本研究主要探討了以模擬退火法為基礎結合變鄰域下降法之啟發式演算法
在 TFT LCD 面板製造業中 Beol 段的自動化排程改善與應用建議。隨著市場訂
單快速變化、少量多樣化生產、大規模生產以及顧客訂單插單/急單頻繁實務運
作下,傳統的人力戰術排程已逐漸難以應對。因此,自動化排程技術成為了提
高生產效率和產品競爭力的重要手段之一。案例是一家面板製造商在 2018 年開
始了人力密集製程自動化升級專案,以改善本身的營運成本增加競爭力。在人
力優化之後傳統人力排程也必須一起升級,因公司舊有生產系統太過龐大,因
此採分段逐步優化策略所花費成本為最佳。本研究以實際工廠排程數據出發,
有效成功減少總換線次數 55%以上、總完工時間可提前 15%以上、總加工時間
可減少 14%以上,並結合現場排程人員經驗提出排程應用建議。

This study focuses on the improvement and application recommendations of automated scheduling using a heuristic algorithm based on simulated annealing combined with the variable neighborhood descent method in the Beol segment of the TFT LCD panel manufacturing company. With the rapid changes in market orders, the need for small-scale diversified production, large-scale manufacturing, and frequent occurrences of rush orders and expedited orders, traditional manual tactical scheduling has become increasingly challenging to cope with. Therefore, automated scheduling technology has become one of the important means to enhance production efficiency and product competitiveness. The case study examines a panel manufacturer that initiated a labor-intensive process automation upgrade project in 2018 to reduce operational costs and increase competitiveness. Following the labor optimization, the traditional manual scheduling also needed to be upgraded. Due to the complexity of the company's existing production system, a segmented gradual optimization strategy was found to be the most cost-effective approach. Based on real factory scheduling data, this research successfully reduced the total number of changeovers by more than 55% and decreased the total processing time by over 14%. Additionally, the study incorporates the practical experience of on-site scheduling personnel to provide scheduling application recommendations.

摘要..........i
Abstract..........ii
誌謝.......... iii
目錄..........iv
圖目錄..........vii
表目錄..........ix
第一章 緒論..........1
1.1 研究背景..........1
1.2 研究動機..........1
1.3 研究目的..........2
1.4 研究架構..........4
第二章 文獻回顧..........5
2.1 單階作業..........5
2.1.1 單機排程..........5
2.1.2 平行機台排程..........6
2.2 多階作業..........11
2.2.1 流線型排程..........12
2.2.2 零工型排程..........12
2.2.3 開放型排程..........13
2.3 工廠導入系統案例..........14
2.3.1 先進規劃系統..........14
2.3.2 解決排程問題..........16
2.3.3 導入系統經驗..........16
2.4 面板廠製造流程簡介..........18
2.4.1 前段製程 - Array..........18
2.4.2 前段製程 - CF ..........19
2.4.3 中段製程 - Cell..........20
2.4.4 後段製程 - 模組組裝..........21
2.5 小結..........22
第三章 研究方法..........24
3.1 問題描述..........24
3.1.1 機台特性..........25
3.1.2 Super Hot Run..........25
3.1.3 Cut 換線次數..........26
3.1.4 Wip 庫存水位..........27
3.1.5 多重 Model 排程..........27
3.2 研究限制..........28
3.3 排程系統演算法..........29
3.3.1 模型架構與符號說明..........29
3.3.2 啟發式演算法..........30
3.3.3 演算法小結..........33
3.4 排程系統導入工廠流程..........34
3.4.1 目標場域現有排程規劃..........34
3.5 總結..........44
第四章 實證研究..........45
4.1 場域環境與程式需求介紹..........45
4.1.1 工廠產線區域位置..........45
4.1.2 產品機台加工時間與生產綁定限制式..........46
4.1.3 數據格式..........48
4.1.4 指標說明..........50
4.2 演算法程式排程結果與效益分析..........51
4.2.1 第一次驗證..........51
4.2.2 第二次驗證..........53
4.2.3 第三次驗證..........57
4.2.4 效益分析小結..........60
4.3 專家訪談..........61
4.3.1 排程導入建議..........61
4.3.2 專家訪談..........61
第五章 研究結論與建議 ..........63
