Enhancing Data-Assimilation in CFD using Graph Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Enhancing Data-Assimilation in CFD using Graph Neural Networks

Résumé

We present a novel machine learning approach for data assimilation applied in fluid mechanics, based on adjoint-optimization augmented by Graph Neural Networks (GNNs) models. We consider as baseline the Reynolds-Averaged Navier-Stokes (RANS) equations, where the unknown is the meanflow and a closure model based on the Reynolds-stress tensor is required for correctly computing the solution. An end-to-end process is cast; first, we train a GNN model for the closure term. Second, the GNN model is introduced in the training process of data assimilation, where the RANS equations act as a physics constraint for a consistent prediction. We obtain our results using direct numerical simulations based on a Finite Element Method (FEM) solver; a twofold interface between the GNN model and the solver allows the GNN's predictions to be incorporated into postprocessing steps of the FEM analysis. The proposed scheme provides an excellent reconstruction of the meanflow without any features selection; preliminary results show promising generalization properties over unseen flow configurations.
Fichier principal
Vignette du fichier
2311.18027.pdf (552.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04319697 , version 1 (05-12-2023)

Identifiants

Citer

Michele Quattromini, Michele Alessandro Bucci, Stefania Cherubini, Onofrio Semeraro. Enhancing Data-Assimilation in CFD using Graph Neural Networks. 37th Conference on Neural Information Processing Systems (Neurips 2023), Dec 2023, La Nouvelle Orléans (LA), United States. ⟨hal-04319697⟩
111 Consultations
44 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More