在半導體DRAM廠中，有許多生產因素及特定的生產限制，顯著地影響著生產排程的表現，特別是具有昂貴機台，且經常被視為瓶頸站的微影製程更為明顯。即將到來的WIP的高度變異和產品組合的多樣性導致頻繁的調度。此外，由於有限的機台資源，屬於不同產品線的產品，經常需要同時在機台上進行安排，導致在排程中，有需多特殊的製程限制必須被考量，因此，對於微影製程來說，如何開發一個有效且有效率的生產排程是急迫且需要的。
本研究提出了一個兩階段多目標基因演算法(Two-Phase Multi-Objective Genetic Algorithm, TPMOGA)，來求解微影製程的生產排程問題，本研究考慮了多個目標及限制，其中，主要圍繞著四個關鍵生產議題－保持晶圓良率、避免產能損失、維持生產線平衡及滿足客戶需求，所提出的TPMOGA，將會實際應用於台灣的一間半導體DRAM廠中，該公司的微影製程具有兩台不相關平行機。
這項研究中，第一階段是根據每日需求，來安排24小時的光罩(Reticle)排程，結果呈現光罩的安排順序，以及每塊光罩24小時內需做多少片的晶圓，然而，第二階段則考慮更多的製程限制，來安排批次(Lot)順序，並估計每批次在機台的執行時間。最終成果顯示，TPMOGA可以在有限的計算時間下，提供一個可行且有效的排程結果，並且可以改善微影設備的效率。

In the semiconductor DRAM fab, there are various factors and specific constraints significantly affecting the performance of the production scheduling system. In particular, the lithography, with extremely expensive equipment and the reentrant nature of the fabrication processes, is generally the bottleneck. The high-frequency variability of the coming WIP (i.e., work in the previous process) and the diversity of the product mix lead to frequent scheduling. Furthermore, the wafer lots processed by different routes are often produced simultaneously due to limited resources, it causes several process-specific constraints must be considered during scheduling. Thus, it is urgent and beneficial to develop an effective and efficient production scheduling in lithography equipment. This study develops a Two-Phase Multi-Objective Genetic Algorithm (TPMOGA) to solve the multi-objective production scheduling problem for the lithography process. The proposed algorithm is applied to the semiconductor DRAM fab in Taiwan, which has the two unrelated parallel machines in the lithography process. The first phase is to provide a 24-hour rough reticles arrangement plan depending on daily demand, and the result displays the reticles sequence and the number of wafers that should be processed for each reticle. Then, the lots process-specific constraints are considered in the second phase to determine the lots processing sequence and estimated execution time for each lot. The result shows that the proposed TPMOGA provides a feasible scheduling report under limited computational time and improves the efficiency of lithography equipment.

Bitar, A. et al. (2016) ‘A memetic algorithm to solve an unrelated parallel machine scheduling problem with auxiliary resources in semiconductor manufacturing’, Journal of Scheduling. Springer US, 19(4), pp. 367–376. doi: 10.1007/s10951-014-0397-6.
Chien, C.-F. and Chen, C.-H. (2007) ‘A novel timetabling algorithm for a furnace process for semiconductor fabrication with constrained waiting and frequency-based setups’, OR Spectrum, 29(3), pp. 391–419. doi: 10.1007/s00291-006-0062-3.
Dabbas, R. M. and Fowler, J. W. (2003) ‘A new scheduling approach using combined dispatching criteria in wafer fabs’, IEEE Transactions on Semiconductor Manufacturing, 16(3), pp. 501–510. doi: 10.1109/TSM.2003.815201.
Davis, L. (1985) ‘Applying Adaptive Algorithms to Epistatic Domains’, Proceedings of the 9th International Joint Conference on Artificial Intelligence, 85, pp. 162-164.
Deb, K. et al. (2002) ‘A fast and elitist multiobjective genetic algorithm: NSGA-II’, IEEE Transactions on Evolutionary Computation, 6(2), pp. 182-197. doi: 10.1109/4235.996017.
