Artificial Intelligence and Constitutive Modeling Equations for Predictive Design of High-Performance Polymer Composites

Notice

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.

Year : 2026 | Volume : 14 | 04 | Page :
By

Harshal P. Varade,

P. William,

Amit V. Mohod,

Dipesh B. Pardeshi,

Atul A. Barhate,

Sharad Ninu Kolte,

Ganesh P. Dawange,

  1. Assistant Professor, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  2. Professor (Research), School of Computer Science and Technology, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India
  3. Assistant Professor, Department of Electrical Engineering, Prof. Ram Meghe college of Engineering and Management, Badnera, Maharashtra, India
  4. Professor, Department of Electrical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  5. Associate Professor, Department of Electrical Engineering, Godavari College of Engineering, Jalgaon, Dr. Babasaheb Ambedkar Technological University, Lonere, Maharashtra, India
  6. Lecturer, Department of Electrical Engineering, K. J. Somaiya polytechnic, Mumbai, Maharashtra, India
  7. Assistant Professor, Department of Structural Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India

Abstract

Growing polymer composite applications demand accurate mechanical prediction, yet complex interactions and conventional constitutive models limit predictive capability and require extensive calibration. To report these challenges, this research recommends a combined Artificial Intelligence (AI) and constitutive modeling approach based on an Enhanced Tasmanian Devil Optimizer-tuned Residual Neural Network with Multilayer Perceptron (ETDO-ResNet-MLP) for the predictive design of high-performance polymer composites. The study uses a publicly available Polymer Composite Property Dataset comprising 15,000 specimens with material composition, reinforcement characteristics, processing conditions, constitutive descriptors, and mechanical-property information. The dataset is preprocessed using K-Nearest Neighbor (KNN) imputation and Z-score normalization, while Principal Component Analysis (PCA) extracts the most informative features for predictive modeling. The extracted features are integrated with constitutive modeling equations that characterize the nonlinear stress-strain response and damage evolution of polymer composites. The constitutive parameters and physics-based descriptors are subsequently supplied as inputs to the proposed ETDO-ResNet-MLP model, enabling physics-guided learning and improving prediction reliability. The ETDO automatically determines the optimal network hyperparameters, significantly improving convergence speed and prediction accuracy. The proposed ETDO-ResNet-MLP accurately predicts tensile strength, elastic modulus, fracture toughness, and impact resistance of high-performance polymer composites. Python-based experiments achieved an R² of 0.9796, surpassing conventional models in predictive performance. The model further provides robustness, interpretability, and computational efficiency, supporting rapid material design and optimization.

Keywords: Artificial Intelligence (AI), constitutive modeling, Polymer composites, Material composition.

How to cite this article: Harshal P. Varade, P. William, Amit V. Mohod, Dipesh B. Pardeshi, Atul A. Barhate, Sharad Ninu Kolte, Ganesh P. Dawange. Artificial Intelligence and Constitutive Modeling Equations for Predictive Design of High-Performance Polymer Composites. Journal of Polymer & Composites. 2026; 14(04):-.
How to cite this URL: Harshal P. Varade, P. William, Amit V. Mohod, Dipesh B. Pardeshi, Atul A. Barhate, Sharad Ninu Kolte, Ganesh P. Dawange. Artificial Intelligence and Constitutive Modeling Equations for Predictive Design of High-Performance Polymer Composites. Journal of Polymer & Composites. 2026; 14(04):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=255085