5.1 結論..........63
5.2 未來展望與建議..........64
參考文獻..........65

[1] Al-Harkan, I. M., & Qamhan, A. A. (2019). Optimize Unrelated Parallel Machines Scheduling Problems With Multiple Limited Additional Resources, Sequence- Dependent Setup Times and Release Date Constraints. Ieee Access, 7, 171533- 171547. doi:10.1109/Access.2019.2955975
[2] Bai, D., Zhang, Z-H., & Zhang, Q. (2016). Flexible open shop scheduling problem to minimize makespan. Computers & Operations Research, 67, 207-215. doi:10.1016/j.cor.2015.10.012
[3] Che, A., Wu, X. Q., Peng, J., & Yan, P. Y. (2017). Energy-efficient bi-objective single- machine scheduling with power-down mechanism. Computers & Operations Research, 85, 172-183. doi:10.1016/j.cor.2017.04.004
[4] Cheng, C. Y., & Huang, L. W. (2017). Minimizing total earliness and tardiness through unrelated parallel machine scheduling using distributed release time control. Journal of Manufacturing Systems, 42, 1-10. doi:10.1016/j.jmsy.2016.10.005
[5] Costa, A., Cappadonna, F. A., & Fichera, S. (2017). A hybrid genetic algorithm for minimizing makespan in a flow-shop sequence-dependent group scheduling problem. Journal of Intelligent Manufacturing, 28(6), 1269-1283. doi:10.1007/s10845-015-1049-1
[6] Davari, M., Ranjbar, M., De Causmaecker, P., & Leus, R. (2020). Minimizing makespan on a single machine with release dates and inventory constraints. European Journal of Operational Research, 286(1), 115-128. doi:10.1016/j.ejor.2020.03.029
[7] Ding, H. J., & Gu, X. S. (2020). Improved particle swarm optimization algorithm based novel encoding and decoding schemes for flexible job shop scheduling problem. Computers & Operations Research, 121, 15. doi:10.1016/j.cor.2020.104951
[8] Fleszar, K., & Hindi, K. S. (2018). Algorithms for the unrelated parallel machine scheduling problem with a resource constraint. European Journal of Operational Research, 271(3), 839-848. doi:10.1016/j.ejor.2018.05.056
[9] Fleszar, Krzysztof, Charalambous, Christoforos, & Hindi, Khalil S. (2011). A variable neighborhood descent heuristic for the problem of makespan minimisation on unrelated parallel machines with setup times. Journal of Intelligent Manufacturing, 23(5), 1949-1958. doi:10.1007/s10845-011-0522-8
[10] Fridman, I., Pesch, E., & Shafransky, Y. (2020). Minimizing maximum cost for a single machine under uncertainty of processing times. European Journal of Operational Research, 286(2), 444-457. doi:10.1016/j.ejor.2020.03.052
[11] Hansen, P., Mladenovic, N., & Perez-Britos, D. (2001). Variable neighborhood decomposition search. Journal of Heuristics, 7(4), 335-350. doi:10.1023/a:1011336210885
[12] Holland, John H. (1975). Adaptation in natural and artificial systems. an introductory analysis with applications to biology, control and artificial intelligence. anas.
[13] Hosseinabadi, A. A. R., Vahidi, J., Saemi, B., Sangaiah, A. K., & Elhoseny, M. (2019). Extended Genetic Algorithm for solving open-shop scheduling problem. Soft Computing, 23(13), 5099-5116. doi:10.1007/s00500-018-3177-y
[14] Hsu, Tzu-Han, et al. Development of a Cloud-based Advanced Planning and Scheduling System.Procedia Manufacturing, vol. 17, 2018, pp. 427-434. doi: 10.1016/j.promfg.2018.10.066.
