arrow
Volume 16, Issue 1
DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress

Tianyi Hu, Jerry Zhijian Yang & Cheng Yuan

Adv. Appl. Math. Mech., 16 (2024), pp. 75-100.

Published online: 2023-12

Export citation
  • Abstract

This paper presents a specific network architecture for approximation of the first Piola-Kirchhoff stress. The neural network enables us to construct the constitutive relation based on both macroscopic observations and atomistic simulation data. In contrast to traditional deep learning models, this architecture is intrinsic symmetric, guarantees the frame-indifference and material-symmetry of stress. Specifically, we build the approximation network inspired by the Cauchy-Born rule and virial stress formula. Several numerical results and theory analyses are presented to illustrate the learnability and effectiveness of our network.

  • AMS Subject Headings

68T07, 65Z05, 41A29

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{AAMM-16-75, author = {Hu , TianyiYang , Jerry Zhijian and Yuan , Cheng}, title = {DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress}, journal = {Advances in Applied Mathematics and Mechanics}, year = {2023}, volume = {16}, number = {1}, pages = {75--100}, abstract = {

This paper presents a specific network architecture for approximation of the first Piola-Kirchhoff stress. The neural network enables us to construct the constitutive relation based on both macroscopic observations and atomistic simulation data. In contrast to traditional deep learning models, this architecture is intrinsic symmetric, guarantees the frame-indifference and material-symmetry of stress. Specifically, we build the approximation network inspired by the Cauchy-Born rule and virial stress formula. Several numerical results and theory analyses are presented to illustrate the learnability and effectiveness of our network.

}, issn = {2075-1354}, doi = {https://doi.org/10.4208/aamm.OA-2022-0159}, url = {http://global-sci.org/intro/article_detail/aamm/22290.html} }
TY - JOUR T1 - DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress AU - Hu , Tianyi AU - Yang , Jerry Zhijian AU - Yuan , Cheng JO - Advances in Applied Mathematics and Mechanics VL - 1 SP - 75 EP - 100 PY - 2023 DA - 2023/12 SN - 16 DO - http://doi.org/10.4208/aamm.OA-2022-0159 UR - https://global-sci.org/intro/article_detail/aamm/22290.html KW - Piola-Kirchhoff stress, deep neural networks, Cauchy-Born rule. AB -

This paper presents a specific network architecture for approximation of the first Piola-Kirchhoff stress. The neural network enables us to construct the constitutive relation based on both macroscopic observations and atomistic simulation data. In contrast to traditional deep learning models, this architecture is intrinsic symmetric, guarantees the frame-indifference and material-symmetry of stress. Specifically, we build the approximation network inspired by the Cauchy-Born rule and virial stress formula. Several numerical results and theory analyses are presented to illustrate the learnability and effectiveness of our network.

Hu , TianyiYang , Jerry Zhijian and Yuan , Cheng. (2023). DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress. Advances in Applied Mathematics and Mechanics. 16 (1). 75-100. doi:10.4208/aamm.OA-2022-0159
Copy to clipboard
The citation has been copied to your clipboard