Data driven estimation of fluid flows: ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
Data driven estimation of fluid flows: long-term prediction of velocity fields using machine learning
Author(s) :
Dubois, Pierre [Auteur]
DAAA, ONERA [Lille]
Gomez, thomas [Auteur]
Laboratoire de Mécanique des Fluides de Lille - Kampé de Fériet [LMFL]
Planckaert, Laurent [Auteur]
DAAA, ONERA [Lille]
Perret, Laurent [Auteur]
Laboratoire de recherche en Hydrodynamique, Énergétique et Environnement Atmosphérique [LHEEA]
DAAA, ONERA [Lille]
Gomez, thomas [Auteur]
Laboratoire de Mécanique des Fluides de Lille - Kampé de Fériet [LMFL]
Planckaert, Laurent [Auteur]
DAAA, ONERA [Lille]
Perret, Laurent [Auteur]
Laboratoire de recherche en Hydrodynamique, Énergétique et Environnement Atmosphérique [LHEEA]
Conference title :
AERO 2020+1 - 55th 3AF International Conference on Applied Conference
City :
Poiters (virtuel)
Country :
France
Start date of the conference :
2021-04-12
HAL domain(s) :
Sciences de l'ingénieur [physics]
Physique [physics]
Mathématiques [math]
Informatique [cs]
Physique [physics]
Mathématiques [math]
Informatique [cs]
English abstract : [en]
This paper gives a framework for the data-driven estimation of an unsteady fluid flow field. The strategy combines machine learning tools for the reduction, the reconstruction and the prediction of the considered system. ...
Show more >This paper gives a framework for the data-driven estimation of an unsteady fluid flow field. The strategy combines machine learning tools for the reduction, the reconstruction and the prediction of the considered system. The reduction is performed by linear autoencoding while support vector regression and dynamical mode decomposition are respectively used as reconstruction and prediction models. Starting from an initial condition, reconstructions are frequently assimilated to update erroneous predictions. The procedure is tested on four cases with increasing complexity and robustness is assessed through training and testing errors. Quantitative results suggest that reconstruction and prediction models purely learnt from data can be used for effective data assimilation, hence enabling the long-term prediction of even complex fluid flows.Show less >
Show more >This paper gives a framework for the data-driven estimation of an unsteady fluid flow field. The strategy combines machine learning tools for the reduction, the reconstruction and the prediction of the considered system. The reduction is performed by linear autoencoding while support vector regression and dynamical mode decomposition are respectively used as reconstruction and prediction models. Starting from an initial condition, reconstructions are frequently assimilated to update erroneous predictions. The procedure is tested on four cases with increasing complexity and robustness is assessed through training and testing errors. Quantitative results suggest that reconstruction and prediction models purely learnt from data can be used for effective data assimilation, hence enabling the long-term prediction of even complex fluid flows.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Source :
Files
- https://hal.archives-ouvertes.fr/hal-03206337/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/file/DAAA20123.1614595267.pdf
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/file/DAAA20123.1614595267.pdf
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03206337/document
- Open access
- Access the document
- document
- Open access
- Access the document
- DAAA20123.1614595267.pdf
- Open access
- Access the document