System Engineering and Productivity

System Engineering and Productivity

Reinforcement Learning Framework for Workload Distribution and Scheduling in Multi-Model Production Lines

Articles in Press

Document Type : Research Paper

Author
Fahimeh Tanhaie
Assistant Professor., Department of Industrial Engineering, Faculty of Basic Science and Engineering, Kosar University of Bojnord , Bojnord, Iran
10.22034/sep.2026.2077232.1426
Abstract
This study introduces an innovative approach to addressing the dual challenges of line balancing and sequencing in mixed-model assembly lines through the integration of artificial intelligence. By combining deep neural networks (DNNs) and reinforcement learning (RL), the proposed framework simultaneously optimizes workstation load distribution and task ordering. Historical production data—including task processing times, the total number of workstations, and inter-task dependencies—were collected and structured into predictive models. A Deep Q-Network (DQN)-based RL agent was developed to dynamically assign tasks to stations and determine their execution sequence in real time, aiming to minimize makespan and maximize overall line efficiency. In parallel, DNNs were employed to forecast task processing durations and evaluate the feasibility of relocating tasks across stations. Numerical experiments using real-world production data demonstrate that the proposed method significantly reduces idle time, decreases task waiting periods, and streamlines workflow continuity. Furthermore, benchmarking against conventional optimization techniques—such as Genetic Algorithms and Simulated Annealing—highlights the advantages of this machine learning–driven strategy, particularly in achieving near-optimal solutions more rapidly and with greater adaptability.

Highlights

  • Integrating deep learning and reinforcement learning to simultaneously solve balancing and sequencing problems in mixed-model assembly lines.
  • Presenting a deep Q-network (DQN)-based model that dynamically and in real-time allocates tasks to workstations.
  • Utilizing deep neural networks (DNNs) to accurately predict task processing times and facilitate intelligent task transfers between stations.

Keywords
Scheduling
Workload Distribution
Deep Neural Networks (DNN)
Reinforcement Learning (RL)
Line Balancing
Subjects

Copyright © Fahimeh Tanhaie

 

License

This article is released under the Creative Commons Attribution (CC BY 4.0) license. Anyone is free to copy, share, translate, and adapt this article for any purpose, whether commercial or non-commercial, as long as proper citation is given to the authors and original publication.

