積體電路(Integrated Circuit , IC)自 1958 年發明以來，促使科技快速發展，目前已廣泛運用在電腦、家電和汽車等產品中。在製程上主要可分為三階段：晶片設計(IC design)、晶圓製造(Wafer fabrication)和晶圓封裝測試(Wafer packaging and testing)。在後端封裝廠，通常會同時接多家上游廠商的訂單，進而導致生產線上充斥少量多樣的產品。排程系統在此當中扮演關鍵角色，其優劣將影響客戶訂單是否可以如期完成。然而，在面對眾多產品及機台時，傳統人工排程方式實屬不易綜觀所有生產資源與限制，又同時能顧及產能利用率及顧客需求。基於以上迫切性，本研究提出一套多階段排程系統，透過混合派工及基因演算法(Hybrid dispatching and genetic algorithm, HDGA)為核心算法，解決半導體封裝銲線站點(Wire bond)的排程問題。本系統涵蓋資料建置、排程演算及結果呈現。演算部分除了考量眾多限制外，如批貨狀態、可用機型、樓層運輸時間等，也需確保生產輔助資源(模具、線材)數量足夠及分配等問題。實證的部分，首先，經與本方法第三階段使用的基因演算法(GA)比較，除了在換模次數與總批貨完工時間上表現較為優異，在排程結果的合理性也能滿足廠內作業人員需求。最後，透過與廠內現有方法(Existing scheduling method, ESM)進行驗證，本方法確實可在要求時間內求出更為優異的績效指標(KPI)結果，進而節省相關人力資源耗費，得以讓公司增進獲利能力。

Since the invention of Integrated Circuit (IC) in 1958, it has promoted the rapid development and has been widely used in products. In the back-end packaging factory, orders from multiple upstream manufacturers are usually received at the same time, resulting in a small number of diverse products on the production line. The scheduling system plays a key role in this, and its pros and cons will affect whether customer orders can be completed on schedule. However, manual scheduling method is not easy to achieve the capacity utilization rate and customer demand under all production resources and constraints.
Based on the above difficulty, this study proposes a multi-stage scheduling system, which uses hybrid dispatching and genetic algorithm (HDGA) as the core algorithm to solve the scheduling problem of semiconductor packaging wire bond (WB) process problem. In addition to considering many constraints, such as lot status, available models, floor transportation time, etc., it is also necessary to ensure that the number of production auxiliary resources (molds, wires) are sufficient and allocated.
The empirical part, first, compared with the genetic algorithm (GA) used in the third stage of this method, in addition to the excellent performance in the number of setup times and the total completion time, the rationality of the scheduling results can also satisfy the needs of employee. Finally, through verification with the existing scheduling method (ESM) in the factory, this method can obtain better KPI within the required time, thereby saving related human resources consumption, allowing the company to improve profitability.

Belegundu, A. D., & Chandrupatla, T. R. (2019), Optimization Concepts and Applications in Engineering, Cambridge.
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, 20,1, 27-45.
Chien, C. F., & 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, 391-419.
Dorigo, M., Maniezzo, V., & Colorni, A. (1991), Positive Feedback as a Search Strategy.
Glover, F. (1986), "Future paths for integer programming and links to artificial intelligence," Computers & Operations Research, 13,5, 533-549.
Guo, C. T., Jiang, Z. B., Zhang, H., & Li, N. (2012), "Decomposition-based classified ant colony optimization algorithm for scheduling semiconductor wafer fabrication system," Computers & Industrial Engineering, 62,1, 141-151.
Holland, J. H. (1975), Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence,Oxford, England.
Hur, Y., Bard, J. F., & Chacon, R. (2019), "Hierarchy machine set-up for multi-pass lot scheduling at semiconductor assembly and test facilities," International Journal of Production Research, 57,14, 4351-4370.
Jamrus, T., Chien, C. F., Gen, M., & Sethanan, K. (2018), "Hybrid Particle Swarm Optimization Combined With Genetic Operators for Flexible Job-Shop Scheduling Under Uncertain Processing Time for Semiconductor Manufacturing," IEEE Transactions on Semiconductor Manufacturing, 31,1, 32-41.
Kagermann, H., Helbig, J., Hellinger, A., & Wahlster, W. (2013), Recommendations for Implementing the Strategic Initiative INDUSTRIE 4.0: Securing the Future of German Manufacturing Industry, Final Report of the Industrie 4.0 Working Group.
Kennedy, J., & Eberhart, R. (1995), "Particle swarm optimization, " Proceedings of ICNN'95 - International Conference on Neural Networks.
Kim, Y. D., Joo, B. J., & Choi, S. Y. (2010), "Scheduling Wafer Lots on Diffusion Machines in a Semiconductor Wafer Fabrication Facility," IEEE Transactions on Semiconductor Manufacturing, 23,2, 246-254.
Kirkpatrick, S. (1984), "Optimization by simulated annealing: Quantitative studies," Journal of Statistical Physics, 34,5, 975-986.
Kress, D., & Muller, D. (2022), "Semiconductor final-test scheduling under setup operator constraints," Computers & Operations Research, 138,20.
Lazarev, A. A. (2007), "Solution of the NP-hard total tardiness minimization problem in scheduling theory," Computational Mathematics and Mathematical Physics, 47,6, 1039-1049.
Lee, Y. H., & Kim, J. W. (2011), "Daily stepper scheduling rule in the semiconductor manufacturing for MTO products," International Journal of Advanced Manufacturing Technology, 54,1-4, 323-336.
Lowe, J. J., & Mason, S. J. (2016), "Integrated Semiconductor Supply Chain Production Planning," IEEE Transactions on Semiconductor Manufacturing, 29,2, 116-126.
Ozturk, O., Begen, M. A., & Zaric, G. S. (2017), "A branch and bound algorithm for scheduling unit size jobs on parallel batching machines to minimize makespan," International Journal of Production Research, 55,6, 1815-1831.
Qiao, F., Ma, Y. M., Zhou, M. C., & Wu, Q. D. (2020), "A Novel Rescheduling Method for Dynamic Semiconductor Manufacturing Systems," IEEE Transactions on Systems Man Cybernetics-Systems, 50,5, 1679-1689.
Shannon, R. E., Long, S. S., & Buckles, B. P. (1980), "Operation Research Methodologies in Industrial Engineering: A Survey," AIIE Transactions, 12,4, 364-367.
Ullman, J. D. (1975), "NP-complete scheduling problems," Journal of Computer and System Sciences, 10,3, 384-393.
Wang, H. K., Chien, C. F., & Gen, M. S. (2015), "An Algorithm of Multi-Subpopulation Parameters With Hybrid Estimation of Distribution for Semiconductor Scheduling With Constrained Waiting Time," IEEE Transactions on Semiconductor Manufacturing, 28,3, 353-366.
Yee, G. C., Feng, C. J., Bin Chik, M. A., & Mokhtar, M. (2021), "Weighted grey relational analysis to evaluate multilevel dispatching rules in wafer fabrication," Grey Systems-Theory and Application, 11,4, 619-649.
Zhong, H. X., Liu, M., & Bao, L. (2021), "A job-priority based soft scheduling approach for uncertain work area scheduling in Semiconductor Manufacturing," International Journal of Production Research, 17.