Physics-Informed Deep Learning Surrogate for Mechanical-Response Prediction and Failure Assessment of High-Performance Polymer Composites
6 affiliations
- 1Department of Computer Science, College of Computer Science and Information Technology (CCSIT), King Faisal University, Al-Ahsa 31982, Saudi Arabia
- 2Department of Computer Engineering, College of Computer Science and Information Technology CCSIT, King Faisal University, Al Ahsa 31982, Saudi Arabia
- 3Department of Civil and Environmental Engineering, College of Engineering, King Faisal University, Al-Ahsa 31982, Saudi Arabia
- 4Department of Civil Engineering, Faculty of Engineering, Islamic University of Madinah, Al-Madinah Al-Munawara, Prince Naif Ibn Abdulaziz, Al Jamiah, Medina 42351, Saudi Arabia
- 5Department of Computer Engineering, College of Computer, Qassim University, Buraydah 51452, Saudi Arabia
- 6Department of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia
Abstract
Polymer composites show complex, nonlinear mechanical behavior. This makes their rational design hard. Running tests or high-fidelity simulations for every candidate design is slow and costly. Purely data-driven models are fast, but they can break basic mechanics outside the training range. Most physics-informed (PI) models, on the other hand, target a single constitutive law or failure mode, and their loss weights are set by hand. This study presents a DBN-GJO-PI-RNN surrogate that links deep feature learning, physics-constrained learning and failure screening in one workflow. A Deep Belief Network (DBN) learns compact latent features from the material and loading inputs. A PI Recurrent Neural Network (PI-RNN) then predicts the mechanical response under a composite loss with data, constitutive, equilibrium and boundary terms. Golden Jackal Optimization (GJO) tunes the network settings and the three loss weights together. Its fitness function rewards both accuracy and physical consistency. The predicted failure index is then checked against the onset criterion (FI ≥ 1). We tested the framework on a public dataset of 5000 polymer-composite samples with six response targets. On the test set, it reached a MAE of 1.1132, a RMSE of 1.3962 and an R2 of 0.9932. Its RMSE was 38.3% lower than that of the best purely data-driven baseline (TCN) and 50.6% lower than that of a standard RNN. The ablation study showed that each module reduced the error. The framework offers a fast, physics-aware surrogate for screening polymer-composite designs before costly tests or simulations.
Related
- Mechanical performance of natural fiber reinforced polymer composites with critical assessment of recent advances and future perspectives
- The Role of Carbon Fibers in FFF 3D Printed Composites: A Comprehensive Review on the Effect on Mechanical Properties, Fracture Toughness, and Tribological Performance
- From Reinforcement to Prediction: Mechanical Behavior and Modeling of CNT-Reinforced Cementitious Composites
- Flow-Induced Structuring of Polypropylene-Based Composites for Improved Mechanical and Thermal Performance
- Mechanical performance and eco-efficiency of thermoplastic polyurethane composites reinforced with recycled tire rubber
BibTeX
@article{haque2026physicsinformed,
title = {{Physics-Informed Deep Learning Surrogate for Mechanical-Response Prediction and Failure Assessment of High-Performance Polymer Composites}},
author = {Md Ehtesam Haque and Ramasamy Naidu and Md Arifuzzaman and Ayed Eid Alluqmani and Muhammad Ali Martuza and Akm Azad},
journal = {Polymers},
year = {2026},
month = oct,
doi = {10.3390/polym18212678},
url = {https://www.mdpi.com/2073-4360/18/21/2678},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Physics-Informed Deep Learning Surrogate for Mechanical-Response Prediction and Failure Assessment of High-Performance Polymer Composites
AU - Md Ehtesam Haque
AU - Ramasamy Naidu
AU - Md Arifuzzaman
AU - Ayed Eid Alluqmani
AU - Muhammad Ali Martuza
AU - Akm Azad
PY - 2026
DA - 2026/10/28
JO - Polymers
DO - 10.3390/polym18212678
UR - https://www.mdpi.com/2073-4360/18/21/2678
AB - Polymer composites show complex, nonlinear mechanical behavior. This makes their rational design hard. Running tests or high-fidelity simulations for every candidate design is slow and costly. Purely data-driven models are fast, but they can break basic mechanics outside the training range. Most physics-informed (PI) models, on the other hand, target a single constitutive law or failure mode, and their loss weights are set by hand. This study presents a DBN-GJO-PI-RNN surrogate that links deep feature learning, physics-constrained learning and failure screening in one workflow. A Deep Belief Network (DBN) learns compact latent features from the material and loading inputs. A PI Recurrent Neural Network (PI-RNN) then predicts the mechanical response under a composite loss with data, constitutive, equilibrium and boundary terms. Golden Jackal Optimization (GJO) tunes the network settings and the three loss weights together. Its fitness function rewards both accuracy and physical consistency. The predicted failure index is then checked against the onset criterion (FI ≥ 1). We tested the framework on a public dataset of 5000 polymer-composite samples with six response targets. On the test set, it reached a MAE of 1.1132, a RMSE of 1.3962 and an R2 of 0.9932. Its RMSE was 38.3% lower than that of the best purely data-driven baseline (TCN) and 50.6% lower than that of a standard RNN. The ablation study showed that each module reduced the error. The framework offers a fast, physics-aware surrogate for screening polymer-composite designs before costly tests or simulations.
SN - 2073-4360
ER -