Digital Twin and Constraint-Guided Generative Decision Support for Human-Machine Collaborative Manufacturing under Industry 5.0
DOI:
https://doi.org/10.4108/eetsis.13777Keywords:
industry 5.0, human-machine collaboration, digital twin, generative artificial intelligence, adaptive production decision supportAbstract
INTRODUCTION: In Industry 5.0 manufacturing systems, adaptive decision support is required to handle demand fluctuations, machine degradation, and operational feasibility constraints under human supervision. However, existing digital twin and data-driven approaches remain primarily focused on monitoring or forecasting, with limited integration into decision-oriented production control and feedback adaptation.
OBJECTIVES: This study aims to develop a human-in-the-loop adaptive production decision-support framework that transforms external demand signals into feasible, risk-aware, and reviewable production actions by integrating demand-production state fusion, digital twin-based constraints, structured generative decision decoding, and feedback-driven updates.
METHODS: A constrained decision-making system is constructed using Online Retail II and AI4I 2020 datasets. A unified state representation is learned by fusing demand indicators with manufacturing digital twin variables. A constraint-guided policy decoder is designed to generate discrete production actions under feasibility constraints rather than performing demand forecasting. Human feedback is encoded into subsequent decision states to enable iterative adaptation. The model is trained via a unified optimization objective balancing demand alignment, risk control, and explanation consistency.
RESULTS: Experimental results on two datasets show that the proposed framework achieves improved demand-production alignment while consistently reducing manufacturing risk exposure and human override rates compared with forecasting-based and decision-oriented baselines.
CONCLUSION: The proposed framework demonstrates that integrating digital twin constraints, constrained generative decision-making, and human feedback enables a shift from demand prediction to feasibility-aware production decision optimization, improving safety, interpretability, and human acceptability in Industry 5.0 manufacturing systems.
References
[1] Ghobakhloo M, Mahdiraji HA, Iranmanesh M, Jafari-Sadeghi V. From Industry 4.0 digital manufacturing to Industry 5.0 digital society: A roadmap toward human-centric, sustainable, and resilient production. Information Systems Frontiers. 2024:1-33. https://doi.org/10.1007/s10796-024-10476-z
[2] Martini B, Bellisario D, Coletti P. Human-centered and sustainable artificial intelligence in industry 5.0: Challenges and perspectives. Sustainability. 2024;16(13):5448. https://doi.org/10.3390/su16135448
[3] Cai Y, He Y, Shi R, Feng T, Li J. Resilience-oriented approach of dynamic production and maintenance scheduling optimisation considering operational uncertainty. International Journal of Production Research. 2024;62(21):7812-7835. https://doi.org/10.1080/00207543.2024.2329324
[4] Figueroa AJ, Poler R, Andres B. Adaptive production rescheduling system for managing unforeseen disruptions. Mathematics. 2024;12(22):3478. https://doi.org/10.3390/math12223478
[5] Zhang C, Juraschek M, Herrmann C. Deep reinforcement learning-based dynamic scheduling for resilient and sustainable manufacturing: A systematic review. Journal of Manufacturing Systems. 2024;77:962-989. https://doi.org/10.1016/j.jmsy.2024.10.026
[6] Cai Y, He Y, Shi R, Liao R, Cao H, Guo H, Lu H. Resilience-oriented adaptive predictive maintenance optimization for continuous process manufacturing systems considering mission profile variation. Computers & Industrial Engineering. 2024;197:110532. https://doi.org/10.1016/j.cie.2024.110532