References

  1. Yim YJ, Yoon YH, Kim SH, Lee JH, Chung DC, Kim BJ. Carbon nanotube/polymer composites for functional applications. Polymers. 2025;17(1):119. doi:10.3390/polym17010119.
  2. Tarhini A, Tehrani-Bagha AR. Advances in preparation methods and conductivity properties of graphene-based polymer composites. Applied Composite Materials. 2023;30(6):1737-1762. doi:10.1007/s10443-023-10145-5.
  3. Fu X, Lin J, Liang Z, Yao R, Wu W, Fang Z, et al. Graphene oxide as a promising nanofiller for polymer composite. Surfaces and Interfaces. 2023;37:102747. doi:10.1016/j.surfin.2023.102747.
  4. Mohammed K, Zulkifli R, Tahir MFM, Gaaz TS. A study of mechanical properties and performance of bamboo fiber/polymer composites. Results in Engineering. 2024;23:102396. doi:10.1016/j.rineng.2024.102396.
  5. Wang Q, Che J, Wu W, Hu Z, Liu X, Ren T, et al. Contributing factors of dielectric properties for polymer matrix composites. Polymers. 2023;15(3):590. doi:10.3390/polym15030590.
  6. Smola-Dmochowska A, Lewicka K, Macyk A, Rychter P, Pamuła E, Dobrzyński P. Biodegradable polymers and polymer composites with antibacterial properties. International Journal of Molecular Sciences. 2023;24(8):7473. doi:10.3390/ijms24087473.
  7. Zotti A, Paduano T, Napolitano F, Zuppolini S, Zarrelli M, Borriello A. Fused deposition modeling of polymer composites: Development, properties and applications. Polymers. 2025;17(8):1054. doi:10.3390/polym17081054.
  8. Yuan X, Zhang Z, Mu X, Shan C, Gao X, Zhu B. Recent progress on interface characterization methods of carbon fiber reinforced polymer composites. Chemical Engineering Journal. 2024;499:156220. doi:10.1016/j.cej.2024.156220.
  9. Zhou X, Wu L, Wang J. Recent developments in conductive polymer composites for fused deposition modeling. Composites Part A: Applied Science and Manufacturing. 2023;174:107739. doi:10.1016/j.compositesa.2023.107739.
  10. Li Y, Meng J, Luo J, Wang P, Ma J, Zhao Z, et al. Cryogenic mechanics and damage behaviors of carbon fiber reinforced polymer composites. Composites Part A: Applied Science and Manufacturing. 2023;169:107484. doi:10.1016/j.compositesa.2023.107484.
  11. Malashin IP, Martysyuk D, Nelyub V, Borodulin A, Gantimurov A, Tynchenko V. Deep learning for property prediction of natural fiber polymer composites. Scientific Reports. 2025;15(1):27837. doi:10.1038/s41598-025-10841-1.
  12. Imoisili PE, Makhatha ME, Jen TC. Artificial intelligence prediction and optimization of the mechanical strength of modified natural fibre/MWCNT polymer nanocomposite. Journal of Science: Advanced Materials and Devices. 2024;9(2):100705. doi:10.1016/j.jsamd.2024.100705.
  13. Malashin I, Tynchenko V, Gantimurov A, Nelyub V, Borodulin A. A multi-objective optimization of neural networks for predicting the physical properties of textile polymer composite materials. Polymers. 2024;16(12):1752. doi:10.3390/polym16121752.
  14. Hamzat AK, Salman UT, Murad MS, Altay O, Bahceci E, Asmatulu E, et al. Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites. Hybrid Advances. 2025;8:100385. doi:10.1016/j.hybadv.2025.100385.
  15. Shi D, Xu K, Yu X, Cui P, Chao Z. Strength estimation of textured polymer layer-reinforced materials in practical marine engineering based on physical experiments and artificial intelligence modelling. Frontiers in Marine Science. 2025;12:1653741. doi:10.3389/fmars.2025.1653741.
  16. Li Z, Du J, Yi H, Mao Z, Du K, Li T, et al. Machine learning framework for evaluating microscale interface cohesive zone models of polymer composites. ACS Applied Materials & Interfaces. 2025;17(45):62590-62605. doi:10.1021/acsami.5c16583.
  17. Niang N, Barrière T, Gabrion X, Holopainen S, Placet V. Predicting the deformability of natural short-fiber reinforced polymer composites through combined constitutive mathematical and AI-based modeling approaches. Composites Science and Technology. 2025:111353. doi:10.1016/j.compscitech.2025.111353.
