由於消費性電子市場的蓬勃發展，連帶著使被動元件的需求也持續上升，其中多層陶瓷電容 (Multi-Layer Ceramic Capacitor, MLCC)為市場中產值最大的電容產品，作為電子元件中的重要零件，因其體積小又具有高溫和高電壓的耐受性且運作溫度範圍廣的特性，因而廣泛應用於3C電子產品。
然而在MLCC製程包含十五個製程步驟，其中Binder Burn Out (BBO)站和後站燒結站 (Sintering)的協調對排程來說相當關鍵，BBO站是針對前製程所添加的黏結劑經加熱去除，使產品中的含量降低，留下少許的黏結劑使下一站燒結站可以藉由高溫使陶瓷粉末結合成緻密而強固之固體，並產生基本電性。由於產品種類繁多且批貨間的大小不一，不同規格與條件都需經過縝密的判斷才能夠進行集批生產，在過去總仰賴現場人員依照經驗來安排批貨，導致耗費的時間冗長且無法遵照固定邏輯進行排程，使得BBO站成為瓶頸站，因此本研究旨在針對零工式生產等效平行機台問題中BBO站的特性與限制開發一套自動化的生產排程系統， 以最小完工時間為目標提高整體生產效率。
本研究提出了兩種方法來解決MLCC製造過程中BBO站的生產排程問題：派工法則結合動態規劃，以及基因演算法 (Genetic Algorithm, GA)。派工法則結合動態規劃提供了一種處理生產限制的結構化方法，確保排程過程系統化並遵循預定規則，減少人為錯誤的可能性。而基因演算法則通過模仿自然選擇過程，能有效在廣大的搜索空間中找到最佳或近似最佳解。透過本研究提出的方法，能夠最小化完工時間，避免生產中斷和燒結站待料產生的等待時間，降低生產成本，同時提高排程的靈活性，並應對生產環境的變化。

Due to the rapid growth of the consumer electronics market, the demand for passive components has also continuously increased. Among these, the Multi-Layer Ceramic Capacitor (MLCC) stands as the highest-value capacitor product in the market. As a critical component in electronic devices, MLCC are widely used in 3C electronic products due to their small size, high temperature and voltage tolerance, and broad operating temperature range. However, the MLCC manufacturing process involves fifteen steps, with the coordination between the Binder Burn Out (BBO) station and the subsequent Sintering station being crucial for scheduling. The BBO station removes the binders added in the preceding process through heating, reducing their content and leaving a small amount of binder. This allows the subsequent Sintering station to use high temperatures to consolidate the ceramic powder into a dense and strong solid, thereby creating the basic electrical properties. Due to the wide variety of products and varying batch sizes, different specifications and conditions must be meticulously evaluated to enable batch production. Traditionally, scheduling relied heavily on the experience of on-site personnel, leading to lengthy scheduling times and an inability to follow a fixed logic, thereby making the BBO station a bottleneck.
This study aims to develop an automated production scheduling system for the BBO station, addressing its unique characteristics and constraints in the context of job shop scheduling problems with parallel machines, to maximize equipment utilization and enhance overall production efficiency with the goal of minimizing completion time. The study proposes two methods to resolve the production scheduling issues at the BBO station in the MLCC manufacturing process: the integration of dispatching rules with dynamic programming (DRDP), and the Genetic Algorithms for Batch Production (GABP). The combination of dispatching rules and dynamic programming provides a structured approach to handling production constraints, ensuring a systematic scheduling process that adheres to predefined rules and minimizes human errors. Meanwhile, the GABP, inspired by the process of natural selection, effectively searches a vast solution space to find the optimal or near-optimal solutions. By implementing the proposed methods, the utilization rate of the BBO station's equipment can be maximized, production interruptions can be avoided, and waiting times at the Sintering station can be minimized. This not only reduces production costs but also enhances scheduling flexibility and adaptability to changes in the production environment.

Bellman, R., 1966 DYNAMIC PROGRAMMING, Science Vol. 153, (3731), 34-&.
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 Vol. 20, (1), 27-45.
