Physics-Informed Deep Learning Constitutive Model for Anisotropic and Pressure-Dependent Behavior of Short Fiber-Reinforced Polymers

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Aamir Dean
  • Vinayak B. Naik
  • Betim Bahtiri
  • Elsadig Mahdi
  • Pavan K.A.V. Kumar

Organisationseinheiten

Externe Organisationen

  • Universität Sudan für Wissenschaft und Technologie (SUST)
  • Qatar University (QU)
  • Technische Universität Wien (TUW)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummere70144
FachzeitschriftInternational Journal for Numerical Methods in Engineering
Jahrgang126
Ausgabenummer19
PublikationsstatusVeröffentlicht - 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

Zitieren

Physics-Informed Deep Learning Constitutive Model for Anisotropic and Pressure-Dependent Behavior of Short Fiber-Reinforced Polymers. / Dean, Aamir; Naik, Vinayak B.; Bahtiri, Betim et al.
in: International Journal for Numerical Methods in Engineering, Jahrgang 126, Nr. 19, e70144, 07.10.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Download
@article{4f57716a6fb84979abdcd179aa1f4ff4,
title = "Physics-Informed Deep Learning Constitutive Model for Anisotropic and Pressure-Dependent Behavior of Short Fiber-Reinforced Polymers",
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.",
keywords = "anisotropic constitutive modeling, data-driven mechanics, physics-informed neural networks (PINNs), pressure-dependent materials, short fiber-reinforced polymers (SFRPs)",
author = "Aamir Dean and Naik, {Vinayak B.} and Betim Bahtiri and Elsadig Mahdi and Kumar, {Pavan K.A.V.}",
note = "Publisher Copyright: {\textcopyright} 2025 The Author(s). International Journal for Numerical Methods in Engineering published by John Wiley & Sons Ltd.",
year = "2025",
month = oct,
day = "7",
doi = "10.1002/nme.70144",
language = "English",
volume = "126",
journal = "International Journal for Numerical Methods in Engineering",
issn = "0029-5981",
publisher = "John Wiley and Sons Ltd",
number = "19",

}

Download

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 -