  18. Zhao W, Mao L, Pang Z, Du Z. Development and validation of modified constitutive model for carbon fiber reinforced polymer composites under impact loading. Aerospace Science and Technology. 2025;157:109845. doi:10.1016/j.ast.2024.109845.
  19. Cózar IR, Otero F, Maimi P, González EV, Turon A, Camanho PP. An enhanced constitutive model to predict plastic deformation and multiple failure mechanisms in fibre-reinforced polymer composite materials. Composite Structures. 2024;330:117696. doi:10.1016/j.compstruct.2023.117696.
  20. Yuan XW, Li WG, Xiao ZM, Zhang YM. Prediction of temperature-dependent transverse strength of carbon fiber reinforced polymer composites by a modified cohesive zone model. Composite Structures. 2023;304:116310. doi:10.1016/j.compstruct.2022.116310.
  21. Guo X, Wang E, Yang H, Zhai W. Mechanical characterization and constitutive modeling of additively-manufactured polymeric materials and lattice structures. Journal of the Mechanics and Physics of Solids. 2024;189:105711. doi:10.1016/j.jmps.2024.105711.
  22. Wang W, Liu Y, Xie Z. A modified constitutive model for isotropic hyperelastic polymeric materials and its parameter identification. Polymers. 2023;15(15):3172. doi:10.3390/polym15153172.
  23. Behseresht S, Park YH. Additive manufacturing of composite polymers: Thermomechanical FEA and experimental study. Materials. 2024;17(8):1912. doi:10.3390/ma17081912.
  24. Ghasemi H, Yazdani H. Atomistic simulation and machine learning predictions of mechanical response in nanotube-polymer composites considering filler morphology and aggregation. Computational Materials Science. 2025;246:113399. doi:10.1016/j.commatsci.2024.113399.
  25. Maharana SK, Soni G, Mitra M. A machine learning-based prediction of biaxial failure envelope of a short fiber-reinforced polymer composite. Composites Science and Technology. 2025;267:111176. doi:10.1016/j.compscitech.2025.111176.
  26. Maharana SK, Soni G, Mitra M. A machine learning based prediction of elasto-plastic response of a short fiber reinforced polymer (SFRP) composite. Modelling and Simulation in Materials Science and Engineering. 2023;31(7):075001. doi:10.1088/1361-651X/aced5a.
  27. Jiang K, Wen J, Wei Y. Machine learning based constitutive modelling on craze yielding in polymeric materials. Acta Mechanica Sinica. 2025;41(7):425370. doi:10.1007/s10409-025-25370-x.
  28. Chen J, Zhou X, Du C, Wang Q, Peng X. A constitutive model for carbon fabric-reinforced shape memory polymer composites based on Eshelby’s inclusion theorem. Composites Science and Technology. 2025;261:111042. doi:10.1016/j.compscitech.2025.111042.
  29. Lin CH, Hung YC. Viscoelastic effects on the overall responses of Terfenol-D/polymer composites. International Journal of Solids and Structures. 2023;262:112087. doi:10.1016/j.ijsolstr.2022.112087.
  30. Chen S, Li L. An anisotropic damage-plasticity constitutive model of continuous fiber-reinforced polymers. Polymers. 2024;16(3):334. doi:10.3390/polym16030334.
  31. Shen T, Fang Y, Zhang Y, Lou J, Du J. Multi-scale modeling of damage evolution for particle-filled polymer composites. Composite Structures. 2025;351:118572. doi:10.1016/j.compstruct.2024.118572.
  32. Gu J, Wang C, Zeng H, Duan H, Wan M, Sun H. A thermo-mechanical constitutive model for triple-shape and two-way shape memory polymers. Smart Materials and Structures. 2024;33(6):065034. doi:10.1088/1361-665X/ad4cc2.
  33. Champa-Bujaico E, Díez-Pascual AM, Redondo AL, Garcia-Diaz P. Optimization of mechanical properties of multiscale hybrid polymer nanocomposites: A combination of experimental and machine learning techniques. Composites Part B: Engineering. 2024;269:111099. doi:10.1016/j.compositesb.2023.111099.
Ahead of Print Subscription Original Research
Volume 14
04
Received 12/08/2026
Accepted 01/09/2026
Published 09/09/2026
Publication Time 28 Days

Login

My IP

PlumX Metrics