A machine learning-based viscoelastic–viscoplastic model for epoxy nanocomposites with moisture content

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

Organisationseinheiten

Externe Organisationen

  • Oslomet – Metropoluniversität
  • Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR) Standort Braunschweig
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer116293
FachzeitschriftComputer Methods in Applied Mechanics and Engineering
Jahrgang415
Frühes Online-Datum7 Aug. 2023
PublikationsstatusVeröffentlicht - 1 Okt. 2023

Abstract

In this work, we propose a deep learning (DL)-based constitutive model for investigating the cyclic viscoelastic-viscoplastic-damage behavior of nanoparticle/epoxy nanocomposites with moisture content. For this, a long short-term memory network is trained using a combined framework of a sampling technique and a perturbation method. The training framework, along with the training data generated by an experimentally validated viscoelastic-viscoplastic model, enables the DL model to accurately capture the rate-dependent stress–strain relationship and consistent tangent moduli. In addition, the DL-based constitutive model is implemented into finite element analysis. Finite element simulations are performed to study the effect of load rate and moisture content on the force–displacement response of nanoparticle/epoxy samples. Numerical examples show that the computational efficiency of the DL model depends on the loading condition and is significantly higher than the conventional constitutive model. Furthermore, comparing numerical results and experimental data demonstrates good agreement with different nanoparticle and moisture contents.

ASJC Scopus Sachgebiete

Zitieren

A machine learning-based viscoelastic–viscoplastic model for epoxy nanocomposites with moisture content. / Bahtiri, Betim; Arash, Behrouz; Scheffler, Sven Sigo et al.
in: Computer Methods in Applied Mechanics and Engineering, Jahrgang 415, 116293, 01.10.2023.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Download
@article{7e7d4f5f65d54a4699a93ab462a4f93c,
title = "A machine learning-based viscoelastic–viscoplastic model for epoxy nanocomposites with moisture content",
abstract = "In this work, we propose a deep learning (DL)-based constitutive model for investigating the cyclic viscoelastic-viscoplastic-damage behavior of nanoparticle/epoxy nanocomposites with moisture content. For this, a long short-term memory network is trained using a combined framework of a sampling technique and a perturbation method. The training framework, along with the training data generated by an experimentally validated viscoelastic-viscoplastic model, enables the DL model to accurately capture the rate-dependent stress–strain relationship and consistent tangent moduli. In addition, the DL-based constitutive model is implemented into finite element analysis. Finite element simulations are performed to study the effect of load rate and moisture content on the force–displacement response of nanoparticle/epoxy samples. Numerical examples show that the computational efficiency of the DL model depends on the loading condition and is significantly higher than the conventional constitutive model. Furthermore, comparing numerical results and experimental data demonstrates good agreement with different nanoparticle and moisture contents.",
keywords = "Deep-Learning, Finite element, Nanocomposite, Recurrent neural network, Viscoelasticity-viscoplasticity",
author = "Betim Bahtiri and Behrouz Arash and Scheffler, {Sven Sigo} and Maximilian Jux and Raimund Rolfes",
note = "This work originates from the following research project: “Challenges of industrial application of nanomodified and hybrid material systems in lightweight rotor blade construction” (“HANNAH - Herausforderungen der industriellen Anwendung von nanomodifiziertenund hybriden Werkstoffsystemen im Rotorblattleichtbau”), funded by the Federal Ministry for Economic Affairs and Energy, Germany. The authors wish to express their gratitude for the financial support. ",
year = "2023",
month = oct,
day = "1",
doi = "10.48550/arXiv.2305.08102",
language = "English",
volume = "415",
journal = "Computer Methods in Applied Mechanics and Engineering",
issn = "0045-7825",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - A machine learning-based viscoelastic–viscoplastic model for epoxy nanocomposites with moisture content

AU - Bahtiri, Betim

AU - Arash, Behrouz

AU - Scheffler, Sven Sigo

AU - Jux, Maximilian

AU - Rolfes, Raimund

N1 - This work originates from the following research project: “Challenges of industrial application of nanomodified and hybrid material systems in lightweight rotor blade construction” (“HANNAH - Herausforderungen der industriellen Anwendung von nanomodifiziertenund hybriden Werkstoffsystemen im Rotorblattleichtbau”), funded by the Federal Ministry for Economic Affairs and Energy, Germany. The authors wish to express their gratitude for the financial support.

PY - 2023/10/1

Y1 - 2023/10/1

N2 - In this work, we propose a deep learning (DL)-based constitutive model for investigating the cyclic viscoelastic-viscoplastic-damage behavior of nanoparticle/epoxy nanocomposites with moisture content. For this, a long short-term memory network is trained using a combined framework of a sampling technique and a perturbation method. The training framework, along with the training data generated by an experimentally validated viscoelastic-viscoplastic model, enables the DL model to accurately capture the rate-dependent stress–strain relationship and consistent tangent moduli. In addition, the DL-based constitutive model is implemented into finite element analysis. Finite element simulations are performed to study the effect of load rate and moisture content on the force–displacement response of nanoparticle/epoxy samples. Numerical examples show that the computational efficiency of the DL model depends on the loading condition and is significantly higher than the conventional constitutive model. Furthermore, comparing numerical results and experimental data demonstrates good agreement with different nanoparticle and moisture contents.

AB - In this work, we propose a deep learning (DL)-based constitutive model for investigating the cyclic viscoelastic-viscoplastic-damage behavior of nanoparticle/epoxy nanocomposites with moisture content. For this, a long short-term memory network is trained using a combined framework of a sampling technique and a perturbation method. The training framework, along with the training data generated by an experimentally validated viscoelastic-viscoplastic model, enables the DL model to accurately capture the rate-dependent stress–strain relationship and consistent tangent moduli. In addition, the DL-based constitutive model is implemented into finite element analysis. Finite element simulations are performed to study the effect of load rate and moisture content on the force–displacement response of nanoparticle/epoxy samples. Numerical examples show that the computational efficiency of the DL model depends on the loading condition and is significantly higher than the conventional constitutive model. Furthermore, comparing numerical results and experimental data demonstrates good agreement with different nanoparticle and moisture contents.

KW - Deep-Learning

KW - Finite element

KW - Nanocomposite

KW - Recurrent neural network

KW - Viscoelasticity-viscoplasticity

UR - http://www.scopus.com/inward/record.url?scp=85169621887&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2305.08102

DO - 10.48550/arXiv.2305.08102

M3 - Article

VL - 415

JO - Computer Methods in Applied Mechanics and Engineering

JF - Computer Methods in Applied Mechanics and Engineering

SN - 0045-7825

M1 - 116293

ER -

Von denselben Autoren