[15] Huang, Hsiang-Hsi, et al. A research on problems of mixed-line production and the re-scheduling.Robotics and Computer-Integrated Manufacturing, vol. 29, no. 3, 2013, pp. 64-72. doi: 10.1016/j.rcim.2012.04.014.
[16] Joo, C. M., & Kim, B. S. (2015). Hybrid genetic algorithms with dispatching rules for unrelated parallel machine scheduling with setup time and production availability. Computers & Industrial Engineering, 85, 102-109. doi:10.1016/j.cie.2015.02.029
[17] Jouhari, H., Lei, D. M., Al-qaness, M. A. A., Abd Elaziz, M., Ewees, A. A., & Farouk, O. (2019). Sine-Cosine Algorithm to Enhance Simulated Annealing for Unrelated Parallel Machine Scheduling with Setup Times. Mathematics, 7(11), 18. doi:10.3390/math7111120
[18] Kim, J. G., Song, S., & Jeong, B. (2020). Minimising total tardiness for the identical parallel machine scheduling problem with splitting jobs and sequence- dependent setup times. International Journal of Production Research, 58(6), 1628-1643. doi:10.1080/00207543.2019.1672900
[19] Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983). Optimization by Simulated Annealing. Science, 220(4598), 671-680. doi:10.1126/science.220.4598.671
[20] Komaki, G. M., Teymourian, E., & Kayvanfar, V. (2016). Minimising makespan in the two-stage assembly hybrid flow shop scheduling problem using artificial immune systems. International Journal of Production Research, 54(4), 963- 983. doi:10.1080/00207543.2015.1035815
[21] Kundakci, N., & Kulak, O. (2016). Hybrid genetic algorithms for minimizing makespan in dynamic job shop scheduling problem. Computers & Industrial Engineering, 96, 31-51. doi:10.1016/j.cie.2016.03.011
[22] Li, X. Y., & Gao, L. (2016). An effective hybrid genetic algorithm and tabu search for flexible job shop scheduling problem. International Journal of Production Economics, 174, 93-110. doi:10.1016/j.ijpe.2016.01.016
[23] Lin, D. Y., & Huang, T. Y. A Hybrid Metaheuristic for the Unrelated Parallel Machine Scheduling Problem.Mathematics, vol. 9, no. 7, 2021, Article 768. doi: 10.3390/math9070768.
[24] Lin, S. W., & Ying, K. C. (2017). Uniform Parallel-Machine Scheduling for Minimizing Total Resource Consumption With a Bounded Makespan. Ieee Access, 5, 15791-15799. doi:10.1109/access.2017.2735538
[25] Machine scheduling problem with sequence dependent setup times, precedence constraints and machine eligibility restrictions. Computers & Industrial Engineering, 98, 40-52. doi:10.1016/j.cie.2016.05.020
[26] Marinho Diana, Rodney Oliveira, & de Souza, Se?rgio Ricardo. (2020). Analysis of variable neighborhood descent as a local search operator for total weighted tardiness problem on unrelated parallel machines. Computers & Operations Research, 117. doi:10.1016/j.cor.2020.104886
[27] Mir, M. S. S., & Rezaeian, J. (2016). A robust hybrid approach based on particle swarm optimization and genetic algorithm to minimize the total machine load on unrelated parallel machines. Applied Soft Computing, 41, 488-504. doi:10.1016/j.asoc.2015.12.035
[28] Ozbak?r, L., Yenisey, M., & Ekinci, E. (2015). Open shop scheduling problem with a multi-skills resource constraint: a genetic algorithm and an ant colony optimisation approach. International Journal of Production Research, 53(1), 292-310.