Blanchard, A. E., Shekar, M. C., Gao, S., Gounley, J., Lyngaas, I., Glaser, J., & Bhowmik, D., 2022 Automating Genetic Algorithm Mutations for Molecules Using a Masked Language Model, Ieee Transactions on Evolutionary Computation Vol. 26, (4), 793-799.
Dobson, G., & Nambimadom, R. S., 2001 The batch loading and scheduling problem, Operations Research Vol. 49, (1), 52-65.
Gao, J., Sun, L. Y., & Gen, M. S., 2008 A hybrid genetic and variable neighborhood descent algorithm for flexible job shop scheduling problems, Computers & Operations Research Vol. 35, (9), 2892-2907.
Haupt, R., 1989 A SURVEY OF PRIORITY RULE-BASED SCHEDULING, Or Spektrum Vol. 11, (1), 3-16.
Holland, J. H. (1975). Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press.
Holthaus, O., & Rajendran, C., 1997 Efficient dispatching rules for scheduling in a job shop, International Journal of Production Economics Vol. 48, (1), 87-105.
Kim, Y. J., Jang, J. W., Kim, D. S., & Kim, B. S., 2022 Batch loading and scheduling problem with processing time deterioration and rate-modifying activities, International Journal of Production Research Vol. 60, (5), 1600-1620.
Koh, S. G., Koo, P. H., Kim, D. C., & Hur, W. S., 2005 Scheduling a single batch processing machine with arbitrary job sizes and incompatible job families, International Journal of Production Economics Vol. 98, (1), 81-96.
Liu, D. R., Xue, S., Zhao, B., Luo, B., & Wei, Q. L., 2021 Adaptive Dynamic Programming for Control: A Survey and Recent Advances, Ieee Transactions on Systems Man Cybernetics-Systems Vol. 51, (1), 142-160.
Mathirajan, M., & Sivakumar, A. I., 2006 A literature review, classification and simple meta-analysis on scheduling of batch processors in semiconductor, International Journal of Advanced Manufacturing Technology Vol. 29, (9-10), 990-1001.
May, G., Stahl, B., Taisch, M., & Prabhu, V., 2015 Multi-objective genetic algorithm for energy-efficient job shop scheduling, International Journal of Production Research Vol. 53, (23), 7071-7089.
Norman, B. A., & Bean, J. C., 1999 A genetic algorithm methodology for complex scheduling problems, Naval Research Logistics Vol. 46, (2), 199-211.
Pinedo, M. L. (2012). Scheduling (Vol. 29). Springer.
Shapiro, J. F., 1993 Mathematical programming models and methods for production planning and scheduling, Handbooks in operations research and management science Vol. 4, 371-443.
Song, Z. Y., Hofmann, H., Li, J. Q., Han, X. B., & Ouyang, M. G., 2015 Optimization for a hybrid energy storage system in electric vehicles using dynamic programing approach, Applied Energy Vol. 139, 151-162.
Subramaniam, V., Ramesh, T., Lee, G. K., Wong, Y. S., & Hong, G. S., 2000 Job shop scheduling with dynamic fuzzy selection of dispatching rules, International Journal of Advanced Manufacturing Technology Vol. 16, (10), 759-764.
Wang, F. L., Xu, G., & Wang, M., 2023 An Improved Genetic Algorithm for Constrained Optimization Problems, Ieee Access Vol. 11, 10032-10044.
Wang, X. M., He, H. W., Sun, F. C., & Zhang, J. L., 2015 Application Study on the Dynamic Programming Algorithm for Energy Management of Plug-in Hybrid Electric Vehicles, Energies Vol. 8, (4), 3225-3244.
Xuan, H., & Tang, L. X., 2007 Scheduling a hybrid flowshop with batch production at the last stage, Computers & Operations Research Vol. 34, (9), 2718-2733.
Yang, F., Davari, M., Wei, W. C., Hermans, B., & Leus, R., 2022 Scheduling a single parallel-batching machine with non-identical job sizes and incompatible job families, European Journal of Operational Research Vol. 303, (2), 602-615.
Yavuz, M., & Tufekci, S., 2006 A bounded dynamic programming solution to the batching problem in mixed-model just-in-time manufacturing systems, International Journal of Production Economics Vol. 103, (2), 841-862.