A supervised neural network for drag prediction of arbitrary 2D shapes in laminar flows at low Reynolds number

DOI10.1016/j.compfluid.2020.104645OpenAlexW3040821245MaRDI QIDQ2019945

Jonathan Viquerat, Elie Hachem

Publication date: 22 April 2021

Published in: Computers and Fluids (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1907.05090

zbMATH Keywords

neural networkscomputational fluid dynamicsmachine learningconvolutional networksimmersed method

Mathematics Subject Classification ID

Fluid mechanics (76-XX)

Related Items (3)

A deep learning approach for the transonic flow field predictions around airfoils ⋮ Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates ⋮ Bridging the gap: machine learning to resolve improperly modeled dynamics

Uses Software

• Python
• Keras

Cites Work

• Anisotropic meshing with time-stepping control for unsteady convection-dominated problems
• Immersed stress method for fluid-structure interaction using anisotropic mesh adaptation
• Using a signed distance function for the simulation of metal forming processes: Formulation of the contact condition and mesh adaptation. From a Lagrangian approach to an Eulerian approach
• A mass‐conserving Level‐Set method for modelling of multi‐phase flows
• A numerical model to track two‐fluid interfaces based on a stabilized finite element method and the level set technique
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

This page was built for publication: A supervised neural network for drag prediction of arbitrary 2D shapes in laminar flows at low Reynolds number