[29] Pang, Jihong, et al. A scatter simulated annealing algorithm for the bi-objective scheduling problem for the wet station of semiconductor manufacturing. Computers & Industrial Engineering, vol. 123, 2018, pp. 54-66. doi:10.1016/j.cie.2018.06.017
[30] Pinedo, M. L. (2012). Scheduling: Theory, Algorithms, and Systems (4th ed.). Springer.
[31] Ruiz, R., & Stutzle, T. (2007). A simple and effective iterated greedy algorithm for the permutation flowshop scheduling problem. European Journal of Operational Research, 177(3), 2033-2049. doi:10.1016/j.ejor.2005.12.009
[32] Santos, H. G., Toffolo, T. A. M., Silva, Cltf, & Vanden Berghe, G. (2019). Analysis of stochastic local search methods for the unrelated parallel machine scheduling problem. International Transactions in Operational Research, 26(2), 707-724. doi:10.1111/itor.12316
[33] Soares, L. C. R., & Carvalho, M. A. M. (2020). Biased random-key genetic algorithm for scheduling identical parallel machines with tooling constraints. European Journal of Operational Research, 285(3), 955-964. doi:10.1016/j.ejor.2020.02.047
[34] Vallada, E., & Ruiz, R. (2011). A genetic algorithm for the unrelated parallel machine scheduling problem with sequence dependent setup times. European Journal of Operational Research, 211(3), 612-622. doi:10.1016/j.ejor.2011.01.011
[35] Wang, I. L., Yang, T. H., & Chang, Y. B. (2012). Scheduling two-stage hybrid flow shops with parallel batch, release time, and machine eligibility constraints. Journal of Intelligent Manufacturing, 23(6), 2271-2280. doi:10.1007/s10845- 011-0571-z
[36] Wang, X. M., Li, Z. T., Chen, Q. X., & Mao, N. (2020). Meta-heuristics for unrelated parallel machines scheduling with random rework to minimize expected total weighted tardiness. Computers & Industrial Engineering, 145. doi:UNSP 10650510.1016/j.cie.2020.106505
[37] Ying, K. C., & Lin, S. W. (2017). Minimizing Makespan in Distributed Blocking Flowshops Using Hybrid Iterated Greedy Algorithms. Ieee Access, 5, 15694- 15705. doi:10.1109/access.2017.2732738
[38] Yu, C. L., Semeraro, Q., & Matta, A. (2018). A genetic algorithm for the hybrid flow shop scheduling with unrelated machines and machine eligibility. Computers & Operations Research, 100, 211-229. doi:10.1016/j.cor.2018.07.025
[39] 王慶煌(2022)，應用基因演算法於流程式排程之研究-以J公司為例，國立雲林科技大學
[40] 王駿威(2014)，應用即時交貨啟發式演算法於最小化 訂單延遲與提早完工之排程問題 -以精密刀具加工製造業為例，東海大學
[41] 吳民友(2016)，多目標隨機排程最佳化:以台灣汽車零組件製造商為例，國立成功大學
[42] 李家岩, 洪佑鑫(2022)，製造數據科學：邁向智慧製造與數位決策，前程文化
[43] 林則孟(2012)，生產計畫與管理，華泰文化
[44] 紀進鎧(2014)，觸控感應面板廠導入先進規劃排程系統以解決人力排程問題—以A公司為例，國立成功大學
[45] 郭建男(2009)，基因演算法應用於面板產業Cell製程後段排程之研究—以H公司為例，國立成功大學
[46] 陳建宏(2013)，整合元件製造廠導入先進規劃與排程系統之研究-以A公司為例，國立臺北科技大學
[47] 陳嘉杰(2005)，自動派送系統導入光電面板產業製造之研究，國立成功大學
[48] 陳澤明(2007)，航太製造業導入先進規劃與排程系統之個案研究，逢甲大學
[49] 蔡沛霖(2022)，可拆分訂單生產排程問題之研究，國立清華大學
[50] 謝仲為(2002)，先進規劃與排程系統應用於TFT-LCD產業之研究，東海大學