A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problems - Laboratoire de mécanique et technologie
Article Dans Une Revue Computer Methods in Applied Mechanics and Engineering Année : 2024

A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problems

Victor Matray
Faisal Amlani
David Néron
  • Fonction : Auteur
  • PersonId : 1147995

Résumé

This work introduces a new approach for accelerating the numerical analysis of time-domain partial differential equations (PDEs) governing complex physical systems. The methodology is based on a combination of a classical reduced-order modeling (ROM) framework and recently-introduced Graph Neural Networks (GNNs), where the latter is trained on highly heterogeneous databases of varying numerical discretization sizes. The proposed techniques are shown to be particularly suitable for non-parametric geometries, ultimately enabling the treatment of a diverse range of geometries and topologies. Performance studies are presented in an application context related to the design of aircraft seats and their corresponding mechanical responses to shocks, where the main motivation is to reduce the computational burden and enable the rapid design iteration for such problems that entail non-parametric geometries. The methods proposed here are straightforwardly applicable to other scientific or engineering problems requiring a large number of finite element-based numerical simulations, with the potential to significantly enhance efficiency while maintaining reasonable accuracy.
Fichier principal
Vignette du fichier
cmame_vmatray_etal.pdf (5.32 Mo) Télécharger le fichier
Origine Publication financée par une institution
licence

Dates et versions

hal-04585018 , version 1 (28-05-2024)
hal-04585018 , version 2 (29-08-2024)

Licence

Identifiants

Citer

Victor Matray, Faisal Amlani, Frédéric Feyel, David Néron. A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problems. Computer Methods in Applied Mechanics and Engineering, 2024, 430, pp.117243. ⟨10.1016/j.cma.2024.117243⟩. ⟨hal-04585018v2⟩
113 Consultations
94 Téléchargements

Altmetric

Partager

More