An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design
Journal of Computational Design and Engineering · 29.04.2023 · 10 (3) · 1026-1046
DOI: 10.1093/jcde/qwad025 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Design and Engineering, online erschienen am 25.03.2023. Verfasst von Xingyu Fu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MOTIE, DOE.
Abstract (Originalsprache)
In this work, we present a boundary oriented graph embedding (BOGE) approach for the graph neural network to assist in rapid design and digital prototyping. The cantilever beam problem has been solved as an example to validate its potential of providing physical field results and optimized designs using only 10 ms. Providing shortcuts for both boundary elements and local neighbor elements, the BOGE approach can embed unstructured mesh elements into the graph and performs an efficient regression on large-scale triangular-mesh-based finite element analysis (FEA) results, which cannot be realized by other machine-learning-based surrogate methods. It has the potential to serve as a surrogate model for other boundary value problems. Focusing on the cantilever beam problem, the BOGE approach with 3-layer DeepGCN model achieves the regression with mean square error (MSE) of 0.011 706 (2.41% mean absolute percentage error) for stress field prediction and 0.002 735 MSE (with 1.58% elements having error larger than 0.01) for topological optimization. The overall concept of the BOGE approach paves the way for a general and efficient deep-learning-based FEA simulator that will benefit both industry and Computer Aided Design (CAD) design-related areas.
Förderung
- MOTIE
- DOE
Zitieren
APA
Fu, X., Zhou, F., Peddireddy, D., Kang, Z., Jun, M. B., & Aggarwal, V. (2023). An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design. Journal of Computational Design and Engineering, 10(3), 1026-1046. https://doi.org/10.1093/jcde/qwad025
Vancouver
Fu X, Zhou F, Peddireddy D, Kang Z, Jun MB, Aggarwal V. An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design. Journal of Computational Design and Engineering. 2023;10(3):1026-1046. doi:10.1093/jcde/qwad025
BibTeX
@article{Fu2023,
author = {Fu, Xingyu and Zhou, Fengfeng and Peddireddy, Dheeraj and Kang, Zhengyang and Jun, Martin Byung-Guk and Aggarwal, Vaneet},
title = {An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design},
journal = {Journal of Computational Design and Engineering},
year = {2023},
volume = {10},
number = {3},
pages = {1026--1046},
doi = {10.1093/jcde/qwad025}
}
EUVIMED