Improving the Vector Basis Neural Network for RANS Equations Using Separate Trainings

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Oberto, Davide
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912047181070336
author Oberto, Davide
author_facet Oberto, Davide
contents We present a new data-driven turbulence model for Reynolds-averaged Navier-Stokes equations called $ν_t$-Vector Basis Neural Network. This new model, grounded on the already existing Vector Basis Neural Network, predicts separately the turbulent viscosity $ν_t$ and the contribution of the Reynolds force vector that is not already accounted in $ν_t$. Numerical experiments on the flow in a Square Duct show the better accuracy of the new model compared to the reference one.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17721
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the Vector Basis Neural Network for RANS Equations Using Separate Trainings
Oberto, Davide
Fluid Dynamics
Numerical Analysis
We present a new data-driven turbulence model for Reynolds-averaged Navier-Stokes equations called $ν_t$-Vector Basis Neural Network. This new model, grounded on the already existing Vector Basis Neural Network, predicts separately the turbulent viscosity $ν_t$ and the contribution of the Reynolds force vector that is not already accounted in $ν_t$. Numerical experiments on the flow in a Square Duct show the better accuracy of the new model compared to the reference one.
title Improving the Vector Basis Neural Network for RANS Equations Using Separate Trainings
topic Fluid Dynamics
Numerical Analysis
url https://arxiv.org/abs/2409.17721