U-net architectures for fast prediction of incompressible laminar flows

Abstract : 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 Bezier 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02428694
Contributor : Elie Hachem <>
Submitted on : Monday, January 6, 2020 - 11:01:31 AM
Last modification on : Thursday, January 16, 2020 - 1:11:14 AM

Links full text

Identifiers

Citation

Junfeng Chen, Jonathan Viquerat, Elie Hachem. U-net architectures for fast prediction of incompressible laminar flows. 2020. ⟨hal-02428694⟩

Share

Metrics

Record views

18