Prediction of tensile properties in fiber-reinforced composites by machine learning models
DOI:
https://doi.org/10.15282/ijame.23.3.2026.12.1048Keywords:
Fiber-reinforced composite, Tensile properties, Prediction, Machine learningAbstract
The consistent design of fiber-reinforced composites (FRCs) remains challenging due to their heterogeneous structures and the complex relationships among processing parameters and material properties. Conventional tensile characterization is costly and destructive, while existing predictive models are often limited to specific tensile parameters or single-fiber composite systems. This study addresses these limitations by developing machine learning (ML) models to simultaneously predict multiple tensile properties of both pure and hybrid composites using experimental data. A total of 54 laminates were fabricated and subjected to tensile testing, including pure and hybrid compositions of carbon, Kevlar, and glass fibers in cross-ply and quasi-isotropic lay-up with 4-, 8-, and 12-ply configurations. Several ML algorithms were implemented, including baseline algorithms [Linear Regression (LR), K-Nearest Neighbor (KNN), Decision Tree (DT), and Support Vector Machine (SVM)], ensemble models [Random Forest (RF), Gradient Boosting (GB), Stochastic Gradient Boosting (SGB), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost)], and Artificial Neural Network (ANN). The experimental results showed that the Kevlar-glass bi-hybrid cross-ply 4-ply laminate (373.46 MPa) and the carbon-glass-Kevlar tri-hybrid cross-ply 8-ply laminate (389.79 MPa) exhibited higher tensile strength than the pure Kevlar laminate (326.40 MPa). Among the evaluated models, K-Nearest Neighbor (KNN) achieved the best predictive performance (R2 = 0.87, MSE = 318.84, MAE = 7.73), followed by Stochastic Gradient Boosting (SGB) (R2 = 0.78), while the ANN demonstrated moderate performance
(R2 = 0.41). The results validate the feasibility of applying ML, particularly instance-based and ensemble learning models, to predict the tensile behavior of fiber-reinforced composites using a limited experimental dataset, thereby reducing reliance on destructive testing and accelerating the design of high-performance hybrid composites for aerospace and automotive applications.
References
[1] E. Selver, P. Potluri, C. Soutis, and P. Hogg, “Healing potential of hybrid materials for structural composites,” Composition Structure, vol. 122, pp. 57–66, 2015, doi: 10.1016/j.compstruct.2014.11.027.
[2] A. K. Hamzat, U. T. Salman, M. S. Murad, et al., “Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites,” Hybrid Advance, vol. 8, no. 2024. p. 100385, 2025, doi: 10.1016/j.hybadv.2025.100385.
[3] R. R. Baishya and S. W. Case, “Prediction of mechanical properties of glass-epoxy composites using supervised learning,” Journal Reinforce Plastic Composite, pp. 1–26, 2025, doi: 10.1177/07316844251318775.
[4] M. Su, L. Liu, Y. Xie, H. Peng, and C. Kang, “Prediction of the elastic properties and strength of unidirectional carbon fiber reinforced polymers based on representative volume element simulation,” Case Study Construction Material, vol. 23, no. June, p. e04963, 2025, doi: 10.1016/j.cscm.2025.e04963.
[5] J. K. Jatavallabhula, V. R. Veeredhi, G. S. Reddy, R. R. Baridula, and V. V. Satyanarayana, “Machine Learning-Based Prediction of Impact Toughness in AISI 430–AISI 304 Friction-Welded Joints,” International Journal Automotive Mechanical Engineering, vol. 22, no. 1, pp. 12118–12132, 2025, doi: 10.15282/IJAME.22.1.2025.13.0930.
[6] Z. Qi, N. Zhang, Y. Liu, and W. Chen, “Prediction of mechanical properties of carbon fiber based on cross-scale FEM and machine learning,” Composite. Structure, vol. 212,2018, pp. 199–206, 2019, doi: 10.1016/j.compstruct.2019.01.042.
[7] K. Berladir, K. Antosz, V. Ivanov, and Z. Mitaľová, “Machine Learning-Driven Prediction of Composite Materials Properties Based on Experimental Testing Data,” Polymers (Basel)., vol. 17, no. 5, p. 694, 2025, doi: 10.3390/polym17050694.
