Augmented reality-based intelligent manufacturing system for clothing customization: user immersive interaction and process visualization method
DOI:
https://doi.org/10.4108/eetsis.13960Keywords:
Clothing customization, Intelligent manufacturing, Process visualization, Knowledge graph, Digital twinAbstract
INTRODUCTION: AR-based clothing customization improves user interaction, but multimodal customer requirements remain weakly connected to process planning and shop-floor scheduling.
OBJECTIVES: This study develops a closed-loop method that converts immersive interaction data into executable manufacturing decisions.
METHODS: A KG-DT-MARL framework was developed to encode body scans, speech, gestures, touch inputs, and fabric preferences into a six-element semantic graph, synchronize order, equipment, material, process, and quality states through a digital twin, and perform constraint-guided multi-agent scheduling.
RESULTS: The framework achieved 96.38% requirement-parsing accuracy, 95.74% process-chain generation accuracy, 91.86% resource utilization, and 94.62% on-time delivery under the tested order and disturbance scenarios.
CONCLUSION: The framework provides a closed-loop connection between immersive customization and visualized manufacturing execution.
References
[1] Zhang J, Hu Y Y, Zhang M Y, Hu X Y, Lu L S, Sha S, Xiao J, Jiang X W. Non-contact body measurement for clothing customization based on 2D images: A systematic review [J]. Journal of Textile Research Journal, 2025, 95 (19-20) : 2452-2471. The DOI: 10.1177/00405175251318629.
[2] Lyu Y R, Wang Z H, Ye Q W, Sun Y X, Chao J. Body data-driven garment pattern construction in digital fashion innovations: A review [J]. Journal of Textile Research Journal, 2026, 96 (11-12) : 1299-1335. The DOI: 10.1177/00405175251352800.
[3] Guo Y X, Sun L. Garment pattern generation method based on Diffusion Model and 3D reconstruction technology[J]. Textile Research Journal, 2025, 95 (23-24) : 2866-2881. The DOI: 10.1177/00405175251328296.
[4] Sun Y X, Hao Z H, Wang Z H, Jin J, Ye Q W, Lyu Y R. Deep learning for 3D garment generation: A review [J]. Journal of Textile Research Journal, 2025, 95 (23-24) : 2882-2908. The DOI: 10.1177/00405175251335188.
[5] Yu J J, Shi H, Duan W J. Personalized digital human modeling in the customized clothing industry under Industry 5.0[J]. Textile Research Journal, 2025, 95 (21, 22) : 2679-2690. The DOI: 10.1177/00405175251318243.
[6] Shi H, Yu J J, Duan T. Advances in personalized modelling and virtual display of ethnic clothing for intelligent customization[J]. AUTEX Research Journal, 2024, 24(1):28-41. DOI:10.1515/aut-2023-0040.
[7] Han H S, Park C K. An optimized production assignment algorithm for custom-made garments[J]. Advances in Production Engineering & Management, 2025, 20 (2) : 239-253. The DOI: 10.14743 / apem2025.2.538.
[8] Cui J X, Lou R D, Mantelet F, Segonds F. Integration of additive manufacturing and augmented reality in early design phases: A way to foster remote creativity[J]. International Journal on Interactive Design and Manufacturing, 2024, 18(2):609-625. DOI:10.1007/s12008-023-01629-6.
[9] Ozbek A. Analysis of Turkish consumers' customized clothing purchase intention[J]. Textile and Apparel, 2025 35 (1) : 64-75. The DOI: 10.32710 / tekstilvekonfeksiyon. 1472514.
[10] Xiao Y Z, Zheng S, Shi J C, Du X D, Hong J. Knowledge graph-based manufacturing process planning: A state - of - the - art review [J]. Journal of Manufacturing Systems, 2023, 70 (1) : 417-435. The DOI: 10.1016 / j.j. Msy 2023.08.006.
[11] Kaven L, Huke P, Goppert A Schmitt R H. Multi agent reinforcement learning for online layout planning and scheduling in flexible assembly systems[J]. Journal of Intelligent Manufacturing, 2024, 35(8):3917-3936. DOI:10.1007/s10845-023-02309-8.
[12] Meyers B, Vangheluwe H, Lietaert P, Vanderhulst G, Van Noten J, Schaffers M, Maes D, Gadeyne K. Towards a knowledge graph framework for ad hoc analysis in manufacturing[J]. Journal of Intelligent Manufacturing, 2024, 35(8):3731-3752. DOI:10.1007/s10845-023-02319-6.
