Parametric deep energy approach for elasticity accounting for strain gradient effects

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Vien Minh Nguyen-Thanh
  • Cosmin Anitescu
  • Naif Alajlan
  • Timon Rabczuk
  • Xiaoying Zhuang

Research Organisations

External Research Organisations

  • Bauhaus-Universität Weimar
  • King Saud University
View graph of relations

Details

Original languageEnglish
Article number114096
JournalComputer Methods in Applied Mechanics and Engineering
Volume386
Early online date23 Aug 2021
Publication statusPublished - 1 Dec 2021

Abstract

In this work, we present a Parametric Deep Energy Method (P-DEM) for elasticity problems accounting for strain gradient effects. The approach is based on physics-informed neural networks (PINNs) for the solution of the underlying potential energy. Therefore, a cost function related to the potential energy is subsequently minimized. P-DEM does not need any classical discretization and requires only a definition of the potential energy, which simplifies the implementation. Instead of training the model in the physical space, we define a parametric/reference space similar to isoparametric finite elements, which is in our example a unit square. The inputs are naturally normalized preventing the vanishing gradient problem and leading to much faster convergence compared to the original DEM. Forward–backward mapping is established by means of NURBS basis functions. Another advantage of this approach is that Gauss quadrature can be employed to approximate the total potential energy, which is the loss function calculated in the parametric domain. Backpropagation available in PyTorch with automatic differentiation is performed to calculate the gradients of the loss function with respect to the weights and biases. Once the network is trained, a numerical solution can be obtained in the reference domain and then is mapped back to the physical domain. The performance of the method is demonstrated through various numerical benchmark problems in elasticity and compared to analytical solutions. We also consider strain gradient elasticity, which poses challenges to conventional finite elements due to the requirement for C1 continuity.

Keywords

    Deep energy method, Elasticity, Neural networks (NN), Partial differential equations (PDEs), Physics-informed neural networks (PINNs), Strain gradient elasticity

ASJC Scopus subject areas

Cite this

Parametric deep energy approach for elasticity accounting for strain gradient effects. / Nguyen-Thanh, Vien Minh; Anitescu, Cosmin; Alajlan, Naif et al.
In: Computer Methods in Applied Mechanics and Engineering, Vol. 386, 114096, 01.12.2021.

Research output: Contribution to journalArticleResearchpeer review

Nguyen-Thanh VM, Anitescu C, Alajlan N, Rabczuk T, Zhuang X. Parametric deep energy approach for elasticity accounting for strain gradient effects. Computer Methods in Applied Mechanics and Engineering. 2021 Dec 1;386:114096. Epub 2021 Aug 23. doi: 10.1016/j.cma.2021.114096
Nguyen-Thanh, Vien Minh ; Anitescu, Cosmin ; Alajlan, Naif et al. / Parametric deep energy approach for elasticity accounting for strain gradient effects. In: Computer Methods in Applied Mechanics and Engineering. 2021 ; Vol. 386.
Download
@article{32adfd5392fa46bbbc969879f4343c1c,
title = "Parametric deep energy approach for elasticity accounting for strain gradient effects",
abstract = "In this work, we present a Parametric Deep Energy Method (P-DEM) for elasticity problems accounting for strain gradient effects. The approach is based on physics-informed neural networks (PINNs) for the solution of the underlying potential energy. Therefore, a cost function related to the potential energy is subsequently minimized. P-DEM does not need any classical discretization and requires only a definition of the potential energy, which simplifies the implementation. Instead of training the model in the physical space, we define a parametric/reference space similar to isoparametric finite elements, which is in our example a unit square. The inputs are naturally normalized preventing the vanishing gradient problem and leading to much faster convergence compared to the original DEM. Forward–backward mapping is established by means of NURBS basis functions. Another advantage of this approach is that Gauss quadrature can be employed to approximate the total potential energy, which is the loss function calculated in the parametric domain. Backpropagation available in PyTorch with automatic differentiation is performed to calculate the gradients of the loss function with respect to the weights and biases. Once the network is trained, a numerical solution can be obtained in the reference domain and then is mapped back to the physical domain. The performance of the method is demonstrated through various numerical benchmark problems in elasticity and compared to analytical solutions. We also consider strain gradient elasticity, which poses challenges to conventional finite elements due to the requirement for C1 continuity.",
keywords = "Deep energy method, Elasticity, Neural networks (NN), Partial differential equations (PDEs), Physics-informed neural networks (PINNs), Strain gradient elasticity",
author = "Nguyen-Thanh, {Vien Minh} and Cosmin Anitescu and Naif Alajlan and Timon Rabczuk and Xiaoying Zhuang",
note = "Funding Information: The authors extend their appreciation to the Distinguished Scientist Fellowship Program (DSFP) at King Saud University, Saudi Arabia for funding this work. ",
year = "2021",
month = dec,
day = "1",
doi = "10.1016/j.cma.2021.114096",
language = "English",
volume = "386",
journal = "Computer Methods in Applied Mechanics and Engineering",
issn = "0045-7825",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Parametric deep energy approach for elasticity accounting for strain gradient effects

