Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation

Computational fluid dynamics (CFD) simulation is an irreplaceable modelling step in many engineering designs, but it is often computationally expensive. Some graph neural network (GNN)-based CFD methods have been proposed. However, the current methods inherit the weakness of traditional numerical si...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-11
Hauptverfasser:	Loh Sher En Jessica, Naheed Anjum Arafat, Lim, Wei Xian, Wai Lee Chan, Adams Wai Kin Kong
Format:	Artikel
Sprache:	eng
Schlagworte:	Centroids Computational fluid dynamics Finite element method Finite volume method Global geometry Graph neural networks Machine learning Mathematical models Message passing Nodes Representations Simulation Simulators
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!