[7] Babazadeh R, Taraghi Nazloo H, Kamran MA. A hybrid ANN-MILP model for agile recovery production planning for PPE products under sharp demands. International Journal of Production Research. 2025;63(2):758-778. https://doi.org/10.1080/00207543.2024.2313100
[8] Lee H. Fault-Resilient Manufacturing Scheduling with Deep Learning and Constraint Solvers. Applied Sciences. 2025;15(4):1771. https://doi.org/10.3390/app15041771
[9] Douaioui K, Oucheikh R, Benmoussa O, Mabrouki C. Machine learning and deep learning models for demand forecasting in supply chain management: A critical review. Applied System Innovation. 2024;7(5):93. https://doi.org/10.3390/asi7050093
[10] Ahangar MN, Farhat ZA, Sivanathan A. AI trustworthiness in manufacturing: challenges, toolkits, and the path to industry 5.0. Sensors. 2025;25(14):4357. https://doi.org/10.3390/s25144357
[11] Bussieweke F, Mula J, Campuzano-Bolarin F. Optimisation of recovery policies in the era of supply chain disruptions: a system dynamics and reinforcement learning approach. International Journal of Production Research. 2025;63(5):1649-1673. https://doi.org/10.1080/00207543.2024.2383293
[12] Elyasi M, Altan B, Ekici A, Özener ÖÖ, Yanıkoğlu İ, Dolgui A. Production planning with flexible manufacturing systems under demand uncertainty. International Journal of Production Research. 2024;62(1-2):157-170. https://doi.org/10.1080/00207543.2023.2288722
[13] Shao Z, Li W, Tan Y, Otto K. A systematic energy-aware scheduling framework for manufacturing factories integrated with renewables. International Journal of Production Research. 2024;62(21):7644-7659. https://doi.org/10.1080/00207543.2024.2323067
[14] Chowdhury AR, Paul R, Rozony FZ. A systematic review of demand forecasting models for retail e-commerce enhancing accuracy in inventory and delivery planning. International Journal of Scientific Interdisciplinary Research. 2025;6(1):01-27. https://doi.org/10.63125/mbbfw637
[15] Holguin Jimenez S, Trabelsi W, Sauvey C. Multi-objective production rescheduling: A systematic literature review. Mathematics. 2024;12(20):3176. https://doi.org/10.3390/math12203176
[16] Xu H, Zheng J, Huang L, Tao J, Zhang C. Solving dynamic multi-objective flexible job shop scheduling problems using a dual-level integrated deep Q-network approach. Processes. 2025;13(2):386. https://doi.org/10.3390/pr13020386
[17] Hu S, Li C, Li B, Yang M, Wang X, Gao T, et al. Digital twins enabling intelligent manufacturing: from methodology to application. Intelligent and Sustainable Manufacturing. 2024;1(1):10007. https://doi.org/10.35534/ism.2024.10007
[18] Ouahabi N, Chebak A, Kamach O, Laayati O, Zegrari M. Leveraging digital twin into dynamic production scheduling: A review. Robotics and Computer-Integrated Manufacturing. 2024;89:102778. https://doi.org/10.1016/j.rcim.2024.102778
[19] Grznár P, Papánek L, Marčan M, Krajčovič M, Antoniuk I, Mozol Š, Mozolová L. Enhancing production efficiency through digital twin simulation scheduling. Applied Sciences. 2025;15(7):3637. https://doi.org/10.3390/app15073637
[20] Webb L, Tokhi OM, Alkan B. State of the art and future directions of digital twin-enabled smart assembly automation in discrete manufacturing industries. International Journal of Computer Integrated Manufacturing. 2025;38(8):1126-1160. https://doi.org/10.1080/0951192x.2024.2387775
[21] Ghobakhloo M, Fathi M, Iranmanesh M, Vilkas M, Grybauskas A, Amran A. Generative artificial intelligence in manufacturing: opportunities for actualizing Industry 5.0 sustainability goals. Journal of Manufacturing Technology Management. 2024;35(9):94-121. https://doi.org/10.1108/jmtm-12-2023-0530
