Skip to Main content Skip to Navigation
Conference papers

Deep Surrogate for Direct Time Fluid Dynamics

Abstract : The ubiquity of fluids in the physical world explains the need to accurately simulate their dynamics for many scientific and engineering applications. Traditionally, well established but resource intensive CFD solvers provide such simulations. The recent years have seen a surge of deep learning surrogate models substituting these solvers to alleviate the simulation process. Some approaches to build data-driven surrogates mimic the solver iterative process. They infer the next state of the fluid given its previous one. Others directly infer the state from time input. Approaches also differ in their management of the spatial information. Graph Neural Networks (GNN) can address the specificity of the irregular meshes commonly used in CFD simulations. In this article, we present our ongoing work to design a novel direct time GNN architecture for irregular meshes. It consists of a succession of graphs of increasing size connected by spline convolutions. We test our architecture on the Von Kármán's vortex street benchmark. It achieves small generalization errors while mitigating error accumulation along the trajectory.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03451432
Contributor : Lucas Meyer Connect in order to contact the contributor
Submitted on : Friday, November 26, 2021 - 2:30:42 PM
Last modification on : Saturday, December 18, 2021 - 3:59:24 AM

File

Deep_Surrogate_for_Direct_Time...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03451432, version 1

Citation

Lucas Meyer, Louen Pottier, Alejandro Ribes, Bruno Raffin. Deep Surrogate for Direct Time Fluid Dynamics. NeurIPS 2021 - Thirty-fifth Workshop on Machine Learning and the Physical Sciences, Dec 2021, Vancouver, Canada. pp.1-7. ⟨hal-03451432v1⟩

Share

Metrics

Les métriques sont temporairement indisponibles