U-net architectures for fast prediction in fluid mechanics - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

U-net architectures for fast prediction in fluid mechanics

Junfeng Chen
Elie Hachem

Résumé

Machine learning is a popular tool that is being applied to many domains, from computer vision to natural language processing. It is not long ago that its use was extended to physics, but its capabilities remain to be accurately contoured. In this paper, we are interested in the prediction of 2D velocity and pressure fields around arbitrary shapes in laminar flows using supervised neural networks. To this end, a dataset composed of random shapes is built using Bézier curves, each shape being labeled with its pressure and velocity fields by solving Navier-Stokes equations using a CFD solver. Then, several U-net architectures are trained on the latter dataset, and their predictive efficiency is assessed on unseen shapes, using ad hoc error functions.
Fichier principal
Vignette du fichier
nn_flow_2d.pdf (2.94 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02401465 , version 1 (10-12-2019)

Identifiants

  • HAL Id : hal-02401465 , version 1

Citer

Junfeng Chen, Jonathan Viquerat, Elie Hachem. U-net architectures for fast prediction in fluid mechanics. 2019. ⟨hal-02401465⟩
380 Consultations
643 Téléchargements

Partager

Gmail Facebook X LinkedIn More