AU - Nguyen-Thanh, Vien Minh

AU - Anitescu, Cosmin

AU - Alajlan, Naif

AU - Rabczuk, Timon

AU - Zhuang, Xiaoying

N1 - Funding Information: The authors extend their appreciation to the Distinguished Scientist Fellowship Program (DSFP) at King Saud University, Saudi Arabia for funding this work.

PY - 2021/12/1

Y1 - 2021/12/1

N2 - In this work, we present a Parametric Deep Energy Method (P-DEM) for elasticity problems accounting for strain gradient effects. The approach is based on physics-informed neural networks (PINNs) for the solution of the underlying potential energy. Therefore, a cost function related to the potential energy is subsequently minimized. P-DEM does not need any classical discretization and requires only a definition of the potential energy, which simplifies the implementation. Instead of training the model in the physical space, we define a parametric/reference space similar to isoparametric finite elements, which is in our example a unit square. The inputs are naturally normalized preventing the vanishing gradient problem and leading to much faster convergence compared to the original DEM. Forward–backward mapping is established by means of NURBS basis functions. Another advantage of this approach is that Gauss quadrature can be employed to approximate the total potential energy, which is the loss function calculated in the parametric domain. Backpropagation available in PyTorch with automatic differentiation is performed to calculate the gradients of the loss function with respect to the weights and biases. Once the network is trained, a numerical solution can be obtained in the reference domain and then is mapped back to the physical domain. The performance of the method is demonstrated through various numerical benchmark problems in elasticity and compared to analytical solutions. We also consider strain gradient elasticity, which poses challenges to conventional finite elements due to the requirement for C1 continuity.

AB - In this work, we present a Parametric Deep Energy Method (P-DEM) for elasticity problems accounting for strain gradient effects. The approach is based on physics-informed neural networks (PINNs) for the solution of the underlying potential energy. Therefore, a cost function related to the potential energy is subsequently minimized. P-DEM does not need any classical discretization and requires only a definition of the potential energy, which simplifies the implementation. Instead of training the model in the physical space, we define a parametric/reference space similar to isoparametric finite elements, which is in our example a unit square. The inputs are naturally normalized preventing the vanishing gradient problem and leading to much faster convergence compared to the original DEM. Forward–backward mapping is established by means of NURBS basis functions. Another advantage of this approach is that Gauss quadrature can be employed to approximate the total potential energy, which is the loss function calculated in the parametric domain. Backpropagation available in PyTorch with automatic differentiation is performed to calculate the gradients of the loss function with respect to the weights and biases. Once the network is trained, a numerical solution can be obtained in the reference domain and then is mapped back to the physical domain. The performance of the method is demonstrated through various numerical benchmark problems in elasticity and compared to analytical solutions. We also consider strain gradient elasticity, which poses challenges to conventional finite elements due to the requirement for C1 continuity.

KW - Deep energy method

KW - Elasticity

KW - Neural networks (NN)

KW - Partial differential equations (PDEs)

KW - Physics-informed neural networks (PINNs)

KW - Strain gradient elasticity

UR - http://www.scopus.com/inward/record.url?scp=85113281461&partnerID=8YFLogxK

U2 - 10.1016/j.cma.2021.114096

DO - 10.1016/j.cma.2021.114096

M3 - Article

AN - SCOPUS:85113281461

VL - 386

JO - Computer Methods in Applied Mechanics and Engineering

JF - Computer Methods in Applied Mechanics and Engineering

SN - 0045-7825

M1 - 114096

ER -