Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal for Numerical Methods in Engineering Année : 2021

Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models

Résumé

In this article, an investigation was carried out to verify hybrid models capabilities to predict the effective properties of heterogeneous materials. A hybrid model (Formula presented.) is developed by combining artificial neural networks and micromechanical modeling. The homogenization approach used in this study is mainly based on Eshelby's inclusion problem. The (Formula presented.) model, once trained on an Eshelby's tensors database, showed an excellent predictive capabilities of the effective mechanical behavior and local stresses in heterogeneous materials. The obtained results with (Formula presented.) are compared to numerical estimations which are often costly in terms of computational time. The results presented in this work show that the developed hybrid model can provide a significant computational time saving by a factor up to 2000 for (Formula presented.) phases while maintaining its accuracy and reliability.
Fichier non déposé

Dates et versions

hal-03498851 , version 1 (21-12-2021)

Identifiants

Citer

Aymen Danoun, Etienne Pruliére, Yves Chemisky. Hybrid approach to predict the effective properties of heterogeneous materials using artificial neural networks and micromechanical models. International Journal for Numerical Methods in Engineering, 2021, ⟨10.1002/nme.6877⟩. ⟨hal-03498851⟩
57 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More