Abolghasemian, M., Kheiri, A. O., & Saberifard, N. (2024). Prioritizing factors affecting the flexibility and performance of the digital supply chain system in the Iranian food industry. System Engineering and Productivity, 4(1), 41-57. https://doi.org/10.22034/msb.2024.2025240.1194
Akpınar, S., & Bayhan, G. M. (2011). A hybrid genetic algorithm for mixed model assembly line balancing problem with parallel workstations and zoning constraints. Engineering Applications of Artificial Intelligence, 24(3), 449–457. https://doi.org/10.1016/j.engappai.2010.08.006
Ayough, A., & Khorshidvand, B. (2023). Robust optimization for the integrated worker-cell assignment and sequencing problem in a lean U-shaped assembly line. Computers & Industrial Engineering, 178, 109139. https://doi.org/10.1016/j.cie.2023.109139
Boysen, N., Fliedner, M., & Scholl, A. (2009). Sequencing mixed-model assembly lines: Survey, classification and model critique. European journal of operational research, 192(2), 349-373. https://doi.org/10.1016/j.ejor.2007.09.013
Çil, Z. A., & Kizilay, D. (2020). Constraint programming model for multi-manned assembly line balancing problem.  Computers & Operations Research, 124, 105069. https://doi.org/10.1016/j.cor.2020.105069
Defersha, F. M., & Mohebalizadehgashti, F. (2018). Simultaneous balancing, sequencing, and workstation planning for a mixed model manual assembly line using hybrid genetic algorithm. Computers & industrial engineering, 119, 370-387. https://doi.org/10.1016/j.cie.2018.04.014
Gholamian, S. A. (2025). Evaluation and selection of sustainable suppliers by providing a decision support system based on a new data envelopment analysis model and cumulative star utility. System Engineering and Productivity, 4(1), 1-13. https://doi.org/10.22034/msb.2024.2025845.1198
Guo, G., & Ryan, S. M. (2022). Sequencing mixed-model assembly lines with risk-averse stochastic mixed-integer programming.  International Journal of Production Research, 60 (12), 3774–3791. https://doi.org/10.1080/00207543.2021.1931978
Janardhanan, M. N., Li, Z., Bocewicz, G., Banaszak, Z., & Nielsen, P. (2019). Metaheuristic algorithms for balancing robotic assembly lines with sequence-dependent robot setup times. Applied Mathematical Modelling, 65, 256-270. https://doi.org/10.1016/j.apm.2018.08.016
Kashanian Monfared, N., Safaie, N., & Hosseininezhad, S. J. (2025). A decision-making model for the problem of designing the layout of medical centers considering uncertainty. System Engineering and Productivity, 5(2), 97-118. https://doi.org/10.22034/sep.2025.2049327.1252
Kucukkoc, I., Buyukozkan, K., Satoglu, S. I., & Zhang, D. Z. (2019). A mathematical model and artificial bee colony algorithm for the lexicographic bottleneck mixed-model assembly line balancing problem.  Journal of Intelligent Manufacturing, 30, 2913–2925. https://doi.org/10.1007/s10845-015-1150-5
Li, Y., Liu, D., & Kucukkoc, I. (2023). Mixed-model assembly line balancing problem considering learning effect and uncertain demand.  Journal of Computational and Applied Mathematics, 422, 114823. https://doi.org/10.1016/j.cam.2022.114823
Montazeri Najafabadi, R., & Shams, M. (2026). Developing a deep learning-based power outage predictive model to improve resilience of power systems. System Engineering and Productivity.  https://doi.org/10.22034/sep.2026.2076246.1420
Razali, M. M., Kamarudin, N. H., Ab. Rashid, M. F. F., & Mohd Rose, A. N. (2019). Recent trend in mixed-model assembly line balancing optimization using soft computing approaches.  Engineering Computations, 36 (2), 622–645. https://doi.org/10.1108/EC-05-2018-0205
Saif, U., Guan, Z., Zhang, L., Zhang, F., Wang, B., & Mirza, J. (2019). Multi-objective artificial bee colony algorithm for order oriented simultaneous sequencing and balancing of multi-mixed model assembly line.  Journal of Intelligent Manufacturing, 30, 1195–1220. https://doi.org/10.1007/s10845-017-1316-4
Taha, R. B., & Zamzam, N. Z. (2022). A genetic algorithm for multi-manned multi-position assembly line under technological constraint.  Port-Said Engineering Research Journal, 26 (3), 134–145. https://doi.org/10.21608/pserj.2022.74000.1107
Tang, Q., Liang, Y., Zhang, L., Floudas, C. A., & Cao, X. (2016). Balancing mixed-model assembly lines with sequence-dependent tasks via hybrid genetic algorithm.  Journal of Global Optimization, 65 (1), 83–107. https://doi.org/10.1007/s10898-015-0316-1
Tanhaie, F. (2024). Applying a multi-objective particle swarm optimization algorithm for sequencing and balancing a mixed-model assembly line problem with setup times between tasks.  Journal of Applied Research on Industrial Engineering, 11 (3), 350–368. https://doi.org/10.22105/jarie.2024.394265.1545
Zhang, X., Fathollahi-Fard, A. M., Tian, G., Yaseen, Z. M., Pham, D. T., Zhao, Q., & Wu, J. (2024). Human–robot collaboration in mixed-flow assembly line balancing under uncertainty: An efficient discrete bees’ algorithm.  Journal of Industrial Information Integration, 41, 100676. https://doi.org/10.1016/j.jii.2024.100676
Zhang, Z., Tang, Q., Chica, M., & Li, Z. (2023). Reinforcement learning-based multiobjective evolutionary algorithm for mixed-model multimanned assembly line balancing under uncertain demand. IEEE Transactions on Cybernetics, 54(5), 2914-2927. https://doi.org/10.1109/TCYB.2022.3229666
 
System Engineering and Productivity

Articles in Press, Accepted Manuscript
Available Online from 07 February 2026

  • Receive Date 09 November 2025
  • Revise Date 02 January 2026
  • Accept Date 31 January 2026
  • First Publish Date 07 February 2026
  • Publish Date 07 February 2026