半導體產業在競爭的環境之下，如何提高生產量，並藉由降低在製品水準來降低生產週期時間為首要課題。而半導體製造當中存在著再回流特性與複雜的製程，使得在製品存貨量的管理變得相當困難。在管理者無法掌控在製品存貨量的情況下，會造成產出量不穩定，生產週期時間更加不易掌控，週期時間的變異也跟著上升，因此，本研究提出了一套在製品存貨的控制方法，利用倒傳遞類神經網路(Back Propagation Neural Networks；BPNN)來釐清產出、生產週期時間、在製品水準這三者的關係，並且訂下整廠與瓶頸工作站最適的在製品水準。
此外，在考量某些上下游站別之間存在的等候時間限制，本研究利用倒傳遞類神經網路找出等候限制時間的長短與在製品數量的關係，以決定出該站別的在製品水準上限，以避免在製品數量過多導致等候時間超過等候時間的限制，有效降低因超過等候時間限制而重工的機率；沒有等候時間限制的站別則先透過過去歷史資料的分析整理，找出上游機台批量大小與下游機台的來到間隔時間變異係數(Ca)的關係，並將此Ca值代入等候線理論中的GI/G/m模型來決定其該分配到的在製品數量為多少。最後，以參考文獻當中所提出的最小存貨變異派工法則(MIVS)為基礎，並針對此派工法則如未考量多種產品組合、以及將在同一個生產優序內的每個晶圓批的重要性視為相同等缺點，利用X-Factor來作為第二層次的派工優序判斷標準，使得原先所定下的每個工作站的標準在製品水準得以藉由此修正後的MIVS派工法來加以維護。透過此新在製品標準，再加上兩層次的派工判斷，使平均生產週期時間降低了約11%，生產週期時間的變異則下降了約13%，此外，因超過等候時間限制而重工的機率也能夠有效下降。

In order to meet the requirement of short product life cycle, the goal of most semiconductor manufacturing is to reduce its manufacturing cycle time and to deliver products at the right time. Base on Little’s Law, cycle time is proportional to the WIP level, given the same throughput rate. Therefore, in order to reduce the cycle time, the most important thing is to control the WIP. From the Theory of Constraints (TOC) , the throughput of a bottleneck workstation is the determinant of the entire fab throughput ,so the first step to control the WIP is to set reasonable WIP levels for the bottleneck workstation and the entire Fab, In this study, the bottleneck WIP and the total fab WIP are estimated by using the neural networks, and then the remaining WIP are allocated to other operations .
In addition, because of yield consideration, a queue time limit is usually set between two continuous operations, which are called the queue time constraint. If the queue time of a lot exceeds the queue time constraint, the lot will be send back to the previous operation for rework .If the times of rework are too many, a lot may even be discarded. So, before allocating the WIP to each operation, setting a reasonable WIP level for the operations which contain the queue time limit to prevent lots from exceeding the limit is necessary. The WIP levels of operations without time constraint are allocated by using the queueing theory.
After setting the standard WIP level of all operations, a dispatching rule to maintain those standard WIP level should be applied. From literature review, there are many useful dispatching rules to reduce the mean cycle time and the standard deviation of the cycle time. But most of them still have some shortages. So in this study, a revised dispatching rule is developed to maintain those standard WIP levels of each workstation and operation, and the mean cycle time and the standard deviation of the cycle time can be effectively reduced.

英文部分:
[1] Uzsoy, R., C. Y. Lee and L. A. Martin-Vega, “A review of production planning and scheduling models in semiconductor industry. Part I: System characteristics, performance evaluation and production planning,” IIE Transactions, 24(4), 47-60, 1992.
[2] Uzsoy, R., C. Y. Lee and L. A. Martin-Vega, “A review of production planning and scheduling models in semiconductor industry. Part II: Shop floor control,”IIE Transactions, 26(5), 44-54, 1994.
[3] Crandall, R. E. and T. H. Burwell, “The Effect of Work-In-Process Inventory Levels on Throughput and Lead Time,” Production and Inventory Management Journal, no. 1, pp. 6-12, 1993.
[4] Maiorana, A., “Improving cycle time through managing variability in DRAM production line,” in Proc. Int. Symp. Semiconductor Manuf. San Francisco, CA, Oct. 1997, pp. A29-A32.
[5] Kumar, S. and P. R. Kumar, “Queueing Network Models in the Design and Analysis of Semiconductor Wafer Fabs,” IEEE Transactions on Robotics and Automation, vol. 17, no. 5, pp. 548-561, 2001.
[6] Miller, D. J. , “ Simulation of a Semiconductor manufacturing line ,” Communications of The ACM 33/10,99-108.
[7] Buzacott, J. A., “The Role of Banks in Flow-line Production Systems,” International Journal of Production Research, vol. 9, no. 4, pp. 425-436, 1971.
