由於建置成本的增加以及組織的人力與資本的限制，透過維護活動與管理以維持設備運作與產能的改善，對所有產業而言愈來愈重要。現今零工式生產中常見的問題是如何在多種彼此衝突的目標與資源之間取得平衡。本研究旨在開發一個基於模擬過程之多目標派遣規則，應用於自動化機台生產線維護員工的調度，達到從維護人員多技能資源 (multi-skilled resource) 不完全兼容的特性中，並同時確保生產線的穩定運行下，優化所需之維護人選數量以及可涵蓋的產線維護範圍與保留之多技能資源類型，取得最適配的維修人員名單。本研究利用多目標非凌駕演算法 NSGAIII，透過多個目標式諸如使用之人力資源數量、多技能資源涵蓋範圍及多技能資源的分數大小，先計算出多目標解。再根據取得所需使用之初始解，結合所定義之調度規則，並藉由模擬過程進行驗證，確認初始解是否滿足歷史維護資料需求。透過模擬過程中所獲得之各種事件回饋特徵和相關狀態作為參數，動態更新調度所需之資源需求，並對維修人員多技能資源所需大小和配置等指標進行調配。藉由模擬過程不斷進行裁定與確認，使其結果最終在實務上是可行的，並驗證所得之結果。本研究將透過執行上述提出之框架，利用一個實際的資料進行框架的驗證，在不同生產專案所建構之模擬情境下，選擇不同員工，並根據員工的歷史指派資料去計算每一個員工的使用率以及取得其他觀測結果。在與產線現存方法進行比較後，發現所提出之框架確實能夠改善製造業於流水生產線上，在多能員工人力資源的調配上得到優化。

Due to the increase in construction costs and the constraints of the human, maintaining the improvement of equipment operation and production capacity through maintenance and management has become increasingly important for all industries. The purpose of this research is to develop a multi-objective dispatch rule based on a simulation process, which can be applied to the scheduling of maintenance staff in automated machine production lines. In addition, how to ensure that the production line is stable while optimizing the number of maintenance workers, production line maintenance coverage, and the resource type to obtain a suitable maintenance personnel list is a challenge problem. This research used a multi-objective non-dominated algorithm to obtain the multi-objective solution for objectives such as the number of human resources used, the coverage of multi-skilled resources, and the score of multi-skilled resources. Then, the obtained solutions combined with the defined dispatch rules was used to verify whether the initial solution meets the requirements of historical data through the developed simulation. Results and the related states obtained from the simulation were used as the inputs of the model to adjust resources such as the number of maintenance personnel and multi-skilled maintenance required for each service are dynamically updated. Through the continuous adjustment and confirmation of the simulation process, the converged results can be considered as feasible solutions in practice. This research utilized real-world data to verify the proposed framework. After comparing with the existing methods, the results showed that the proposed framework can improve the production line of the manufacturing industry and optimize the allocation of human resources for multi-skilled employees.

[1] X. Xu, Y. Chen, Y. Yuan, T. Huang, X. Zhang, and L. Qi, "Blockchain-based cloudlet management for multimedia workflow in mobile cloud computing," Multimedia Tools Applications, vol. 79, no. 15, pp. 9819-9844, 2020.
[2] O. M. Sedeh, B. Ostadi, and F. J. J. o. B. E. Zagia, "A novel hybrid GA-PSO optimization technique for multi-location facility maintenance scheduling problem," vol. 40, p. 102348, 2021.
[3] J.-H. Lee, Y. Kim, Y. B. Kim, B.-H. Kim, G.-H. Jung, and H.-J. Kim, "A Sequential Search Method of Dispatching Rules for Scheduling of LCD Manufacturing Systems," IEEE Transactions on Semiconductor Manufacturing, vol. 33, no. 4, pp. 496-503, 2020.
[4] S. Lee, "Role of parallelism in ambulance dispatching," IEEE Transactions on Systems, Man, Cybernetics: Systems, vol. 44, no. 8, pp. 1113-1122, 2014.
[5] M. Yu, S. Wang, and Y. Cai, "A dispatching method for trucks at container terminal by using fuzzy-cnp concept," in 2010 International Conference on Logistics Engineering and Intelligent Transportation Systems, 2010, pp. 1-4: IEEE.
[6] A. Verma et al., "Automated optimal dispatching of service requests," in 2011 Annual SRII Global Conference, 2011, pp. 426-429: IEEE.
[7] O. Rose, S. Chick, P. Sánchez, D. Ferrin, and D. Morrice, "Accelerating products under due-date oriented dispatching rules in semiconductor manufacturing," in Winter Simulation Conference, 2003, vol. 2, pp. 1346-1350.
[8] K. Saito and S. Arima, "A simulation study on periodical priority dispatching of WIP for product-mix fabrication," in 13th Annual IEEE/SEMI Advanced Semiconductor Manufacturing Conference. Advancing the Science and Technology of Semiconductor Manufacturing. ASMC 2002 (Cat. No. 02CH37259), 2002, pp. 33-37: IEEE.
[9] S. Nguyen, M. Zhang, M. Johnston, and K. C. Tan, "Genetic programming for job shop scheduling," in Evolutionary and Swarm Intelligence Algorithms: Springer, 2019, pp. 143-167.
[10] C. Akjiratikarl, P. Yenradee, and P. R. Drake, "PSO-based algorithm for home care worker scheduling in the UK," Computers Industrial Engineering, vol. 53, no. 4, pp. 559-583, 2007.
[11] T. Bhaskar, M. N. Pal, and A. K. Pal, "A heuristic method for RCPSP with fuzzy activity times," European Journal of Operational Research, vol. 208, no. 1, pp. 57-66, 2011.
