☆ 4.7 Article

Finite strain FE2 analysis with data-driven homogenization using deep neural networks

COMPUTERS & STRUCTURES (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Mathematics, Interdisciplinary Applications

Neural network constitutive model for crystal structures

Sunyoung Im et al.

Summary: Neural network constitutive models (NNCMs) for crystal structures based on computationally generated high-fidelity data were proposed, demonstrating better performance for cubic structures compared to classical models. Constructed artificial neural networks were tested under various strain states, with consideration of symmetry conditions, showcasing the potential for embedding into a nonlinear finite element method.

COMPUTATIONAL MECHANICS (2021)

添加到收藏夹

Article Mechanics

Non-linear FE2 multiscale simulation of damage, micro and macroscopic strains in polyamide 66-woven composite structures: Analysis and experimental validation

E. Tikarrouchine et al.

Summary: This paper presents an experimental approach for analyzing and validating a two-scale nonlinear Finite Element (FE2) simulation of a 3D composite structure. The multiscale parallel computation is based on periodic homogenization at the microscopic scale, considering the time-dependent and non-linear local behavior of each constitutive phase. By developing an advanced UMAT subroutine and combining it with parallelization technique, the numerical results of the FE multiscale simulation show good agreement with experimental results. The multiscale strategy provides access to microscopic strain fields and spatiotemporal distributions of internal variables, demonstrating capabilities in damage evolution prediction.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mathematics, Interdisciplinary Applications

Anisotropic hyperelastic constitutive models for finite deformations combining material theory and data-driven approaches with application to cubic lattice metamaterials

Mauricio Fernandez et al.

Summary: This study investigates the capabilities of anisotropic theory-based, purely data-driven, and hybrid approaches to model the homogenized behavior of cubic lattice metamaterials. The results show that the data-driven models can accurately reproduce simulation data and manifest lattice instabilities, achieving superior accuracy in additional test scenarios.

COMPUTATIONAL MECHANICS (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

Smart constitutive laws: Inelastic homogenization through machine learning

Hernan J. Logarzo et al.

Summary: This work introduces an alternative formulation to concurrent multiscale models (CMMs) called smart constitutive laws (SCLs), which leverage advanced micromechanical modeling and machine learning techniques to boost computational efficiency and scalability for nonlinear and history-dependent materials. SCLs are suitable for arbitrary loading histories and enable the automatic generation of microstructurally-informed constitutive laws for solving macro-scale complex structures. The research findings suggest that SCLs can significantly improve computational homogenization for materials with arbitrary microstructures.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Neural network-aided prediction of post-cracking tensile strength of fibre-reinforced concrete

T. Ikumi et al.

Summary: This paper introduces the use of a neural network to predict the post-cracking tensile strength of fibre-reinforced concrete, optimizing the network architecture and parameters to improve prediction accuracy. It can effectively predict the tensile strength of concrete at different cracking stages and perform parameter analysis to validate the consistency of the predicted results.

COMPUTERS & STRUCTURES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Effective elastic and fracture properties of regular and irregular masonry from nonlinear homogenization

Tomas Krejci et al.

Summary: This study presents a method to predict the effective elastic and strength parameters of both regular and irregular masonry walls from homogenization. By adopting different constitutive models and boundary conditions, it is found that using a simple isotropic damage model is more suitable when solving the homogenization problem.

COMPUTERS & STRUCTURES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Learning constitutive relations using symmetric positive definite neural networks

Kailai Xu et al.

Summary: The SPD-NN predicts the Cholesky factor of the tangent stiffness matrix to calculate stress, achieving good numerical stability. Two training methods are proposed based on the types of available data.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Constitutive artificial neural networks: A fast and general approach to predictive data-driven constitutive modeling by deep learning

Kevin Linka et al.

Summary: Constitutive artificial neural networks (CANNs) are a novel machine learning architecture for data-driven modeling of the mechanical constitutive behavior of materials. By incorporating information from stress-strain data, materials theory, and additional information, CANNs can efficiently learn the constitutive behavior of complex materials with minimal training data. The ability to predict properties of new materials without existing stress-strain data makes CANNs potentially useful for in-silico material design in the future.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Finite element network analysis: A machine learning based computational framework for the simulation of physical systems

Mehdi Jokar et al.

Summary: Finite element network analysis (FENA) is a physics-informed, machine-learning-based computational framework that leverages trained neural networks and bidirectional recurrent neural networks for simulating physical systems. It can simulate the response of interconnected physical systems without the need for further training, and has the potential for a broad spectrum of applications in computational science. This new concept of computational platform demonstrates outstanding performance when compared to traditional finite element analysis.

