Zhang, W., and Chen, M., 2001. “A mathematical programming model for production planning using CONWIP,” International Journal of Production Research, 39 (12), 2723-2734.