This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Krishna Priya R,
R. Dhanasekar,
A. Saravanan,
A Ramaprathap Reddy,
Ramesh Velumayil,
- Head of Research and Consultancy, Faculty of Engineering, University of Technology and Applied Sciences, Musandam, PO. 12, PC 811, Khasab, Musandam, , Oman
- Associate Professor, Department of Electrical and Electronics Engineering Sri Sairam Engineering College, Chennai, Tamil Nadu, India
- Assistant Professor (Sr.G), Department of Automobile Engineering Kongu Engineering College, Tamil Nadu, India
- Assistant Professor, Department of Artificial Intelligence & Machine Learning (Computer Science and Engineering), R.V.R. & JC College of Engineering, Chaudavaram, Guntur, Andhra Pradesh, India
- Associate Professor, Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, India
Abstract
The growing demand for sustainable advanced materials has accelerated the development of recyclable thermoplastic graphene composites for next-generation smart manufacturing systems. The typical central optimization methods have challenges with data privacy, scalability, and poor collaboration between distributed manufacturing sites. By combining material informatics, edge intelligence and distributed artificial intelligence, this study introduces a Federated Learning (FL) framework to design recyclable thermoplastic graphene composites at multiple scales sustainably. The proposed framework allows multiple manufacturing nodes to use them to train their own predictive models without revealing any proprietary process or material information, ensuring confidentiality while enhancing the model’s generalization. These multi-scale material descriptors – such as graphene dispersion, interface bonding, crystallinity, fiber orientation, tensile strength, thermal conductivity, recyclability index, and energy consumption – are integrated in the federated optimization process to ensure structure–property relationships. Smart manufacturing sensors continuously collect production data in real time, and through adaptive model updates, it can improve the stability of the production process, reduce the waste of production materials, and optimize the manufacturing efficiency. The framework also includes subjective sustainability functions, to optimize mechanical performance and recyclability while reducing carbon emissions and production costs. Through simulation-based evaluation, it is shown that the system enables significant improvements in terms of accuracy of predictions, stability of convergence, use of resources and sustainability of the lifecycle with respect to traditional centralized machine learning approaches. This proposed federated intelligence approach offers a safe, scalable and eco-friendly approach to designing high-performance recyclable thermoplastic graphene composites for smart manufacturing in an Industry 5.0 context.
Keywords: Recyclable Thermoplastic Graphene Composites; Federated Learning; Multi-Scale Material Informatics; Sustainable Materials Design; Smart Manufacturing; Industry 5.0.
References
1. Wang, Y., Zhou, Z., Zhang, J., Tang, J., Wu, P., Wang, K., & Zhao, Y. (2020). Properties of Graphene-Thermoplastic Polyurethane Flexible Conductive Film. Coatings, 10(4), 400. https://doi.org/10.3390/coatings10040400 (JOURNAL)
2. Elizalde-Herrera, F. J., Flores-Soto, P. A., Mora-Cortes, L. F., González, F. J., Soria-Arguello, G., Avalos-Belmontes, F., Narro-Céspedes, R. I., & Hoyos, M. (2024). Recent Development of Graphene-Based Composites for Electronics, Energy Storage, and Biomedical Applications: A Review. Journal of Composites Science, 8(11), 481. https://doi.org/10.3390/jcs8110481 (JOURNAL)
3. Periasamy, K., Kandare, E., Das, R., Darouie, M., & Khatibi, A. A. (2023). Interfacial Engineering Methods in Thermoplastic Composites: An Overview. Polymers, 15(2), 415. https://doi.org/10.3390/polym15020415 (JOURNAL)
4. Park, J. H., Dao, T. D., Lee, H.-i., Jeong, H. M., & Kim, B. K. (2014). Properties of Graphene/Shape Memory Thermoplastic Polyurethane Composites Actuating by Various Methods. Materials, 7(3), 1520-1538. https://doi.org/10.3390/ma7031520 (JOURNAL)
5. Kontiza, A., & Kartsonakis, I. A. (2024). Smart Composite Materials with Self-Healing Properties: A Review on Design and Applications. Polymers, 16(15), 2115. https://doi.org/10.3390/polym16152115 (JOURNAL)
6. Wu, Y., An, C., & Guo, Y. (2023). 3D Printed Graphene and Graphene/Polymer Composites for Multifunctional Applications. Materials, 16(16), 5681. https://doi.org/10.3390/ma16165681 (JOURNAL)
7. Francesca Aliberti, Raffaele Longo, Marialuigia Raimondo, Roberto Pantani, Luigi Vertuccio, Liberata Guadagno; Additive manufacturing of polymers and composites for applications in aerospace and aeronautics. Mater. Horiz. 2026; 13 (2): 532–588. https://doi.org/10.1039/d5mh01403d (JOURNAL)
