STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Review Article

Machine Learning Optimization for VARTM Carbon Polymer Laminates

  1. M. Rajkumar Department of Information Technology, Sri Krishna College of Engineering and Technology, Coimbatore
  2. Mridula Mavuri Department of Computer science, Louisiana state university, Shreveport
  3. K. Sithananthan Department of Mechanical engineering Achariya college of engineering technology
  4. M. Bala Theja Department of Mechanical Engineering, Santhiram Engineering College (Autonomous), Nandyal
  5. Ankush B. Khansole Department of Mechanical Engineering, CSMSS Chhatrapati SHAHU college of engineering
  6. Gokul Pran S. Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai

Abstract

Vacuum-assisted resin transfer moulding (VARTM) is a key low-cost, out-of-autoclave process for manufacturing large-scale carbon-fibre reinforced polymer (CFRP) laminates crucial to aerospace wings, wind-turbine blades, marine hulls, and automotive structures. Unpredictable resin flow often leads to voids, dry spots, and race-tracking defects, resulting in 27.9% scrap rates and lengthy, costly trial-and-error design cycles. Although surrogate models provide rapid impregnation predictions for simple flat-plate geometries, vision-based monitoring is limited to idealized test media without closed-loop integration, and conventional optimization techniques are computationally prohibitive for high-dimensional flow-media networks on realistic aerospace parts, no unified solution yet achieves rapid impregnation prediction, real-time void tracking, and instant optimization. This work proposes a novel hybrid machine-learning framework that integrates a surrogate neural network for thickness-direction impregnation forecasting, a U-Net-based vision system for non-intrusive real-time flow-front and void monitoring, and a proximal policy optimization agent for instant optimal flow-media network generation on new geometries. Trained offline on the VARTM-ML-Opt-2026 dataset from high-fidelity control-volume finite-element simulations and validated on three-dimensionally printed porous media, the closed-loop pipeline achieves 35% fill-time reduction with complete preform saturation and zero trap off, reduces computational cost to 0.74% of full three-dimensional simulations, limits impregnation errors to below 6.5%, and keeps void segmentation errors under 14%. The end-to-end framework offers a scalable, data-driven pathway to defect-free VARTM manufacturing.

Keywords

References (37)

