IC 產業的競爭核心在於創新思維與資源整合，自動化、差異化和快速回應市場改變才能降低成本、提昇競爭力；為實現上下游供應鏈智能製造策略，生產規劃與排程必須從傳統的人工作業，轉型為具有決策支援的先進規劃排程系統。
先進規劃排程系統需透過許多管理規劃技術，整體考量企業資源限制，達成供給與需求間的平衡規劃。其中啟發式演算法是近年來求解最佳化組合問題的主流，而IC產業鏈測試廠生產排程是零工式工廠排程問題，具有不同工件、不同優序、不同機台之間排序組合的特性，故擬研究應用遺傳演算法求解IC晶圓針測生產排程的最佳化組合問題，來建構先進規劃排程系統中的自動排程模組。
選擇遺傳演算法是因其具有很好的全域搜尋能力，在演算過程中，可以多點同時搜尋，跳出局部區域最佳解，以求得近似最佳解。本研究內容首先以個案公司重視的交期特性（績效指標），開發以此特性設定之適應度函數的遺傳演算法程式；再探討遺傳演算法程式中各參數如：演化代數、交配率、突變率…等對遺傳演算法之影響，並找出最佳化組合。最後蒐集實驗數據，比較自動排程模組和人工排程結果的差異，驗證以自動排程模組取代人工作業能提高排程績效。

IC industry depends on innovative thinking and resource integration. Automation, differentiation, and rapid response to market changes can reduce costs and enhance competitiveness; in order to achieve supply chain intelligent manufacturing strategies, production planning and scheduling must transform to the advanced planning and scheduling system with decision support.
The advanced planning and scheduling system requires many planning techniques to consider the overall resource constraints of the enterprise, and to achieve a balanced plan between supply and demand. In recent years, the heuristic algorithm is the mainstream of solving the optimal problem. So the genetic algorithm is proposed to solve the wafer test problem, as the job-shop scheduling problem which has different work pieces, different priorities, and different machines.
The genetic algorithm is selected because of global search ability. Multiple points can be searched at the same time, to find an approximate best solution. First, develop the genetic algorithm program of the fitness function (based on the delivery). Then discuss the effects of various parameters in the genetic algorithm program such as generations, crossover rate, mutation rate, etc. Finally, collect experimental data, compare the performance of the automatic scheduling module and manual scheduling results.

摘要 I
ABSTRACT II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
第 1 章 緒論 1
1.1 背景 1
1.2 動機 1
1.3 目的 2
1.4 論文架構 3
第 2 章 文獻探討 4
2.1 半導體產業結構 4
2.1.1 半導體產業營運現況 4
2.1.2 半導體產業生管特性 7
2.2 工廠排程問題 8
2.2.1 排程問題分類 8
2.2.2 求解工廠排程問題相關技術 10
2.2.3 零工式工廠排程問題 11
2.3 先進規劃排程系統 12
2.3.1 排程核心引擎之演進 12
2.3.2 先進規劃排程系統架構 14
2.4 遺傳演算法 18
2.4.1 遺傳演算法的步驟 19
2.4.2 遺傳演算法的應用 21
第 3 章 研究方法 24
3.1 系統架構 24
3.2 問題定義 27
3.3 研究限制 29
3.4 系統實作 31
3.4.1 資料模組 31
3.4.2 物料資源規劃 32
3.4.3 產能平衡配置 33
3.4.4 生產排程與再排程 35
3.4.5 遺傳演算法設計 40
第 4 章 實驗設計與分析 49
4.1 實驗設計 49
4.1.1 通用全因子實驗設計 50
4.1.2 實驗因子ANOVA 52
4.2 實驗數據 55
4.3 結果分析 61
4.3.1 排程績效改善 61
4.3.2 排程品質比較 62
4.3.3 分析實驗設計與主效應交互作用 65
第 5 章 結論與未來發展 72
5.1 結論 72
5.2 未來發展 73
參考文獻 74
附錄：驗證資料 78

