EUVIMEDEUVIMED entdecken
Crossref

Scalar Field Prediction on Meshes Using Interpolated Multiresolution Convolutional Neural Networks

Kevin Ferguson, Andrew Gillman, James Hardin, Levent Burak Kara

Journal of Applied Mechanics · 01.10.2024 · 91 (10)

DOI: 10.1115/1.4065782 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Mechanics, online erschienen am 12.07.2024. Verfasst von Kevin Ferguson und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Air Force Research Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scalar fields, such as stress or temperature fields, are often calculated in shape optimization and design problems in engineering. For complex problems where shapes have varying topology and cannot be parametrized, data-driven scalar field prediction can be faster than traditional finite element methods. However, current data-driven techniques to predict scalar fields are limited to a fixed grid domain, instead of arbitrary mesh structures. In this work, we propose a method to predict scalar fields on arbitrary meshes. It uses a convolutional neural network whose feature maps at multiple resolutions are interpolated to node positions before being fed into a multilayer perceptron to predict solutions to partial differential equations at mesh nodes. The model is trained on finite element von Mises stress fields, and once trained, it can estimate stress values at each node on any input mesh. Two shape datasets are investigated, and the model has strong performance on both, with a median R2 value of 0.91. We also demonstrate the model on a temperature field in a heat conduction problem, where its predictions have a median R2 value of 0.99. Our method provides a potential flexible alternative to finite element analysis in engineering design contexts. Code and datasets are available online.

Förderung

  • Air Force Research Laboratory

Zitieren

APA

Ferguson, K., Gillman, A., Hardin, J., & Kara, L. B. (2024). Scalar Field Prediction on Meshes Using Interpolated Multiresolution Convolutional Neural Networks. Journal of Applied Mechanics, 91(10). https://doi.org/10.1115/1.4065782

Vancouver

Ferguson K, Gillman A, Hardin J, Kara LB. Scalar Field Prediction on Meshes Using Interpolated Multiresolution Convolutional Neural Networks. Journal of Applied Mechanics. 2024;91(10). doi:10.1115/1.4065782

BibTeX
@article{Ferguson2024,
  author = {Ferguson, Kevin and Gillman, Andrew and Hardin, James and Kara, Levent Burak},
  title = {Scalar Field Prediction on Meshes Using Interpolated Multiresolution Convolutional Neural Networks},
  journal = {Journal of Applied Mechanics},
  year = {2024},
  volume = {91},
  number = {10},
  doi = {10.1115/1.4065782}
}
Kostenlos starten →