  1. Matsuzaki R, Morikawa M, Oikawa Y, Ushiyama K. Predicting thickness impregnation in a VaRTM resin flow simulation using machine learning. Composites Part C: Open Access. 2021;5:100158. doi:10.1016/j.jcomc.2021.100158
  2. Szarski M, Chauhan S. Instant flow distribution network optimization in liquid composite molding using deep reinforcement learning. Journal of Intelligent Manufacturing. 2022;34(1):197-218. doi:10.1007/s10845-022-01990-5
  3. Wu D, Larsson R, Blinzler B. A preform deformation and resin flow coupled model including the cure kinetics and chemo-rheology for the VARTM process. International Journal of Material Forming. 2020;14(3):421-434. doi:10.1007/s12289-020-01570-z
  4. Jeong JM, Eum S, On SY, Kageyama K, Murayama H, Uzawa K, et al. In-situ resin flow monitoring in VaRTM process by using optical frequency domain reflectometry and long-gauge FBG sensors. Composite Structures. 2022;282:115034. doi:10.1016/j.compstruct.2021.115034
  5. Lepore MA, Ferrante L, Sanguigno L, Maligno AR. A non‐crimp fabric mechanical characterization for the production of aerospace components. Material Design & Processing Communications. 2021;3(5). doi:10.1002/mdp2.222
  6. Hindersmann, “Experimental investigation of a method to avoid channel marks during vacuum infusion,” J. Compos. Mater., vol. 54, no. 16, pp. 2147–2158, Jul. 2020, doi: 10.1177/ 0021998319889120.
  7. Musa SMA, Dzulkifli MH, Azmi AI, Ibrahim SA. Embedded and Surface-Mounted Fiber Bragg Grating as a Multiparameter Sensor in Fiber-Reinforced Polymer Composite Materials: A Review. IEEE Access. 2023;11:86611-86644. doi:10.1109/access.2023.3304679
  8. Lee D, Lee IY, Park YB. Real-time process monitoring and prediction of flow-front in resin transfer molding using electromechanical behavior and generative adversarial network. Composites Part B: Engineering. 2025;298:112382. doi:10.1016/j.compositesb.2025.112382
  9. Jeong JM, Eum S, On SY, Kageyama K, Murayama H, Uzawa K, et al. In-situ resin flow monitoring in VaRTM process by using optical frequency domain reflectometry and long-gauge FBG sensors. Composite Structures. 2022;282:115034. doi:10.1016/j.compstruct.2021.115034
  10. Wu D, Larsson R, Blinzler B. A preform deformation and resin flow coupled model including the cure kinetics and chemo-rheology for the VARTM process. International Journal of Material Forming. 2020;14(3):421-434. doi:10.1007/s12289-020-01570-z
  11. Kamath S, Caselato Gandia G, Adab N, Mehrdad E, Qian D, Lu H. Machine-Learning Based Curing Cycle Optimization in Wind Blade Manufacturing. Volume 2: Advanced Manufacturing. 2024. doi:10.1115/imece2024-146131
  12. Struzziero G, Skordos AA. Multi-objective optimization of Resin Infusion. Advanced Manufacturing: Polymer & Composites Science. 2019;5(1):17-28. doi:10.1080/20550340.2019.1565648
  13. Mendikute J, Baskaran M, Llavori I, Zugasti E, Aretxabaleta L, Aurrekoetxea J. Predicting the effect of voids generated during RTM on the low-velocity impact behaviour by machine learning-based surrogate models. Composites Part B: Engineering. 2023;260:110790. doi:10.1016/j.compositesb.2023.110790
  14. Francisco MB, Oliveira LAD, Pereira JLJ, Souza AD, da Cunha SS, Gomes GF. An optimization analysis of a sandwich composite panel with auxetic reentrant core using lichtenberg algorithm based on surrogate modelling. Mechanics of Advanced Materials and Structures. 2024;31(29):11953-11967. doi:10.1080/15376494.2024.2313165
  15. Feng Y, Yang B, Huang Y, Wang J, Causse P. FlowCastNet: A CNN-based surrogate model for the rapid prediction of flow filling patterns in VARTM processes. Composites Part A: Applied Science and Manufacturing. 2026;204:109656. doi:10.1016/j.compositesa.2026.109656
  16. Christoph Petroll MD. Synthetic Data Generation for Deep Learning Models. DS 111: Proceedings of the 32nd Symposium Design for X. 2021. doi:10.35199/dfx2021.11
  17. Chen S, Ouyang X, Rao X. Physics-Informed Neural Network (PINNs) for Flow Simulation in Polymer-Assisted Hot Water Flooding. Processes. 2026;14(2):197. doi:10.3390/pr14020197
  18. D. Humfeld, D. Gu, G. A. Butler, K. Nelson, and N. Zobeiry, “A machine learning framework for real-time inverse modeling and multi-objective process optimization of composites for active manufacturing control,” Compos. B Eng., vol. 223, Oct. 2021, doi:10.1016/J.COMPOSITESB. 2021.109150.
  19. Kyriazi E, Petsinis G, Zervos C, Poulopoulos I, Syriopoulos G, Neale G, et al. ML-based surrogate cure simulation for predicting process time and temperature overshoot in resin transfer moulding. Journal of Reinforced Plastics and Composites. 2025. doi:10.1177/07316844251390926