Eiben, A. E. (2002) ‘Genetic algorithms + data structures = evolution programs’, Artificial Intelligence in Medicine. doi: 10.1016/s0933-3657(96)00378-8.
Ham, A. M. and Cho, M. (2015) ‘A Practical Two-Phase Approach to Scheduling of Photolithography Production’, IEEE Transactions on Semiconductor Manufacturing. IEEE, 28(3), pp. 367–373. doi: 10.1109/TSM.2015.2451512.
Holland, J. H. (1992) ‘Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence’, The Quarterly Review of Biology. doi: 10.1137/1018105.
Hong, T.-Y. et al. (2018) ‘A two-phase decoding genetic algorithm for TFT-LCD array photolithography stage scheduling problem with constrained waiting time’, Computers and Industrial Engineering. Elsevier, 125(August), pp. 200–211. doi: 10.1016/j.cie.2018.08.024.
Hwang, C.-L. and Yoon, K. (1981) ‘Methods for Multiple Attribute Decision Making’, Multiple attribute decision making, pp. 58–191. doi: 10.1007/978-3-642-48318-9_3.
Johri, P. K. (1993) ‘Practical issues in scheduling and dispatching in semiconductor wafer fabrication’, Journal of Manufacturing Systems, 12(6), pp. 474–485. doi: 10.1016/0278-6125(93)90344-S.
Kalervo, J. and Jaana, K. (2002) ‘Cumulated Gain-Based Evaluation of IR Techniques’, ACM Transactions on Information Systems, 20(4), pp. 422–446.
Kim, Y. D. et al. (2001) ‘Production scheduling in a semiconductor wafer fabrication facility producing multiple product types with distinct due dates’, IEEE Transactions on Robotics and Automation, 17(5), pp. 589–598. doi: 10.1109/70.964660.
Mann, H. B. and Whitney, D. R. (1947) ‘On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other’, The Annals of Mathematical Statistics, pp. 50-56. doi: 10.1214/aoms/1177730491.
Pham, H. N. A., Shr, A. and Chen, P. P. (2009) ‘Scheduling for the dedicated machine constraint in semiconductor manufacturing using a goal-oriented approach’, Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. IEEE, pp. 551–558. doi: 10.1109/ICTAI.2009.14.
Song, Y. H. et al. (1997) ‘Environmental/economic dispatch using fuzzy logic controlled genetic algorithms’, IEE Proceedings - Generation, Transmission and Distribution, 144(4), pp. 377-382. doi: 10.1049/ip-gtd:19971100.
Taboada, H. A. and Coit, D. W. (2008) ‘Multi-objective scheduling problems: Determination of pruned Pareto sets’, IIE Transactions (Institute of Industrial Engineers), 40(5), pp. 552–564. doi: 10.1080/07408170701781951.
Uzsoy, R. and Martin-Vega, L. A. (1992) ‘A Review of Production Planning and Scheduling Models in the Semiconductor Industry Part I: System Characteristics, Performance Evaluation and Production Planning’, IIE Transactions (Institute of Industrial Engineers), 24(4), pp. 47-60. doi: 10.1080/07408179208964233.
Wein, L. M. (1988) ‘Scheduling Semiconductor Wafer Fabrication’, IEEE Transactions on Semiconductor Manufacturing, 1(3), pp. 115–130. doi: 10.1109/66.4384.
Wilcoxon, F. (1945) ‘Individual Comparisons by Ranking Methods’, Biometrics Bulletin, pp. 196-202. doi: 10.2307/3001968.
Wu, M.-Y. and Lee, C.-Y. (2016) ‘Multi-Objective Stochastic Scheduling Optimization: A Study of Auto Parts Manufacturer in Taiwan’.
Yang, F.-C. and Kuo, C.-N. (2010) ‘A time window rolling- and GA-based method for the ynamic dispatching problem in photolithography area’, 40th International Conference on Computers and Industrial Engineering: Soft Computing Techniques for Advanced Manufacturing and Service Systems, CIE40 2010. doi: 10.1109/ICCIE.2010.5668209.