[8] T. R. C. Chuaqui, A. T. Rhead, R. Butler, and C. Scarth, “A data-driven Bayesian optimisation framework for the design and stacking sequence selection of increased notched strength laminates,” Composite Part B Eng., vol. 226, p. 109347, 2021, doi: 10.1016/j.compositesb.2021.109347.
[9] Y. Zhang and X. Xu, “Machine learning tensile strength and impact toughness of wheat straw reinforced composites,” Machine Learning with Application, vol. 6, p. 100188, 2021, doi: 10.1016/j.mlwa.2021.100188.
[10] P. Beldar and S. Kadbhane, “Utilizing machine learning to forecast mechanical characteristics of NaOH-Treated jute fiber reinforced composite materials,” Material Letter, vol. 377,p. 137411,2024, doi: 10.1016/j.matlet.2024.137411.
[11] E. Kosicka, A. Krzyzak, M. Dorobek, and M. Borowiec, “Prediction of Selected Mechanical Properties of Polymer Composites with Alumina Modifiers,” Materials (Basel)., vol. 15, no. 3, p. 882,2022. doi: 10.3390/ma15030882.
[12] T. Sadat, “Machine Learning-Assisted Tensile Modulus Prediction for Flax Fiber/Shape Memory Epoxy Hygromorph Composites,” Applied Mechanics, vol. 4, no. 2, pp. 752–762,2023. doi: 10.3390/applmech4020038.
[13] A. Mahajan, S. Bajoliya, S. Khandelwal, et al., “Comparison of ML algorithms for prediction of tensile strength of polymer matrix composites,” Materials Today Proceeding, vol. 12, no. 105, pp. 2214–7853, 2022. doi: 10.1016/j.matpr.2022.12.105.
[14] F. Rehman, H. Li, S. A. Khokhar, U. J. Malik, A. Hamza, and S. Song, “Development of an artificial neural network (ANN) based model for tailoring the fracture response of eco-friendly engineered geopolymer composites (EGC),” Next Material, vol. 8, no. February, p. 100812, 2025.doi: 10.1016/j.nxmate.2025.100812.
[15] M. Li, H. Zhang, S. Li, W. Zhu, and Y. Ke, “Machine learning and materials informatics approaches for predicting transverse mechanical properties of unidirectional CFRP composites with microvoids,” Material Design, vol. 224, p. 111340, 2022, doi: 10.1016/j.matdes.2022.111340.
[16] J. Friemann, B. Dashtbozorg, M. Fagerström, and S. M. Mirkhalaf, “A micromechanics-based recurrent neural network model for path-dependent cyclic deformation of short fiber composites,” International Journal for Numerical Methods in Engineering, vol. 124, no. 10, pp. 2292–2314, 2023. doi: 10.1002/nme.7211.
[17] A. Y. Diab and A. C. Ferche, “Prediction of Tensile Properties of Ultra-High-Performance Concrete Using Artificial Neural Network,” ACI Structure Journal, vol. 121, no. 2, pp. 57–68, 2024, doi: 10.14359/51740245.
[18] J. B. anak Jores, E. Jayamani, T. S. M. Lai, J. Subramanian, and C. R. Rejeesh, “Evaluation of mechanical property of banana HDPE composite through experiment and artificial neural network (ANN),” Material Today Proceeding, vol. 103, no. June 2023, pp. 506–512, 2024.doi: 10.1016/j.matpr.2023.08.351.
[19] P. E. Imoisili, M. E. Makhatha, and T. C. Jen, “Artificial Intelligence prediction and optimization of the mechanical strength of modified Natural Fibre/MWCNT polymer nanocomposite,” Journal Science Advance Material Devices, vol. 9, no. 2, p. 100705, 2024.doi: 10.1016/j.jsamd.2024.100705.
[20] R. Al-Jarrah and F. M. AL-Oqla, “A novel integrated BPNN/SNN artificial neural network for predicting the mechanical performance of green fibers for better composite manufacturing,” Composite Structure, vol. 289, no. March, p. 115475, 2022.doi: 10.1016/j.compstruct.2022.115475.