[12] B. F. Almeida, I. Correia, and F. Saldanha-da-Gama, "Priority-based heuristics for the multi-skill resource constrained project scheduling problem," Expert Systems with Applications, vol. 57, pp. 91-103, 2016.
[13] B. Afshar-Nadjafi, "Multi-skilling in scheduling problems: A review on models, methods and applications," Computers Industrial Engineering, vol. 151, p. 107004, 2021.
[14] R. Liu, M. Liu, F. Chu, F. Zheng, and C. Chu, "Eco-friendly multi-skilled worker assignment and assembly line balancing problem," Computers Industrial Engineering, vol. 151, p. 106944, 2021.
[15] L. Wang and X.-l. Zheng, "A knowledge-guided multi-objective fruit fly optimization algorithm for the multi-skill resource constrained project scheduling problem," Swarm and Evolutionary Computation, vol. 38, pp. 54-63, 2018.
[16] P. B. Myszkowski, M. E. Skowroński, and K. Sikora, "A new benchmark dataset for multi-skill resource-constrained project scheduling problem," in 2015 federated conference on computer science and information systems (FedCSIS), 2015, pp. 129-138: IEEE.
[17] J. Lin, L. Zhu, and K. Gao, "A genetic programming hyper-heuristic approach for the multi-skill resource constrained project scheduling problem," Expert Systems with Applications, vol. 140, p. 112915, 2020.
[18] P. B. Myszkowski, M. E. Skowroński, Ł. P. Olech, and K. Oślizło, "Hybrid ant colony optimization in solving multi-skill resource-constrained project scheduling problem," Soft Computing, vol. 19, no. 12, pp. 3599-3619, 2015.
[19] P. B. Myszkowski and J. J. Siemieński, "GRASP applied to multi–skill resource–constrained project scheduling problem," in International Conference on Computational Collective Intelligence, 2016, pp. 402-411: Springer.
[20] P. B. Myszkowski, Ł. P. Olech, M. Laszczyk, and M. E. Skowroński, "Hybrid differential evolution and greedy algorithm (DEGR) for solving multi-skill resource-constrained project scheduling problem," Applied Soft Computing, vol. 62, pp. 1-14, 2018.
[21] C. Pessan, O. Bellenguez-Morineau, and E. Néron, "Multi-skill project scheduling problem and total productive maintenance," Proceedings of MISTA (2007), pp. 608-610, 2007.
[22] M. Fırat and C. A. Hurkens, "An improved MIP-based approach for a multi-skill workforce scheduling problem," Journal of Scheduling, vol. 15, no. 3, pp. 363-380, 2012.
[23] H. H. Turan, F. Kosanoglu, and M. Atmis, "A multi-skilled workforce optimisation in maintenance logistics networks by multi-thread simulated annealing algorithms," International Journal of Production Research, vol. 59, no. 9, pp. 2624-2646, 2021.
[24] X. Wen, X. Lian, Y. Qian, Y. Zhang, H. Wang, and H. Li, "Dynamic scheduling method for integrated process planning and scheduling problem with machine fault," Robotics Computer-Integrated Manufacturing, vol. 77, p. 102334, 2022.
[25] T. Coito et al., "Integration of industrial IoT architectures for dynamic scheduling," Computers Industrial Engineering, vol. 171, p. 108387, 2022.
[26] J. Mohan, K. Lanka, and A. N. Rao, "A review of dynamic job shop scheduling techniques," Procedia Manufacturing, vol. 30, pp. 34-39, 2019.
[27] L. Xue, P. Wang, H. Cheng, P. Zeng, and H. Yu, "Event-driven dynamic job shop scheduling execution based on improved genetic algorithm and ontology," in 2017 Chinese Automation Congress (CAC), 2017, pp. 6430-6435: IEEE.
[28] M. A. Klapp, A. L. Erera, and A. Toriello, "The dynamic dispatch waves problem for same-day delivery," European Journal of Operational Research, vol. 271, no. 2, pp. 519-534, 2018.
[29] X.-N. Shen and X. Yao, "Mathematical modeling and multi-objective evolutionary algorithms applied to dynamic flexible job shop scheduling problems," Information Sciences, vol. 298, pp. 198-224, 2015.
[30] Y. Tian, X. Zhang, R. Cheng, and Y. Jin, "A multi-objective evolutionary algorithm based on an enhanced inverted generational distance metric," in 2016 IEEE congress on evolutionary computation (CEC), 2016, pp. 5222-5229: IEEE.
[31] L. Imene, S. Sihem, K. Okba, and B. Mohamed, "A third generation genetic algorithm NSGAIII for task scheduling in cloud computing," Journal of King Saud University-Computer Information Sciences, 2022.
[32] F. Zhang, Y. Mei, and M. Zhang, "Evolving dispatching rules for multi-objective dynamic flexible job shop scheduling via genetic programming hyper-heuristics," in 2019 IEEE Congress on Evolutionary Computation (CEC), 2019, pp. 1366-1373: IEEE.
[33] M. Laszczyk and P. B. Myszkowski, "Improved selection in evolutionary multi–objective optimization of multi–skill resource–constrained project scheduling problem," Information Sciences, vol. 481, pp. 412-431, 2019.
[34] K. Deb and H. Jain, "An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints12313213," IEEE transactions on evolutionary computation, vol. 18, no. 4, pp. 577-601, 2013.
[35] I. Das and J. E. Dennis, "Normal-boundary intersection: A new method for generating the Pareto surface in nonlinear multicriteria optimization problems," SIAM journal on optimization, vol. 8, no. 3, pp. 631-657, 1998.