• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux (LEM3)
  • View Item
  • Home
  • Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux (LEM3)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Deep homogenization networks for elastic heterogeneous materials with two- and three-dimensional periodicity

Article dans une revue avec comité de lecture
Author
WU, Jiajun
86289 Laboratoire Procédés et Ingénierie en Mécanique et Matériaux [PIMM]
JIANG, Jindong
107452 Laboratoire de Conception Fabrication Commande [LCFC]
CHEN, Qiang
178323 Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux [LEM3]
301676 Xi'an Jiaotong University [Xjtu]
ccCHATZIGEORGIOU, George
178323 Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux [LEM3]
MERAGHNI, Fodil
178323 Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux [LEM3]

URI
http://hdl.handle.net/10985/24281
DOI
10.1016/j.ijsolstr.2023.112521
Date
2023-12
Journal
International Journal of Solids and Structures

Abstract

We present a deep learning framework that leverages computational homogenization expertise to predict the local stress field and homogenized moduli of heterogeneous materials with two- and three-dimensional periodicity, which is named physics-informed Deep Homogenization Networks (DHN). To this end, the displacement field of a repeating unit cell is expressed as two-scale expansion in terms of averaging and fluctuating contributions dependent on the global and local coordinates, respectively, under arbitrary multi-axial loading conditions. The latter is regarded as a mesh-free periodic domain estimated using fully connected neural network layers by minimizing residuals of Navier's displacement equations of anisotropic microstructured materials for specified macroscopic strains with the help of automatic differentiation. Enabled by the novel use of a periodic layer, the boundary conditions are encoded directly in the DHN architecture which ensures exact satisfaction of the periodicity conditions of displacements and tractions without introducing additional penalty terms. To verify the proposed model, the local field variables and homogenized moduli were examined for various composites against the finite-element technique. We also demonstrate the feasibility of the proposed framework for simulating unit cells with locally irregular fibers via transfer learning and find a significant enhancement in the accuracy of stress field recovery during neural network retraining.

Files in this item

Name:
LEM3_IJSS_2023_MERAGHNI2 (1).pdf
Size:
8.709Mb
Format:
PDF
Embargoed until:
2024-06-01
View/Open

Collections

  • Laboratoire d'Etude des Microstructures et de Mécanique des Matériaux (LEM3)

Related items

Showing items related by title, author, creator and subject.

  • Physically informed deep homogenization neural network for unidirectional multiphase/multi-inclusion thermoconductive composites 
    Article dans une revue avec comité de lecture
    JIANG, Jindong; WU, Jiajun; CHEN, Qiang; ccCHATZIGEORGIOU, George; ccMERAGHNI, Fodil (Elsevier BV, 2023-05)
    Elements of the periodic homogenization framework and deep neural network were seamlessly connected for the first time to construct a new micromechanics theory for thermoconductive composites called physically informed ...
  • Homogenization of size-dependent multiphysics behavior of nanostructured piezoelectric composites with energetic surfaces 
    Article dans une revue avec comité de lecture
    CHEN, Qiang; CHATZIGEORGIOU, George; MERAGHNI, Fodil; JAVILI, Ali (Elsevier BV, 2022)
    Surface piezoelectricity considering the extended Gurtin--Murdoch coherent interface model has been incorporated into the composite cylinder assemblage (CCA), generalized self-consistent method (GSCM), as well as the ...
  • Recursive multiscale homogenization of multiphysics behavior of fuzzy fiber composites reinforced by hollow carbon nanotubes 
    Article dans une revue avec comité de lecture
    CHEN, Qiang; MERAGHNI, Fodil; CHATZIGEORGIOU, George (SAGE, 2022)
    Fuzzy fibers are fibers enhanced in terms of multiphysics properties with radially oriented carbon nanotubes grown on their surface through the chemical deposition process. For the first time, this paper attempts to present ...
  • Extended Mean-Field Homogenization of Viscoelastic-Viscoplastic Polymer Composites Undergoing Hybrid Progressive Degradation Induced by Interface Debonding and Matrix Ductile Damage 
    Article dans une revue avec comité de lecture
    CHEN, Qiang; CHATZIGEORGIOU, George; MERAGHNI, Fodil (Elsevier, 2020)
    In this contribution, a probabilistic micromechanics damage framework is presented to predict the macroscopic stress-strain response and progressive damage in unidirectional glass-reinforced thermoplastic polymer composites. ...
  • Extended mean-field homogenization of unidirectional piezoelectric nanocomposites with generalized Gurtin-Murdoch interfaces 
    Article dans une revue avec comité de lecture
    CHEN, Qiang; ccCHATZIGEORGIOU, George; ccMERAGHNI, Fodil (Elsevier BV, 2022-12)
    This paper presents for the first time an extended Mori-Tanaka approach aimed at identifying the little-explored piezoelectric response of unidirectional nanoporous composites with energetic surfaces. The interface is ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales