EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method

Junyan He, Diab Abueidda, Seid Koric, Iwona Jasiuk

International Journal for Numerical Methods in Engineering · 28.02.2023 · 124 (4) · 864-879

DOI: 10.1002/nme.7146 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal for Numerical Methods in Engineering, online erschienen am 30.10.2022. Verfasst von Junyan He und 3 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A graph convolutional network (GCN) is employed in the deep energy method (DEM) model to solve the momentum balance equation in three‐dimensional space for the deformation of linear elastic and hyperelastic materials due to its ability to handle irregular domains over the traditional DEM method based on a multilayer perceptron (MLP) network. The method's accuracy and solution time are compared to the DEM model based on a MLP network. We demonstrate that the GCN‐based model delivers similar accuracy while having a shorter run time through numerical examples. Two different spatial gradient computation techniques, one based on automatic differentiation (AD) and the other based on shape function (SF) gradients, are also accessed. We provide a simple example to demonstrate the strain localization instability associated with the AD‐based gradient computation and show that the instability exists in more general cases by four numerical examples. The SF‐based gradient computation is shown to be more robust and delivers an accurate solution even at severe deformations. Therefore, the combination of the GCN‐based DEM model and SF‐based gradient computation is potentially a promising candidate for solving problems involving severe material and geometric nonlinearities.

Zitieren

APA

He, J., Abueidda, D., Koric, S., & Jasiuk, I. (2023). On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method. International Journal for Numerical Methods in Engineering, 124(4), 864-879. https://doi.org/10.1002/nme.7146

Vancouver

He J, Abueidda D, Koric S, Jasiuk I. On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method. International Journal for Numerical Methods in Engineering. 2023;124(4):864-879. doi:10.1002/nme.7146

BibTeX
@article{He2023,
  author = {He, Junyan and Abueidda, Diab and Koric, Seid and Jasiuk, Iwona},
  title = {On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method},
  journal = {International Journal for Numerical Methods in Engineering},
  year = {2023},
  volume = {124},
  number = {4},
  pages = {864--879},
  doi = {10.1002/nme.7146}
}
Kostenlos starten →