[13] Zhang Z F, Qu T, Huang G Q, Zhao K, Zhang K, Li M X, Zhang Y H, Liu L, Zhong H H. Digital twin and blockchain-enabled trusted optimal-state synchronized control approach for distributed smart manufacturing system in social manufacturing[J]. Journal of Manufacturing Systems, 2024, 76 (1) : 385-410. The DOI: 10.1016/j.jmsy.2024.08.004.
[14] Didden J B H C, Dang Q V, Adan I J B F. Enhancing stability and robustness in online machine shop scheduling: A multi-agent system and negotiation-based approach for handling machine downtime in industry 4.0[J]. European Journal of Operational Research, 2024, 316 (2) : 569-583. The DOI: 10.1016/j.ejor.2024.02.006.
[15] Dauzère-Pérès S, Ding J W, Shen L J, Tamssaouet K. The flexible job shop scheduling problem: A review[J]. European Journal of Operational Research, 2024, 314 (2) : 409-432. The DOI: 10.1016/j.ejor.2023.05.017.
[16] Wang L K, Wang Z, Gumma K, Turner A, Ratchev S. Multi-agent cooperative swarm learning for dynamic layout optimisation of reconfigurable robotic assembly cells based on digital twin[J]. Journal of Intelligent Manufacturing, 2025, 36 (5) : 2959-2982. The DOI: 10.1007/s10845-023-02229-7.
[17] Pulikottil T, Estrada-Jimenez L A, Ur Rehman H, Mo F, Nikghadam-Hojjati S, Barata J. Agent-based manufacturing: Review and expert evaluation[J]. The International Journal of Advanced Manufacturing Technology, 2023, 127 (5-6) : 2151-2180. The DOI: 10.1007/s00170-023-11517-8.
[18] Li Y Q, Liu X R, Starly B. Manufacturing service capability prediction with Graph Neural Networks[J]. Journal of Manufacturing Systems, 2024, 74 (1) : 291-301. The DOI: 10.1016/j.jmsy.2024.03.010.
[19] Jing X, Yao X F, Liu M, Zhou J J. Multi-agent reinforcement learning based on graph convolutional network for flexible job shop scheduling[J]. Journal of Intelligent Manufacturing, 2024, 35 (1): 75-93. The DOI: 10.1007/s10845-022-02037-5.
[20] Wang R, Wang G, Sun J, Deng F, Chen J. Flexible job shop scheduling via dual attention network-based reinforcement learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35 (3): 3091-3102. The DOI: 10.1109/TNNLS.2023.3306421.
[21] Pitzalis R F, Giordano A, Di Spigno A, Cowell A, Niculita O, Berselli G. Application of augmented reality-based digital twin approaches: a case study to industrial equipment[J]. The International Journal of Advanced Manufacturing Technology, 2025, 138(7-8):3747-3763. DOI:10.1007/s00170-025-15755-w.
[22] Kim M, Kim S. Development of a dedicated process simulator for the digital twin in apparel manufacturing: a case study[J]. International Journal of Clothing Science and Technology, 2024, 36(4):629-645. DOI:10.1108/IJCST-01-2024-0017.
[23] Wagner S, Gonnermann C, Wegmann M, Listl F, Reinhart G, Weyrich M. From framework to industrial implementation: the digital twin in process planning[J]. Journal of Intelligent Manufacturing, 2024, 35(8):3793-3813. DOI:10.1007/s10845-023-02268-0.
[24] Boroukhian T, Supyen K, Samson J B, Bashyal A, Wicaksono H. Integrating 3D object detection with ontologies for accurate digital twin creation in manufacturing systems[J]. The International Journal of Advanced Manufacturing Technology, 2025, 140(9-10):4679-4711. DOI:10.1007/s00170-025-16548-x.
[25] Wan Y W, Liu Y, Chen Z Y, Chen C, Li X Y, Hu F, Packianather M. Making knowledge graphs work for smart manufacturing: Research topics, applications and prospects. Journal of Manufacturing Systems, 2024, 76:103-132. DOI:10.1016/j.jmsy.2024.07.009.
[26] Kim D B, Bajestani M S, Lee J Y, Shin S J, Kim G Y, Sajadieh S M M, Noh S. Human-in-the-loop in smart manufacturing (H-SM): A review and perspective. Journal of Manufacturing Systems, 2025, 82:178-199. DOI:10.1016/j.jmsy.2025.05.020.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zhihui Li
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.