[8] Gross, D. and C. M. Harris, Fundamentals of Queueing Theory, John Wiley & Sons, New York, U. S. A., 1974.
[9] Glassey, C. R. and M. G. C. Resende, “A Scheduling Rule for Job Release in Semiconductor Fabrication,” Operation Research Letters, Vol. 7, No.5, pp. 213-217, 1988.
[10] Kim ,Y. D. , J. U. Kim , S. K. Lim and H. B. Jun, “Due-date based scheduling and control policies in a multiproduct Semiconductor wafer fabrication facility,” IEEE Transactions On Semiconductor Manufacturing, vol. 11, pp. 155-164, Feb. 1998.
[11] Spearman, M. L., D. L. Woodruff and W. J. Hopp, “CONWIP: a pull alternative to kanban,” International Journal of Production Research, Vol. 28, No. 5, pp. 879-894. , 1990.
[12] Wein, L. M. , “Scheduling Semiconductor wafer fabrication,” IEEE Transactions on Semiconductor Manufacturing, Vol. 1, No. 3, pp. 115-130. , 1988.
[13] Glassey, C. R. and M. G. C. Resende , “Closed-loop job shop release control for VLSI circuit manufacturing ,” IEEE Transactions on Semiconductor Manufacturing, Vol. 1, No. 1, pp. 36-46. , 1988
[14] Lu, S. C. H. , D. Ramaswamy and P. R. Kumar, “Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants,” IEEE Trans. Semiconductor Manufacturing, vol. 7, pp. 374-388, Aug. 1994.
[15] Dabbas, R. M. and J. W. Fowler , “A new scheduling approach using Combined dispatching criteria in wafer Fabs,” IEEE Transactions on Semiconductor
Manufacturing, Vol. 16, No. 3, pp. 501-510. , 2003.
[16] Lee, Y. H. , J. Park and S. Kim , “Experimental study on input and bottleneck scheduling for a semiconductor fabrication line,” IIE Transactions, Vol. 34, No. 2, pp. 179-190. , 2002.
[17] Yoon, H. J. and D.Y. Lee, “A control method to reduce the standard deviation of flow time in wafer fabrication,” IEEE Transaction on Semiconductor Manufacturing, 13(3):389-392, 2000.
[18] Li, S., T. Tang and D. W. Collins, “Minimum Inventory Variability Schedule with Applications in Semiconductor Fabrication,” IEEE Transaction on Semiconductor Manufacturing, vol. 9, no. 1, pp. 145-149, 1996.
[19] Gelenbe, E. and G. Pujolle, Introduction to Queueing Network. New York: Wiley, 1987.
[20] Duri, C. , Y. Frein and H. S. Lee , “Performance Evaluation and Design of a CONWIP System with Inspections ,” International Journal of Production Economics, vol. 64, pp. 219-229, 2000.
[21] Gstettner, S. and H. Kuhn, “Analysis of Production Control Systems Kanban and CONWIP,” International Journal of Production Research, vol. 34, no. 11, pp. 3253–3274, 1996.
[22] Hoop, W. J. and M. L. Spearman, “Throughput of a Constant Work in Process Manufacturing Line Subject to Failures,” International Journal of Production Research, vol. 29, no. 3, pp. 635-655, 1991.
[23] Ryan, S. M. , B. Baynat and F. F. Choobineh , “Determining Inventory Levels in a CONWIP Controlled Job Shop,” IIE Transaction, vol. 32, no. 2, pp. 105-114, 2000.
[24] Herer, Y. T. and M. Masin , “Mathematical Programming Formulation of CONWIP Based Production Lines and Relationships to MRP,” International Journal of Production Research, vol. 35, no. 4, pp. 1067–1076, 1997.
[25] Burman, D. Y. , F. J. Gurrola-Gal , A. Norzari , S. Sathaye and J. P. Sitarik ,“Performance Analysis Techniques for IC Manufacturing Lines ,” AT&T Technical Journal, vol. 65, no. 4, pp. 46-57, 1986.
[26] Lin, Y. H. and C. E. Lee, “A Total Standard WIP Estimation Method for WaferFabrication,” European Journal of Operation Research, vol. 131, no. 1, pp. 78-94, 2001.
[27] Bonvik, A. M., C. E. Couch and S. B. Gershwin, “A Comparison of Production-line Control Mechanisms,” International Journal of Production Research, vol. 25, no.3, pp. 789-804, 1997.
[28] Choobineh, F. and S. Sowrirajan , “Capacitated – Constant Work in Process(C-CONWIP): a Job Shop Control System.,” Technical report, Industrial and Management Systems Engineering, University of Nebraska, Lincoln, NE 68588-0518, USA, 1996.
[29] Luh, P. B., X. Zhou and R. N. Tomastik, “An Effective Method to Reduce Inventory in Job Shops,” IEEE Transactions on Robotics and Automation, vol. 16, no. 4, pp. 420-424, 2000.
