Learning constitutive relations using symmetric positive definite neural networks
We present a new neural-network architecture, called the Cholesky-factored symmetric
positive definite neural network (SPD-NN), for modeling constitutive relations in …
positive definite neural network (SPD-NN), for modeling constitutive relations in …
Data-driven multiscale finite element method: From concurrence to separation
This paper aims to propose a novel data-driven multiscale finite element method (data-
driven FE 2) for composite materials and structures. The correlated scales in the classical FE …
driven FE 2) for composite materials and structures. The correlated scales in the classical FE …
[HTML][HTML] Reconstruction of mesostructural material twin models of engineering textiles based on Micro-CT Aided Geometric Modeling
Engineering textiles are used as fibrous reinforcements in high performance polymer
composites. The mechanical properties of composite materials depend on their dual-scale …
composites. The mechanical properties of composite materials depend on their dual-scale …
Data-driven multiscale simulation of FRP based on material twins
In this paper, we propose a multiscale data-driven framework for Fiber Reinforced Polymer
(FRP) composites. At the mesoscopic scale, the 3D stress–strain material database is …
(FRP) composites. At the mesoscopic scale, the 3D stress–strain material database is …
Data-driven multiscale finite-element method using deep neural network combined with proper orthogonal decomposition
In this paper, a data-driven multiscale finite-element method (data-driven FE2) is proposed
using a deep neural network (DNN) and proper orthogonal decomposition (POD) to …
using a deep neural network (DNN) and proper orthogonal decomposition (POD) to …
An investigation on the coupling of data-driven computing and model-driven computing
The aim of this work is to investigate the coupling of data-driven (DD) computing and model-
driven (MD) computing for the analyses of engineering structures. The data-driven …
driven (MD) computing for the analyses of engineering structures. The data-driven …
[HTML][HTML] Predictions of macroscopic mechanical properties and microscopic cracks of unidirectional fibre-reinforced polymer composites using deep neural network …
Fibre-reinforced polymer (FRP) composites have been widely used in different engineering
sectors due to their excellent physical and mechanical properties. Therefore, fast …
sectors due to their excellent physical and mechanical properties. Therefore, fast …
New symplectic analytic solutions for buckling of CNT reinforced composite rectangular plates
This paper presents new analytic solutions for buckling of non-Lévy-type carbon nanotube
(CNT) reinforced composite rectangular plates, including cantilever, free, and clamped ones …
(CNT) reinforced composite rectangular plates, including cantilever, free, and clamped ones …
Data-driven multiscale method for composite plates
Composite plates are widely used in many engineering fields such as aerospace and
automotive. An accurate and efficient multiscale modeling and simulation strategy is of …
automotive. An accurate and efficient multiscale modeling and simulation strategy is of …
Structure genome based machine learning method for woven lattice structures
C Zhang, B Wang, H Zhu, H Fan - International Journal of Mechanical …, 2023 - Elsevier
As a type of lightweight composite material, three-dimensional (3D) woven lattice structure
(WLS) has been extensively applied in various fields. It is extremely significant to investigate …
(WLS) has been extensively applied in various fields. It is extremely significant to investigate …