Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees) - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees)

Résumé

In this paper, we are interested in the acceleration of numerical simulations. We focus on a hypersonic planetary reentry problem whose simulation involves coupling fluid dynamics and chemical reactions. Simulating chemical reactions takes most of the computational time but, on the other hand, cannot be avoided to obtain accurate predictions. We face a trade-off between cost-efficiency and accuracy: the simulation code has to be sufficiently efficient to be used in an operational context but accurate enough to predict the phenomenon faithfully. To tackle this trade-off, we design a hybrid simulation code coupling a traditional fluid dynamic solver with a neural network approximating the chemical reactions. We rely on their power in terms of accuracy and dimension reduction when applied in a big data context and on their efficiency stemming from their matrixvector structure to achieve important acceleration factors (×10 to ×18.6). This paper aims to explain how we design such cost-effective hybrid simulation codes in practice. Above all, we describe methodologies to ensure accuracy guarantees, allowing us to go beyond traditional surrogate modeling and to use these codes as references.
Fichier principal
Vignette du fichier
main.pdf (1.79 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04323551 , version 1 (27-09-2022)
hal-04323551 , version 2 (05-12-2023)

Identifiants

  • HAL Id : hal-04323551 , version 1

Citer

Paul Novello, Gaël Poëtte, David Lugato, Simon Peluchon, Pietro Marco Congedo. Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees). 2022. ⟨hal-04323551v1⟩
100 Consultations
79 Téléchargements

Partager

Gmail Facebook X LinkedIn More