Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport

Nowadays, numerical simulation, such as computational fluid dynamics (CFD), has become an essential tool for scientific investigation and analysis of complex systems in engineering allowing high-fidelity Navier-Stokes resolution for realistic turbulent flows which cannot be solved analytically. Howe...

Full description

Saved in:
Bibliographic Details
Main Authors: Torregrosa Sergio, Champaney Victor, Ammar Amine, Herbert Vincent, Chinesta Francisco
Format: Article
Language:English
Published: EDP Sciences 2024-01-01
Series:Mechanics & Industry
Subjects:
Online Access:https://www.mechanics-industry.org/articles/meca/full_html/2024/01/mi230075/mi230075.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846139373553188864
author Torregrosa Sergio
Champaney Victor
Ammar Amine
Herbert Vincent
Chinesta Francisco
author_facet Torregrosa Sergio
Champaney Victor
Ammar Amine
Herbert Vincent
Chinesta Francisco
author_sort Torregrosa Sergio
collection DOAJ
description Nowadays, numerical simulation, such as computational fluid dynamics (CFD), has become an essential tool for scientific investigation and analysis of complex systems in engineering allowing high-fidelity Navier-Stokes resolution for realistic turbulent flows which cannot be solved analytically. However, although all the studies and development conducted to improve its accuracy and computational cost, CFD remains either not to be trusted completely or too expensive to run. Moreover, with the present data-based revolution, artificial intelligence and machine learning (ML) are acquiring indisputable importance in every field leading to data, theory, and simulation working together for computational efficiency and to increase accuracy. Among the very different applications of data in CFD, here we focus on data-driven correction of coarse simulations based on the knowledge of the error gap between coarse and high-fidelity simulations, also known as the "hybrid twin" rationale. On the one hand, coarse numerical simulations are computed as fast and cheap data, assuming their inherent error. On the other hand, some high-fidelity (HF) data is gathered to train the ML correction model which fills the coarse-HF gap. However, modeling this ignorance gap might be difficult in some fields such as fluids dynamics, where a regression over the localized solutions can lead to non physical interpolated solutions. Therefore, the Optimal Transport theory is followed, which provides a mathematical framework to measure distances between general objects. Such an OT-based "hybrid twin" methodology was already proposed in a previous article by the authors. However, even if in this article the methodology remains the same, the problem solved is conceptually different since we correct no longer the gap between experimental and numerical data but between coarse and high-fidelity simulations.
format Article
id doaj-art-dd3312b4267d44ff88b0dcb2659ed0b8
institution Kabale University
issn 2257-7777
2257-7750
language English
publishDate 2024-01-01
publisher EDP Sciences
record_format Article
series Mechanics & Industry
spelling doaj-art-dd3312b4267d44ff88b0dcb2659ed0b82024-12-06T10:43:31ZengEDP SciencesMechanics & Industry2257-77772257-77502024-01-01253110.1051/meca/2024023mi230075Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transportTorregrosa Sergio0https://orcid.org/0000-0002-9096-8159Champaney Victor1Ammar Amine2Herbert Vincent3Chinesta Francisco4PIMM, Arts et Métiers Institute of TechnologyESI Chair, PIMM, Arts et Métiers Institute of TechnologyESI Chair, LAMPA, Arts et Métiers Institute of TechnologySTELLANTISESI Chair, PIMM, Arts et Métiers Institute of TechnologyNowadays, numerical simulation, such as computational fluid dynamics (CFD), has become an essential tool for scientific investigation and analysis of complex systems in engineering allowing high-fidelity Navier-Stokes resolution for realistic turbulent flows which cannot be solved analytically. However, although all the studies and development conducted to improve its accuracy and computational cost, CFD remains either not to be trusted completely or too expensive to run. Moreover, with the present data-based revolution, artificial intelligence and machine learning (ML) are acquiring indisputable importance in every field leading to data, theory, and simulation working together for computational efficiency and to increase accuracy. Among the very different applications of data in CFD, here we focus on data-driven correction of coarse simulations based on the knowledge of the error gap between coarse and high-fidelity simulations, also known as the "hybrid twin" rationale. On the one hand, coarse numerical simulations are computed as fast and cheap data, assuming their inherent error. On the other hand, some high-fidelity (HF) data is gathered to train the ML correction model which fills the coarse-HF gap. However, modeling this ignorance gap might be difficult in some fields such as fluids dynamics, where a regression over the localized solutions can lead to non physical interpolated solutions. Therefore, the Optimal Transport theory is followed, which provides a mathematical framework to measure distances between general objects. Such an OT-based "hybrid twin" methodology was already proposed in a previous article by the authors. However, even if in this article the methodology remains the same, the problem solved is conceptually different since we correct no longer the gap between experimental and numerical data but between coarse and high-fidelity simulations.https://www.mechanics-industry.org/articles/meca/full_html/2024/01/mi230075/mi230075.htmlhybrid twinartificial intelligenceoptimal transportcomputational fluid dynamics
spellingShingle Torregrosa Sergio
Champaney Victor
Ammar Amine
Herbert Vincent
Chinesta Francisco
Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
Mechanics & Industry
hybrid twin
artificial intelligence
optimal transport
computational fluid dynamics
title Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
title_full Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
title_fullStr Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
title_full_unstemmed Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
title_short Predicting high-fidelity data from coarse-mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
title_sort predicting high fidelity data from coarse mesh computational fluid dynamics corrected using hybrid twins based on optimal transport
topic hybrid twin
artificial intelligence
optimal transport
computational fluid dynamics
url https://www.mechanics-industry.org/articles/meca/full_html/2024/01/mi230075/mi230075.html
work_keys_str_mv AT torregrosasergio predictinghighfidelitydatafromcoarsemeshcomputationalfluiddynamicscorrectedusinghybridtwinsbasedonoptimaltransport
AT champaneyvictor predictinghighfidelitydatafromcoarsemeshcomputationalfluiddynamicscorrectedusinghybridtwinsbasedonoptimaltransport
AT ammaramine predictinghighfidelitydatafromcoarsemeshcomputationalfluiddynamicscorrectedusinghybridtwinsbasedonoptimaltransport
AT herbertvincent predictinghighfidelitydatafromcoarsemeshcomputationalfluiddynamicscorrectedusinghybridtwinsbasedonoptimaltransport
AT chinestafrancisco predictinghighfidelitydatafromcoarsemeshcomputationalfluiddynamicscorrectedusinghybridtwinsbasedonoptimaltransport