Deep homogenization networks for elastic heterogeneous materials with two- and three-dimensional periodicity
Article dans une revue avec comité de lecture
Author
Date
2023-12Journal
International Journal of Solids and StructuresAbstract
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:
- 8.930Mb
- Format:
- Embargoed until:
- 2024-06-01
Related items
Showing items related by title, author, creator and subject.
-
Article dans une revue avec comité de lectureWU, Jiajun; CHEN, Qiang; JIANG, Jindong; CHATZIGEORGIOU, George; MERAGHNI, Fodil (Elsevier BV, 2024-07)We present an adaptive physics-informed deep homogenization neural network (DHN) approach to formulate a full-field micromechanics model for elastic and thermoelastic periodic arrays with different microstructures. The ...
-
Article dans une revue avec comité de lectureJIANG, Jindong; WU, Jiajun; CHEN, Qiang; CHATZIGEORGIOU, George; MERAGHNI, 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 ...
-
Article dans une revue avec comité de lectureDU, Xiaoxiao; CHEN, Qiang; CHATZIGEORGIOU, George; MERAGHNI, Fodil; ZHAO, Gang; CHEN, Xuefeng (Elsevier BV, 2024-08)An isogeometric homogenization (IGH) technique is constructed for the homogenization and localization of unidirectional composites with radially or circumferentially orthotropic carbon/graphite fibers. The proposed theory ...
-
Article dans une revue avec comité de lectureIn 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. ...
-
Article dans une revue avec comité de lectureA new hybrid homogenization approach is proposed for simulating the homogenized and local response of unidirectional fuzzy fiber nanocomposites undergoing inelastic deformations. Fuzzy fiber composites are hierarchical ...