Saved in:
Bibliographic Details
Main Authors: Mitra, Peetak, Haghshenas, Majid, Santo, Niccolo Dal, Daly, Conor, Schmidt, David P.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.00114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911794076844032
author Mitra, Peetak
Haghshenas, Majid
Santo, Niccolo Dal
Daly, Conor
Schmidt, David P.
author_facet Mitra, Peetak
Haghshenas, Majid
Santo, Niccolo Dal
Daly, Conor
Schmidt, David P.
contents High-fidelity computational fluid dynamics (CFD) simulations for design space explorations can be exceedingly expensive due to the cost associated with resolving the finer scales. This computational cost/accuracy trade-off is a major challenge for modern CFD simulations. In the present study, we propose a method that uses a trained machine learning model that has learned to predict the discretization error as a function of largescale flow features to inversely estimate the degree of lost information due to mesh coarsening. This information is then added back to the low-resolution solution during runtime, thereby enhancing the quality of the under-resolved coarse mesh simulation. The use of a coarser mesh produces a non-linear benefit in speed while the cost of inferring and correcting for the lost information has a linear cost. We demonstrate the numerical stability of a problem of engineering interest, a 3D turbulent channel flow. In addition to this demonstration, we further show the potential for speedup without sacrificing solution accuracy using this method, thereby making the cost/accuracy trade-off of CFD more favorable.
format Preprint
id arxiv_https___arxiv_org_abs_2305_00114
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving CFD simulations by local machine-learned correction
Mitra, Peetak
Haghshenas, Majid
Santo, Niccolo Dal
Daly, Conor
Schmidt, David P.
Fluid Dynamics
Machine Learning
High-fidelity computational fluid dynamics (CFD) simulations for design space explorations can be exceedingly expensive due to the cost associated with resolving the finer scales. This computational cost/accuracy trade-off is a major challenge for modern CFD simulations. In the present study, we propose a method that uses a trained machine learning model that has learned to predict the discretization error as a function of largescale flow features to inversely estimate the degree of lost information due to mesh coarsening. This information is then added back to the low-resolution solution during runtime, thereby enhancing the quality of the under-resolved coarse mesh simulation. The use of a coarser mesh produces a non-linear benefit in speed while the cost of inferring and correcting for the lost information has a linear cost. We demonstrate the numerical stability of a problem of engineering interest, a 3D turbulent channel flow. In addition to this demonstration, we further show the potential for speedup without sacrificing solution accuracy using this method, thereby making the cost/accuracy trade-off of CFD more favorable.
title Improving CFD simulations by local machine-learned correction
topic Fluid Dynamics
Machine Learning
url https://arxiv.org/abs/2305.00114