1. Ali, A., Birkett, M., Hackney, P., & Bell, D. (2016, September). Efficient nondominated sorting with genetic algorithm for solving multi-objective job shop scheduling problems. Multidisciplinary Engineering Design Optimization (MEDO) International Conference, (pp. 1-6).
2. Bang, J.-Y., & Kim, Y.-D. (2011, March). "Scheduling algorithms for a semiconductor probing facility". Computers & Operations Research, Vol. 38, No. 3, pp. 666-673.
3. Blackstone, J. H., Phillips, D. T., & Hogg, G. L. (1982). A state-of-the-art survey of dispatching rules for manufacturing job shop operations. International Journal of Production Research, pp. 27-45.
4. Chaudhry, I. A., & Khan, A. A. (2016, May). A research survey: review of flexible job shop scheduling techniques. International Transactions in Operational Research, Vol. 23, No. 3, pp. 551-591.
5. Chen, J. C., & Chen, C.-W. (2009, May). Capacity planning of serial and batch machines with capability constraints for wafer fabrication plants. International Journal of Production Research, Vol. 48, No. 11, pp. 3207-3223.
6. Chen, J. C., Chen, C.-W., Lin, C. J., & Rau, H. (2005, June). Capacity planning with capability for multiple semiconductor manufacturing fabs. Computers & Industrial Engineering, Vol. 48, No. 4, pp. 709-732.
7. Chen, J. C., Chen, T.-L., Ou, T.-C., & Lee, Y.-H. (2019, December). Adaptive genetic algorithm for parcel hub scheduling problem with shortcuts in closed-loop sortation system. Computers & Industrial Engineering, Vol. 138, pp. 106-114.
8. Chen, J. C., Chen, Y.-Y., Chen, T.-L., & Kuo, Y.-H. (2019, July). Applying two-phase adaptive genetic algorithm to solve multi-model assembly line balancing problems in TFT–LCD module process. Journal of Manufacturing Systems, Vol. 52, Part A, pp. 86-99.
9. Chen, J. C., Fan, Y.-C., & Chen, C.-W. (2009, June). Capacity requirements planning for twin Fabs of wafer fabrication. International Journal of Production Research, Vol. 47, pp. 4473-4496.
10. Chen, J. C., Huang, P. B., Wu, J.-G., Lai, K. Y., Chen, C.-C., & Peng, T.-W. (2013, July). Advanced planning and scheduling for TFT-LCD color filter fab with multiple lines. The International Journal of Advanced Manufacturing Technology, Vol. 67, pp. 101–110.
11. Chen, J. C., Su, L.-H., Sun, C.-J., & Hsu, M.-F. (2010). Infinite capacity planning for IC packaging plants. International Journal of Production Research, Vol. 48, pp. 5729-5748.
12. Chen, J. C., Sun, C.-J., & Chen, T.-L. (2015). Capacity planning for integrated circuit final test plants. International Journal of Computer Integrated Manufacturing, Vol. 28, No. 12, pp. 1262-1274.
13. Chen, J. C., Wu, C.-C., Chen, C.-W., & Chen, K.-H. (2012, September). Flexible job shop scheduling with parallel machines using genetic algorithm and grouping genetic algorithm. Expert Systems with Applications, Vol. 39, No. 11, pp. 10016-10021.
14. Gen, M., Tsujimura, Y., & Kubota, E. (1994). Solving job-shop scheduling problems by genetic algorithm. Proceedings of IEEE International Conference on Systems, Man and Cybernetics, Vol. 2, pp. 1577-1582.
15. Heizer, J. (2006). "生產與作業管理". 偉碩出版社.
16. Holland, J. H. (1992, July). Genetic Algorithms. Scientific American, Vol. 267, No. 1, pp. 66-73.
17. Huang, S., Tian, N., Wang, Y., & Ji, Z. (2016, August). Multi-objective flexible job-shop scheduling problem using modified discrete particle swarm optimization. SpringerPlus, Vol. 5.
18. Jain, A., & Meeran, S. (1999, March). Deterministic job-shop scheduling: Past, present and future. European Journal of Operational Research, Vol. 113, No. 2, pp. 390-434.
19. Kuo, R. J., & Han, Y. S. (2011, August). A hybrid of genetic algorithm and particle swarm optimization for solving bi-level linear programming problem – A case study on supply chain model. Applied Mathematical Modelling, Vol. 35, No. 8, pp. 3905-3917.
20. Salza, P., & Ferrucci, F. (2019, March). Speed up genetic algorithms in the cloud using software containers. Future Generation Computer Systems, Vol. 92, pp. 276-289.
21. Shen, X.-N., & Yao, X. (2015, March). Mathematical modeling and multi-objective evolutionary algorithms applied to dynamic flexible job shop scheduling problems. Information Sciences, Vol. 298, pp. 198-224.
22. Stadtler, H. (2005, June). "Supply chain management and advanced planning – basics, overview and challenges". European Journal of Operational Research, Vol. 163, No. 3, pp. 575-588.
23. Stevenson, W. J. (2011). "Operations Management". McGraw-Hill.
24. Yan, J., & Wu, X. (2015, August). A Genetic Based Hyper-Heuristic Algorithm for the Job Shop Scheduling Problem. Intelligent Human-Machine Systems and Cybernetics (IHMSC) 2015 7th International Conference, Vol. 1, (pp. 161-164).
25. 王立志. (2006). "系統化運籌與供應鏈管理：企業營運新典範". 滄海圖書.
26. 林則孟. (2006). 生產計畫與管理. 華泰書局.
27. 陳建良. (1995). 排程概述. 機械工業雜誌, pp. 122-137.
28. 鄭榮郎. (2018). 生產計畫與管理. 全華圖書.
29. 林子獻. （2014）. 比較模擬退火演算法與禁忌搜尋演算法於TFT-LCD彩色濾光片廠先進規劃排程系統.國立清華大學工業工程與工程管理學系碩士論文. 新竹市.
30. 莊美琪. （2014）. 應用啟發式演算法求解等效率平行機台排程問題. 國立清華大學工業工程與工程管理學系博士論文. 新竹市.
31. 林佩儀. （2016）. 以基因演算法求解彈性製造工廠之製程規劃與排程問題. 國立交通大學工業工程與管理系所碩士論文. 新竹市.
32. 王治平. （2003）. 實際零工式生產排程問題的派工法則. 國立政治大學資訊管理研究所碩士論文. 台北市.
33. 田國興. （2000）. 有設置時間之流程型工廠多階段平行機台總排程時間最小化問題. 中原大學工業工程學系碩士論文. 桃園縣.