[22] Filz MA, Thiede S. Generative AI in manufacturing systems: Reference framework and use cases. Procedia CIRP. 2024;130:238-243. https://doi.org/10.1016/j.procir.2024.10.082
[23] Li Y, Zhao H, Jiang H, Pan Y, Liu Z, Wu Z, et al. Large language models for manufacturing. Journal of Manufacturing Systems. 2026;86:516-545. https://doi.org/10.1016/j.jmsy.2026.02.014
[24] Jackson I, Ivanov D, Dolgui A, Namdar J. Generative artificial intelligence in supply chain and operations management: a capability-based framework for analysis and implementation. International Journal of Production Research. 2024;62(17):6120-6145. https://doi.org/10.1080/00207543.2024.2309309
[25] Konstantinou C, Antonarakos D, Angelakis P, Gkournelos C, Michalos G, Makris S. Leveraging Generative AI Prompt Programming for Human-Robot Collaborative Assembly. Procedia CIRP. 2024;128:621-626. https://doi.org/10.1016/j.procir.2024.03.040
[26] Handler A, Larsen KR, Hackathorn R. Large language models present new questions for decision support. International Journal of Information Management. 2024;79:102811. https://doi.org/10.1016/j.ijinfomgt.2024.102811
[27] Lin Z, Guan S, Zhang W, Zhang H, Li Y, Zhang H. Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models. Artificial Intelligence Review. 2024;57(9):1.
[28] Geng S, Döner B, Wendler C, Josifoski M, West R. Sketch-guided constrained decoding for boosting blackbox large language models without logit access. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2024 Aug. p. 234-245.
[29] Lee JY. Introduction of human-in-the-loop in smart manufacturing (H-SM). International Journal of Precision Engineering and Manufacturing-Smart Technology. 2024;2(2):209-214. https://doi.org/10.57062/ijpem-st.2024.00115
[30] Passalacqua M, Pellerin R, Magnani F, Doyon-Poulin P, Del-Aguila L, Boasen J, Léger PM. Human-centred AI in industry 5.0: a systematic review. International Journal of Production Research. 2025;63(7):2638-2669. https://doi.org/10.1080/00207543.2024.2406021
[31] Kim DB, Bajestani MS, Lee JY, Shin SJ, Kim GY, Sajadieh SMM, Noh S. Human-in-the-loop in smart manufacturing (H-SM): A review and perspective. Journal of Manufacturing Systems. 2025;82:178-199. https://doi.org/10.1016/j.jmsy.2025.05.020
[32] Chen D. Online Retail II [Dataset]. UCI Machine Learning Repository; 2012. https://doi.org/10.24432/C5CG6D
[33] Matzka S. Explainable artificial intelligence for predictive maintenance applications. In: 2020 Third International Conference on Artificial Intelligence for Industries (AI4I). IEEE; 2020 Sep. p. 69-74. https://doi.org/10.1109/ai4i49448.2020.00023
[34] Makridakis S, Hibon M. ARMA models and the Box-Jenkins methodology. Journal of Forecasting. 1997;16(3):147-163. https://doi.org/10.1002/(SICI)1099-131X(199705)16:3<147::AID-FOR653>3.0.CO;2-X
[35] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
[36] Zhang Y, Wu R, Dascalu SM, Harris Jr FC. Sparse transformer with local and seasonal adaptation for multivariate time series forecasting. Scientific Reports. 2024;14(1):15909. https://doi.org/10.1038/s41598-024-66886-1
[37] Mejía S, Aguilar J. A demand forecasting system of product categories defined by their time series using a hybrid approach of ensemble learning with feature engineering. Computing. 2024;106(12):3945-3965. https://doi.org/10.1007/s00607-024-01320-y
[38] Graham RL, Lawler EL, Lenstra JK, Kan AR. Optimization and approximation in deterministic sequencing and scheduling: a survey. Annals of Discrete Mathematics. 1979;5:287-326. https://doi.org/10.1016/s0167-5060(08)70356-x
[39] Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529-533. https://doi.org/10.1038/nature14236
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Chen Qian
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
