A data-driven approach using Neural Network for real-time modeling of spot welded patches under impact - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A data-driven approach using Neural Network for real-time modeling of spot welded patches under impact

Résumé

Solving large structural problems with complex localized behaviour is extremely challenging. To address this difficulty, both intrusive as well as non-intrusive multiscale methods have been developed in the past. To reduce the computational time further, we propose the use of Model Order Reduction (MOR) of local scale. This paper presents the MOR technique based on a novel physics-guided architecture (PGA) of neural networks, incorporating physical variables into the architecture. The proposed approach is illustrated in the case of spot-welded plates undergoing large deformation.
Fichier non déposé

Dates et versions

hal-03825839 , version 1 (23-10-2022)

Identifiants

  • HAL Id : hal-03825839 , version 1

Citer

Afsal Pulikkathodi, Elisabeth Longatte-Lacazedieu, Ludovic Chamoin, Juan-Pedro Berro Ramirez, Laurent Rota, et al.. A data-driven approach using Neural Network for real-time modeling of spot welded patches under impact. IUTAM Symposium on Data-driven Mechanics, Oct 2022, Paris, France. ⟨hal-03825839⟩
50 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More