[21] Y. Sun, I. Hanhan, M. D. Sangid, and G. Lin, “Predicting Mechanical Properties from Microstructure Images in Fiber-Reinforced Polymers Using Convolutional Neural Networks,” Journal Composite Science, vol. 8, no. 10, pp. 1–15, 2024, doi: 10.3390/jcs8100387.
[22] S. Sakata, G. Stefanou, Y. Arai, et al., “A dual experimental/computational data-driven approach for random field modeling based strength estimation analysis of composite structures,” Computer Methods Applied Mechanics and Engineering, vol. 433, no. October 2024, p. 117476, 2025, doi: 10.1016/j.cma.2024.117476.
[23] B. Yin, J. Huang, and W. Sun, “Peridynamics-fueled convolutional neural network for predicting mechanical constitutive behaviors of fiber reinforced composites,” Computer Methods Applied Mechanics and Engineering, vol. 431, no. August, p. 117309, 2024, doi: 10.1016/j.cma.2024.117309.
[24] J. Jung, Y. Kim, J. Park, and S. Ryu, “Transfer learning for enhancing the homogenization-theory-based prediction of elasto-plastic response of particle/short fiber-reinforced composites,” Composite Structure, vol. 285, no. October 2021, p. 115210, 2022, doi: 10.1016/j.compstruct.2022.115210.
[25] I. Malashin, V. Tynchenko, A. Gantimurov, V. Nelyub, and A. Borodulin, “A Multi-Objective Optimization of Neural Networks for Predicting the Physical Properties of Textile Polymer Composite Materials,” Polymers (Basel)., vol. 16, no. 12, pp. 1–21, 2024, doi: 10.3390/polym16121752.
[26] Y. Guo, P.; Meng, W.; Xu, M.; Li, V.C.; Bao, “Predicting Mechanical Properties of High-Performance Fiber-Reinforced Cementitious Composites by Integrating Micromechanics and Machine Learning,” Materials (Basel)., vol. 14, p. 3143, 2021, doi: 10.3390/ma14123143.
[27] R. R. Abhendra Pratap Singh, Md Ehsan Asgar, Ajay K.S Singholi, Uma Gautam, “Machine Learning Approaches for Predicting Mechanical Properties of Composite Materials,” AIJR Proc. Proc. 2nd Int. Conf. Emerg. Appl. Artif. Intell. Mach. Learn. Cybersecurity” (ICAMC 2024),pp. 35–41, 2024, doi: 10.21467/proceedings.178.5
[28] G. V. Marrivada, P. K. Chaganti, and R. Sujith, “Experimental investigation and machine learning prediction of mechanical properties of graphene nanoplatelets based triaxial braided composites,” Materials Today Communication, vol. 34, 2022, p. 105305, 2023, doi: 10.1016/j.mtcomm.2022.105305.
[29] M. Gayatri Vineela, A. Dave, and P. Kiran Chaganti, “Artificial neural network based prediction of tensile strength of hybrid composites,” Material Today Proceeding, vol. 5, no. 9, pp. 19908–19915, 2018, doi: 10.1016/j.matpr.2018.06.356.
[30] Q. Liu, F. Wang, W. Xiao, and J. Cui, “Binary dynamic stochastic search algorithm with support vector regression for feature selection in low-velocity impact localization problem,” Engineering Applied Artificial Intelligence, vol. 124, p. 106554, 2023, doi: 10.1016/j.engappai.2023.106554.
[31] T. Kotsiopoulos, P. Sarigiannidis, D. Ioannidis, and D. Tzovaras, “Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm,” Computer Science Review, vol. 40, p. 100341, 2021, doi: 10.1016/j.cosrev.2020.100341.
[32] D. P. Kroese, Z. I. Botev, T. Taimre, and R. Vaisman, “Data Science and Machine Learning,” Data Science Machine Learning, 2019, doi: 10.1201/9780367816971.
[33] M. LOTZ, “Mathematics of Machine Learning MIT,” Mit, pp. 1–156, 2020.
[34] S. Hiremath, Y. Zhang, L. Zhang, and T. W. Kim, “Machine learning approach to evaluating impact behavior in fabric-laminated composite materials,” Results Engineering, vol. 23,p. 102576, 2024, doi: 10.1016/j.rineng.2024.102576.