COMPUTERS & STRUCTURES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings

Ahmed A. Torky et al.

Summary: This paper introduces a new approach for predicting nonlinear multi-component seismic responses of structures using hybrid deep learning techniques. Through a challenging case study, it demonstrates the effectiveness of the method in accurately predicting seismic responses and capacity curves of structures.

COMPUTERS & STRUCTURES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Machine learning in multiscale modeling of spatially tailored materials with microstructure uncertainties

Shaoping Xiao et al.

Summary: This paper proposes a novel hierarchical micro-macro multiscale modeling enhanced via machine learning to study the mechanics of a metal-ceramic (Ti-TiB2) spatially tailored material. Machine learning regression and classification models are trained using data sets collected from microscale simulations, and then implemented in macroscale simulations to analyze the structural responses under various loading conditions. Additionally, the consideration of microstructure uncertainties and the use of artificial neural network as a classification model distinguish this work from others.

COMPUTERS & STRUCTURES (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

A computational framework for homogenization and multiscale stability analyses of nonlinear periodic materials

Guodong Zhang et al.

Summary: This article presents a computational framework for multiscale finite strain homogenization and stability analyses of rate-independent solids with periodic microstructures. The multiscale instabilities include microscale structural instability calculated by Bloch wave analysis, and macroscale material instability calculated by rank-1 convexity checks on the homogenized tangent moduli. Numerical results show that microscopic long wavelength buckling can be equivalently detected by the loss of rank-1 convexity of the homogenized tangent moduli.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Homogenization and numerical modelling of poroelastic materials with self-contact in the microstructure

Eduard Rohan et al.

COMPUTERS & STRUCTURES (2020)

添加到收藏夹

Article Mechanics

On the computational homogenization of three-dimensional fibrous materials

Alp Karakoc et al.

COMPOSITE STRUCTURES (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new Time-distributed Residual U-Net architecture

Arnd Koeppe et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

A surrogate model for computational homogenization of elastostatics at finite strain using high-dimensional model representation-based neural network

Vien Minh Nguyen-Thanh et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths

Ling Wu et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Learning constitutive relations from indirect observations using deep neural networks

Daniel Z. Huang et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2020)

添加到收藏夹

Article Materials Science, Multidisciplinary

Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization

Chengping Rao et al.

COMPUTATIONAL MATERIALS SCIENCE (2020)

添加到收藏夹

Review Materials Science, Multidisciplinary

A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics

Frederic E. Bock et al.

FRONTIERS IN MATERIALS (2019)

添加到收藏夹

Article Engineering, Multidisciplinary

Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network

F. Ghavamian et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2019)

添加到收藏夹

Article Materials Science, Multidisciplinary

A simple explicit homogenization solution for the macroscopic elastic response of isotropic porous elastomers

Bhavesh Shrimali et al.

JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS (2019)

添加到收藏夹

Article Engineering, Multidisciplinary

Direct numerical simulation of 3D woven textile composites subjected to tensile loading: An experimentally validated multiscale approach

Deepak K. Patel et al.

COMPOSITES PART B-ENGINEERING (2018)

添加到收藏夹

Review Statistics & Probability

Variational Inference: A Review for Statisticians

David M. Blei et al.

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION (2017)

添加到收藏夹

Article Engineering, Multidisciplinary

A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality

M. A. Bessa et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2017)

添加到收藏夹

Review Mechanics

Aspects of Computational Homogenization at Finite Deformations: A Unifying Review From Reuss' to Voigt's Bound

Saba Saeb et al.

APPLIED MECHANICS REVIEWS (2016)

添加到收藏夹

Article Engineering, Multidisciplinary

Computational homogenization of nonlinear elastic materials using neural networks

B. A. Le et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

添加到收藏夹

Article Materials Science, Multidisciplinary

An RVE-based multiscale theory of solids with micro-scale inertia and body force effects

E. A. de Souza Neto et al.

MECHANICS OF MATERIALS (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Neural networks as material models within a multiscale approach

Joerg F. Unger et al.

COMPUTERS & STRUCTURES (2009)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Coupling of scales in a multiscale simulation using neural networks

Joerg F. Unger et al.

COMPUTERS & STRUCTURES (2008)

添加到收藏夹

Article Mechanics

Failure surfaces for finitely strained two-phase periodic solids under general in-plane loading

N Triantafyllidis et al.

JOURNAL OF APPLIED MECHANICS-TRANSACTIONS OF THE ASME (2006)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Learning to forget: Continual prediction with LSTM

FA Gers et al.

NEURAL COMPUTATION (2000)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.