[30] Robinson, J. K. and R. Giglio, “Capacity Planning for Semiconductor Wafer Fabrication with Time Constraints between Operations,” in Proc. 1999 Winter Simulation Conf. , pp. 880-887,1999.
[31] Lee, C. E. and C. W. Chen, “A Dispatching Scheme Involving Move Control and Weighted Due Date for Wafer Foundries,” IEEE Transaction on Components, Packaging, and Manufacturing Technology – Part C, vol. 20, No .4, October 1997.
[32] Tang, T., “Simulation model for minimum inventory variance policy practiced in semiconductor manufacturing plants,” Master of Technology Research Project, Department of Manufacturing and Industrial Technology, Arizona State University, Tempe, Aug. 1993.
[33] Huang, Y. L. , T. F. Edgar , D. M. Himmelblau and I. Trachtenberg , “ Constructing a Reliable Neural Network Model for a Plasma Etching Process Using Limited Experimental Data ,” IEEE Transactions on Semiconductor Manufacturing, vol. 7, no. 3, pp. 333-344, 1994.
[34] Stokes, D. and G. S. May, “Indirect Adaptive Control of Reactive Ion Etching Using Neural Networks,” IEEE Transactions on Robotics and Automation, vol. 17, no. 5, pp. 650-657, 2001.
[35] Liao, D.Y. and C.N. Wang, “Neural-Network-Based Delivery Time Estimates for Prioritized 300-mm Automatic Material Handling Operations,” IEEE Transactions on Semiconductor Manufacturing, vol. 17, no. 3, pp. 324-332, 2004.
[36] Lynes K. and J. Miltenburg, “The application of an open queueing network to the analysis of cycle time, variability, throughput, inventory and cost in the batch production system of a microelectronics manufacturer,” International Journal of Production Economics, 37, 189-203, 1994.
[37] Warner, B. and M. Misra, “Understanding Neural Networks as Statistical Tools,” The American Statistician, 50(4), pp.284-293. , 1996.
[38] Delp, D., J. Si and J.W. Fowler, “The development of the complete X-factor contribution measurement for improving cycle time and cycle time variability,” IEEE Transactions on Semiconductor Manufacturing, vol. 19, no. 3, august, 2006.
[39] Robinson, J. , J. Fowler and E. Neacy , “Capacity Loss Factors in Semiconductor Manufacturing ,” Working paper , 2003.
[40] Martin, D. P. , “ How the law of unanticipated consequences can nullify the theory of constraints ,” in Semiconductor Fabtech, pp. 29 -34.
[41] Whitt, W. , “Approximations for the GI/G/m Queue,” Production and Operations Management , vol. 2, no. 2, pp. 115-161, 1993.
[42] Hopp, W. J. and Spearman, M. L., Factory Physics: Foundations of Manufacturing.2nded. UK: Irwin McGraw-Hill, 2001.

中文部分:
[43] 杜瑩美，「晶圓製造廠之在製品管理模式」， 國立交通大學工業工程與管理研究所 博士論文，民國八十七年。
[44] 簡禎富，蕭禮明，王興仁，「建構半導體製造管理目標層級架構與製造資料之資料 挖礦」，工業工程學刊，第21卷，第4期，第313-327頁，民國九十三年。
[45] 邱偉雄，「半導體晶圓廠黃光區及時派工策略之建構」，國立交通大學工業工程研究所碩士論文，民國八十五年。
[46] 謝志岳，「晶圓製造廠黃光區與爐管區派工法則之研究」，國立交通大學工業工程研究所碩士論文，民國八十七年。
[47] 曾信傑，「應用模糊類神經派工法於晶圓製造廠之研究」，國立台北科技大學生產系統工程與管理研究所碩士論文，民國八十八年。
[48] 葉啟聰，「晶圓製造廠考慮等候時間限制之派工策略」，國立交通大學工業工程研究所碩士論文，民國九十四年。
[49] 簡禎富、林鼎浩、劉巧雯、彭誠湧、徐紹鐘、黃佳琪，「建構晶圓圖分類之資料挖礦方法及其實證研究」，工業工程學刊，第19卷，第2期，第23-38頁，民國九十一年。
[50] 黃英鈺，「晶圓製造廠內時間限制機台之現場管控模式」，中華大學科技管理研究所碩士論文，民國九十三年。
[51] 戚志揚，「半導體製造在製品存貨動態分配及控制方法」，國立清華大學工業工程與管理學系碩士論文，民國九十五年。
[52] 簡禎富，施義成，林振銘，陳瑞坤，「半導體製造技術與管理」，國立清華大學出版社，民國九十四年。
[53] 蘇朝墩，「類神經網路模式與應用---上課補充教材」，清華大學工業工程與工程管理系，台灣，民國九十五年。