8. Rahman, M. M., Islam, S., Mubasshira, Islam, M. S., Ahammad, R., Islam, M. A., Hasib, M. A., Rahman, M. S., Moshwan, R., Ehsan, M. M., Rabbi, M. S., Moniruzzaman, M., Nazir, M. A., & Liu, W.-D. (2026). Polymer Composites in Additive Manufacturing: Current Technologies, Applications, and Emerging Trends. Polymers, 18(2), 192. https://doi.org/10.3390/polym18020192 (JOURNAL)
9. Malashin, I., Masich, I., Tynchenko, V., Gantimurov, A., Nelyub, V., Borodulin, A., Martysyuk, D., & Galinovsky, A. (2024). Machine Learning in 3D and 4D Printing of Polymer Composites: A Review. Polymers, 16(22), 3125. https://doi.org/10.3390/polym16223125 (JOURNAL)
10. Gyabaah, K. Y., Mahoney, B., Martey, A. K., Yan, C., Mensah, P., & Li, G. (2026). Machine Learning-Assisted Polymer and Polymer Composite Design for Additive Manufacturing. AI Materials, 1(1), 2. https://doi.org/10.3390/aimater1010002 (JOURNAL)
11. Cetiner, B., Sahin Dundar, G., Yusufoglu, Y., & Saner Okan, B. (2023). Sustainable Engineered Design and Scalable Manufacturing of Upcycled Graphene Reinforced Polylactic Acid/Polyurethane Blend Composites Having Shape Memory Behavior. Polymers, 15(5), 1085. https://doi.org/10.3390/polym15051085 (JOURNAL)
12. Pucci, A. (2018). Smart and Modern Thermoplastic Polymer Materials. Polymers, 10(11), 1211. https://doi.org/10.3390/polym10111211 (JOURNAL)
13. Sun, W.; Yu, S.; Tang, M.; Wang, X. Friction and Wear Properties of Graphene /Epoxy Composites. Earth Environ. Sci. 2021, 706, 012038. (JOURNAL)
14. Gaidukevic, J.; Barkauskas, J. Advanced Technologies in Graphene-Based Materials. Crystals 2024, 14, 769. (JOURNAL)
15. Ibrahim, A.; Klopocinska, A.; Horvat, K.; Hamid, Z.A. Graphene-Based Nanocomposites: Synthesis, Mechanical Properties, and Characterizations. Polymers 2021, 13, 2869. (JOURNAL)
16. Liu, F.; Wang, C.; Sui, X.; Riaz, M.A.; Xu, M.; Wei, L.; Chen, Y. Synthesis of graphene materials by electrochemical exfoliation: Recent progress and future potential. Carbon Energy 2019, 1, 173–199. (JOURNAL)
17. Lee, S.J.; Yoon, S.J.; Jeon, I.-Y. Graphene/Polymer Nanocomposites: Preparation, Mechanical Properties, and Application. Polymers 2022, 14, 4733. (JOURNAL)
18. Hofmann, M.; Chiang, W.-Y.; Nguyễn, T.D.; Hsieh, Y.-P. Controlling the properties of graphene produced by electrochemical exfoliation. Nanotechnology 2015, 26, 335607. (JOURNAL)
19. Raimondo, M.; Naddeo, C.; Guadagno, L. Effect of non-covalent functionalization of graphene-based nanoparticles on the local electrical properties of epoxy nanocomposites. IOP Conf. Ser. Mater. Sci. Eng. 2021, 1024, 012004. (JOURNAL)
20. Negri, E.; Fuscaldo, W.; Burghignoli, P.; Galli, A. Reconfigurable THz leaky-wave antennas based on innovative metal–graphene metasurfaces. J. Phys. D Appl. Phys. 2024, 57, 485102. (JOURNAL)
21. Malik, S.; Zhao, Y.; He, Y.; Zhao, X.; Li, H.; Yi, W.; Occhipinti, L.G. Spray-lithography of hybrid graphene perovskite paper-based photodetectors for sustainable electronics. Nanotechnology 2024, 35, 325301. (JOURNAL)
22. Zhao, J.; Ji, P.; Li, Y.; Li, R.; Zhang, K.; Tian, H.; Yu, K.; Bian, B.; Hao, L.; Xiao, X.; et al. Ultrahigh-mobility semiconducting epitaxial graphene on silicon carbide. Nature 2024, 625, 60. (JOURNAL)
23. Ramalingam, G.; Perumal, N.; Priya, A.K.; Rajendran, S. A Review of Graphene-Based Semiconductors for Photocatalytic Degradation of Pollutants in Wastewater. Chemosphere 2022, 300, 134391. (JOURNAL)
24. Dai, J.; Cheng, C.; Li, H.; Cui, T.; Xiao, K.; Ning, J.; Liu, J.; Wang, C. Synthesis of nickel silicate/reduced graphene oxide composite for long-life lithium-ion storage. Mater. Res. Express 2023, 10, 035503. (JOURNAL)
25. Wu, Z.-Y.; Wu, C.-Y.; Duh, J.-G. Facile synthesis of boron-doped graphene-silicon conductive network composite from recycling silicon for lithium-ion batteries anodes materials. Mater. Lett. 2021, 296, 129875. (JOURNAL)
26. Chen, B.; Wang, D.; Zhang, B.; Zhong, X.; Liu, Y.; Sheng, I.; Zhang, Q.; Zou, X.; Zhou, G.; Cheng, H.-M. Engineering the Active Sites of Graphene Catalyst: From CO2 Activation to Activate LiCO2 Batteries. ACS Nano 2021, 15, 9841. (JOURNAL)
27. Oktay, B.; Erarslan, A.; Üstündağ, C.B.; Özerol, E.A. Preparation and characterization of graphene oxide quantum dots/silver nanoparticles and investigation of their antibacterial effects. Mater. Res. Express 2024, 11, 015603. (JOURNAL)
28. Wekalao, J.; Patel, S.K.; Anushkannan, N.; Alsalman, O.; Surve, J.; Parmar, J. Design of ring and cross shaped graphene metasurface sensor for efficient detection of malaria and 2 bit encodng applications. Diam. Relat. Mater. 2023, 139, 110401. (JOURNAL)
Journal of Polymer & Composites
| Volume | 14 | |
| 04 | ||
| Received | 04/08/2026 | |
| Accepted | 26/08/2026 | |
| Published | 10/09/2026 | |
| Publication Time | 37 Days |