Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | e70144 |
| Fachzeitschrift | International Journal for Numerical Methods in Engineering |
| Jahrgang | 126 |
| Ausgabenummer | 19 |
| Publikationsstatus | Veröffentlicht - 7 Okt. 2025 |
Abstract
Short fiber-reinforced polymers (SFRPs) exhibit complex anisotropic, nonlinear, and pressure-dependent behavior due to their heterogeneous microstructures. Conventional constitutive models, while accurate, require extensive parameter calibration and may lack generalization capability under varied loading conditions. In this study, a physics-informed deep learning (PIDL) constitutive framework is proposed that integrates the governing physical laws with the flexibility of neural networks. The model employs long short-term memory (LSTM) networks to capture path-dependent behaviors and utilizes scalar invariants consistent with transverse isotropy to ensure thermodynamic consistency, objectivity, and material symmetry. The neural network is trained using synthetic data generated from a validated continuum-mechanical model for SFRPs, including elasto-plastic behavior and anisotropy. To validate the PIDL model, an open-hole tensile (OHT) test is simulated, and the predicted stresses are compared against those obtained from the classical constitutive model. While the initial PIDL model showed limitations under complex multiaxial stress states, a retraining strategy using randomly generated loading paths significantly improved its predictive accuracy. This study demonstrates the potential of physics-informed machine learning for developing generalizable and efficient data-driven constitutive models for complex composite materials.
ASJC Scopus Sachgebiete
- Mathematik (insg.)
- Numerische Mathematik
- Ingenieurwesen (insg.)
- Allgemeiner Maschinenbau
- Mathematik (insg.)
- Angewandte Mathematik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Journal for Numerical Methods in Engineering, Jahrgang 126, Nr. 19, e70144, 07.10.2025.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Physics-Informed Deep Learning Constitutive Model for Anisotropic and Pressure-Dependent Behavior of Short Fiber-Reinforced Polymers
AU - Dean, Aamir
AU - Naik, Vinayak B.
AU - Bahtiri, Betim
AU - Mahdi, Elsadig
AU - Kumar, Pavan K.A.V.
N1 - Publisher Copyright: © 2025 The Author(s). International Journal for Numerical Methods in Engineering published by John Wiley & Sons Ltd.
PY - 2025/10/7
Y1 - 2025/10/7
N2 - Short fiber-reinforced polymers (SFRPs) exhibit complex anisotropic, nonlinear, and pressure-dependent behavior due to their heterogeneous microstructures. Conventional constitutive models, while accurate, require extensive parameter calibration and may lack generalization capability under varied loading conditions. In this study, a physics-informed deep learning (PIDL) constitutive framework is proposed that integrates the governing physical laws with the flexibility of neural networks. The model employs long short-term memory (LSTM) networks to capture path-dependent behaviors and utilizes scalar invariants consistent with transverse isotropy to ensure thermodynamic consistency, objectivity, and material symmetry. The neural network is trained using synthetic data generated from a validated continuum-mechanical model for SFRPs, including elasto-plastic behavior and anisotropy. To validate the PIDL model, an open-hole tensile (OHT) test is simulated, and the predicted stresses are compared against those obtained from the classical constitutive model. While the initial PIDL model showed limitations under complex multiaxial stress states, a retraining strategy using randomly generated loading paths significantly improved its predictive accuracy. This study demonstrates the potential of physics-informed machine learning for developing generalizable and efficient data-driven constitutive models for complex composite materials.
AB - Short fiber-reinforced polymers (SFRPs) exhibit complex anisotropic, nonlinear, and pressure-dependent behavior due to their heterogeneous microstructures. Conventional constitutive models, while accurate, require extensive parameter calibration and may lack generalization capability under varied loading conditions. In this study, a physics-informed deep learning (PIDL) constitutive framework is proposed that integrates the governing physical laws with the flexibility of neural networks. The model employs long short-term memory (LSTM) networks to capture path-dependent behaviors and utilizes scalar invariants consistent with transverse isotropy to ensure thermodynamic consistency, objectivity, and material symmetry. The neural network is trained using synthetic data generated from a validated continuum-mechanical model for SFRPs, including elasto-plastic behavior and anisotropy. To validate the PIDL model, an open-hole tensile (OHT) test is simulated, and the predicted stresses are compared against those obtained from the classical constitutive model. While the initial PIDL model showed limitations under complex multiaxial stress states, a retraining strategy using randomly generated loading paths significantly improved its predictive accuracy. This study demonstrates the potential of physics-informed machine learning for developing generalizable and efficient data-driven constitutive models for complex composite materials.
KW - anisotropic constitutive modeling
KW - data-driven mechanics
KW - physics-informed neural networks (PINNs)
KW - pressure-dependent materials
KW - short fiber-reinforced polymers (SFRPs)
UR - http://www.scopus.com/inward/record.url?scp=105018461160&partnerID=8YFLogxK
U2 - 10.1002/nme.70144
DO - 10.1002/nme.70144
M3 - Article
AN - SCOPUS:105018461160
VL - 126
JO - International Journal for Numerical Methods in Engineering
JF - International Journal for Numerical Methods in Engineering
SN - 0029-5981
IS - 19
M1 - e70144
ER -