Conférence scientifique dans des universités ou centres de recherche (Conférences scientifiques dans des universités ou centres de recherche)
A Recurrent Neural Network-based Surrogate Model for History-Dependent Multi-scale Simulations
Wu, Ling; Noels, Ludovic
2021
 

Documents


Texte intégral
2021_Stuttgart_RNN.pdf
Postprint Auteur (4.84 MB)
Télécharger

Tous les documents dans ORBi sont protégés par une licence d'utilisation.

Envoyer vers



Détails



Mots-clés :
Reccurent Reural Network; Machine Learning; Multi-scale
Résumé :
[en] Homogenization-based multi-scale analyses are widely used to account for the effect of material heterogeneity at a structural material point. Among the existing different homogenization methods, computational homogenization solves the meso-scale heterogeneous problems using a full field discretization of the micro-structure. When embedded in a multi-scale analyses, computational homogenization results in the so-called FE2 method, which is an accurate methodology but which yields prohibitive computational time. A more efficient approach is to conduct pre-off-line finite element simulations on the meso-scale problem in order to build a surrogate model by means of constructing mapping functions. Once this so-called training step is completed, the surrogate model can be used as the constitutive law of a single-scale simulation, leading to highly efficient simulations. Artificial neural networks (NNWs) offer the possibility to build such a mapping. However, one difficulty arises for history-dependent material behaviours, such as elasto-plasticity, since state variables are needed to account for the loading history. This difficulty can be solved by considering a Recurrent Neural Network (RNN), which uses sequential information. In [1] a RNN was designed using a Gated Recurrent Unit (GRU). In order to achieve accuracy under multi-dimensional non-proportional loading conditions, the sequential training data were obtained from finite element simulations on an elastoplastic composite RVE subjected to random loading paths. The RNN predictions were found to be in agreement with the finite elements simulations.
Centre de recherche :
A&M - Aérospatiale et Mécanique - ULiège
Disciplines :
Science des matériaux & ingénierie
Ingénierie mécanique
Auteur, co-auteur :
Wu, Ling ;  Université de Liège - ULiège > Département d'aérospatiale et mécanique > Computational & Multiscale Mechanics of Materials (CM3)
Noels, Ludovic  ;  Université de Liège - ULiège > Département d'aérospatiale et mécanique > Computational & Multiscale Mechanics of Materials (CM3)
Langue du document :
Anglais
Titre :
A Recurrent Neural Network-based Surrogate Model for History-Dependent Multi-scale Simulations
Date de publication/diffusion :
04 novembre 2021
Nom de la manifestation :
SimTech Seminar on Model Reduction and Data Techniques for Surrogate Modelling
Lieu de la manifestation :
Stuttgart, Allemagne
Date de la manifestation :
4 November 2021
Projet européen :
H2020 - 862015 - MOAMMM - Multi-scale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials
Intitulé du projet de recherche :
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 862015 for the project “Multi-scale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials (MOAMMM)” of the H2020-EU.1.2.1. - FET Open Programme.
Organisme subsidiant :
UE - Union Européenne [BE]
CE - Commission Européenne [BE]
Disponible sur ORBi :
depuis le 04 novembre 2021

Statistiques


Nombre de vues
128 (dont 7 ULiège)
Nombre de téléchargements
88 (dont 4 ULiège)

Bibliographie


Publications similaires



Contacter ORBi