  20. Shen M, Xu X, Qi J, Li X, Xue B, Zhu M, et al. PMDI cross-linked rare earth/liquid metal reinforced ANF/MXene membranes for multifunctional electromagnetic interference shielding. Composites Part A: Applied Science and Manufacturing. 2024;182:108178. doi:10.1016/j.compositesa.2024.108178
  21. Bello IT, Taiwo R, Esan OC, Adegoke AH, Ijaola AO, Li Z, et al. AI-enabled materials discovery for advanced ceramic electrochemical cells. Energy and AI. 2024;15:100317. doi:10.1016/j.egyai.2023.100317
  22. Guo Y, Su H, Gao H, Shen Z, Yang P, Liu Y, et al. Insight into annealing-induced hardening and softening behaviors in a laser powder-bed fusion printed in-situ composite eutectic high-entropy alloy. Composites Part B: Engineering. 2024;281:111523. doi:10.1016/j.compositesb.2024.111523
  23. Machado J, Bodaghi M, Advani S, Correia N. The Development of Data-Driven Algorithms and Models for Monitoring Void Transport in Liquid Composite Molding Using a 3D-Printed Porous Media. Applied Sciences. 2025;15(19):10690. doi:10.3390/app151910690
  24. A. Almazán-Lázaro, E. López-Alba, and F. A. Díaz-Garrido, “Applied computer vision for composite material manufacturing by optimizing the impregnation velocity: An experimental approach,” J. Manuf. Process., vol. 74, pp. 52–62, Feb. 2022, doi:10.1016/J.JMAPRO. 2021.11.063.
  25. Leon JF, Li Y, Martin XA, Calvet L, Panadero J, Juan AA. A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations. Algorithms. 2023;16(9):408. doi:10.3390/a16090408
  26. Grumbach F, Müller A, Reusch P, Trojahn S. Robustness Prediction in Dynamic Production Processes—A New Surrogate Measure Based on Regression Machine Learning. Processes. 2023;11(4):1267. doi:10.3390/pr11041267
  27. H. Kang, H. J. Lee, T. G. Woo, C. S. You, S. H. Lim, and Y. D. Yoon, “Time Delay Implementation in Sensorless Control for Ultra-High-Speed Air Compressor Motor of Fuel-Cell Systems,” 2024 IEEE 10th International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia, pp. 2332–2337, 2024, doi:10.1109/IPEMC-ECCEASIA60879. 2024.10567890.
  28. Guinovart D, Chaki MS, Guinovart-Díaz R. Two-scale asymptotic homogenization analysis of piezoelectric composite materials in generalized curvilinear coordinates. Composites Part B: Engineering. 2024;284:111677. doi:10.1016/j.compositesb.2024.111677
  29. Charaf N, Haase J, Kulisch A, Von Elm C, Göhringer D. RTASS: a RunTime Adaptable and Scalable System for Network-on-Chip-Based Architectures. 2023 26th Euromicro Conference on Digital System Design (DSD). 2023:585-592. doi:10.1109/dsd60849.2023.00086
  30. Wang Z, Chu R, Zhang M, Wang X, Luan S. An Improved Hybrid Highway Traffic Flow Prediction Model Based on Machine Learning. Sustainability. 2020;12(20):8298. doi:10.3390/su12208298
  31. Lavaggi, F. Muhammed, L. Moretti, J. W. Gillespie, and S. G. Advani, “Correlation of the permeability and porosity development of carbon/carbon composites during pyrolysis,” Compos. Part A Appl. Sci. Manuf., vol. 181, p. 108156, Jun. 2024, doi:10.1016/J.COMPOSITESA. 2024.108156.
  32. Zhou Y, Ye W, Liu W, Chu F, Hu W, Song L, et al. Phosphononitrile based bismaleimide electronic packaging substrate with both fire safety and dielectric properties: Assisting 5G communication. Composites Part B: Engineering. 2024;280:111489. doi:10.1016/j.compositesb.2024.111489
  33. Khalid RZ, Ullah A, Khan A, Khan A, Inayat MH. Comparison of Standalone and Hybrid Machine Learning Models for Prediction of Critical Heat Flux in Vertical Tubes. Energies. 2023;16(7):3182. doi:10.3390/en16073182
  34. Shanthar R, Prosser R, Potluri P, Abeykoon C, Advani SG. Modelling and simulation of the polymer resin flow through fibres during Resin Transfer Moulding: a comprehensive review. Composites Part A: Applied Science and Manufacturing. 2026;208:109839. doi:10.1016/j.compositesa.2026.109839
  35. Matsuzaki R, Morikawa M, Oikawa Y, Ushiyama K. Predicting thickness impregnation in a VaRTM resin flow simulation using machine learning. Composites Part C: Open Access. 2021;5:100158. doi:10.1016/j.jcomc.2021.100158
  36. Machado J, Bodaghi M, Advani S, Correia N. The Development of Data-Driven Algorithms and Models for Monitoring Void Transport in Liquid Composite Molding Using a 3D-Printed Porous Media. Applied Sciences. 2025;15(19):10690. doi:10.3390/app151910690
  37. Szarski M, Chauhan S. Instant flow distribution network optimization in liquid composite molding using deep reinforcement learning. Journal of Intelligent Manufacturing. 2022;34(1):197-218. doi:10.1007/s10845-022-01990-5
Support