[35] S. Selek and Y. Sahin, “Tensile Property of Carbon Reinforced Epoxy Composites for Different Directions,” Eurasia Proceeding Science Technology Engineering Mathematic, vol. 26, pp. 135–141, 2023, doi: 10.55549/epstem.1409414.
[36] D. Gao, Z. Bao, W. Han, et al., “Effect of Strain Rate on Tensile Properties of Carbon Fiber-Reinforced Epoxy Laminates with Different Stacking Sequences and Ply Orientations,” Polymers (Basel)., vol. 15, no. 12, pp. 1–13, 2023, doi: 10.3390/polym15122711.
[37] B. Nagaraj Goud, S. Sura, P. Aravind, B. Jawahar Lal, K. Sanskruti, and C. Pavan, “An experimental study on mechanical properties of Kevlar composite for aircraft structural applications,” Material Today Proceeding, vol. 64, pp. 909–916, 2022, doi: 10.1016/j.matpr.2022.06.053.
[38] L. R. Natarajan, S. Kathiresan, and M. Vinayagam, “Effect of fiber hybridization on bi-directionally oriented natural aglass fiber reinforced polymer composites,” Review Material, vol. 30, 2025, doi: 10.1590/1517-7076-RMAT-2024-0648.
[39] P. Maithil, P. Gupta, and M. L. Chandravanshi, “Study of mechanical properties of the natural-synthetic fiber reinforced polymer matrix composite,” Material Today Proceedings, pp. 1–7, 2023, doi: 10.1016/j.matpr.2023.01.245.
[40] S. M. Gargi Danda De, Soumya Sarkar, “Effects of Fiber Orientation Distribution on the Mechanical Properties of Paper.,” Indian Journal Science Technology, vol. 17, no. 20, pp. 2050–2055, 2024, doi: 10.17485/IJST/v17i20.2536.
[41] E. D. Vial, R. J. da Silva, J. C. dos Santos, et al., “Glass and Aramid Fibre-reinforced Bio-based Polymer Composites Manufactured By Vacuum Infusion: A Statistical Approach to Their Physical and Mechanical Properties,” Appl. Compos. Mater., vol. 30, no. 5, pp. 1627–1644, 2023, doi: 10.1007/s10443-023-10142-8.
[42] R. Hidayanto, D. I. Taufiq, H. Judawisastra, and R. Wirawan, “Compressive Strength and Elastic Modulus of a 3D Woven Glass/Polyester Fire-Retardant Sandwich Composite,” International Journal Automotive Mechanical Engineering, vol. 21, no. 1, pp. 10981–10992, 2024, doi: 10.15282/ijame.21.1.2024.03.0849.
[43] A. Vasudevan, R. Pandiyarajan, B. Navin Kumar, and J. Vijayarangam, “Effect of Kevlar Ply Orientation on Mechanical Characterization of Kevlar-Glass Fiber Laminated Composites,” IOP Conf. Ser. Mater. Sci. Eng., vol. 988, no. 012088, 2020, doi: 10.1088/1757-899X/988/1/012088.
[44] K. Karthik, D. Rajamani, A. Manimaran, and J. Udayaprakash, “Evaluation of tensile properties on Glass/Carbon/Kevlar fiber reinforced hybrid composites,” Material Today Proceedings, vol. 39, pp. 1655–1660, 2020, doi: 10.1016/j.matpr.2020.06.049.
[45] A. Das Anto, S. Mia, and M. A. Hasib, “The influence of number and orientation of ply on tensile properties of hybrid composites,” JPhys Mater., vol. 2, no. 2, p. 025002, 2019, doi: 10.1088/2515-7639/aaff7a.
[46] M. V. Pathan, S. A. Ponnusami, J. Pathan, et al., “Predictions of the mechanical properties of unidirectional fibre composites by supervised machine learning,” Science Report, vol. 9, no. 1, pp. 1–10, 2019, doi: 10.1038/s41598-019-50144-w.
[47] V. Shah, S. Zadourian, C. Yang, Z. Zhang, and G. X. Gu, “Data-driven approach for the prediction of mechanical properties of carbon fiber reinforced composites,” Material Advances, vol. 3, no. 19, pp. 7319–7327, 2022, doi: 10.1039/d2ma00698g.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
