☆ 4.7 Article

Incompressible rubber thermoelasticity: a neural network approach

COMPUTATIONAL MECHANICS (2023)

Related references

Note: Only part of the references are listed.

Article Mathematics, Interdisciplinary Applications

FEANN: an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining

Karl A. Kalina et al.

Summary: In this paper, a new data-driven multiscale framework called FEANN is introduced, which utilizes physics-constrained artificial neural networks (ANNs) as macroscopic surrogate models and includes an autonomous data mining process. This approach enables efficient simulation of materials with complex microstructures exhibiting anisotropic and nonlinear behavior on the macroscale. The proposed framework significantly reduces the number of time-consuming microscale simulations by autonomously gathering and extending the necessary data set.

COMPUTATIONAL MECHANICS (2023)

Add to Collection

Article Materials Science, Multidisciplinary

A Hybrid Approach Employing Neural Networks to Simulate the Elasto-Plastic Deformation Behavior of 3D-Foam Structures

Alexander Malik et al.

Summary: This article presents a methodology to describe the complex inelastic macroscale behavior of cellular media, contributing to the establishment of predictive computational tools for studying the structure-property-performance relations in such materials. The use of numerical micro-macro transition schemes and neural networks allows for a hybrid material model to capture the macroscopic material behavior effectively.

ADVANCED ENGINEERING MATERIALS (2022)

Add to Collection

Article Mathematics, Interdisciplinary Applications

Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks

Karl A. Kalina et al.

Summary: This study presents an ANN-based approach for modeling and simulating isotropic hyperelastic solids efficiently. By reducing the problem's dimensionality, a simplified model using deformation type invariants and stress coefficients is trained to achieve high accuracy in simulating three-dimensional samples.

COMPUTATIONAL MECHANICS (2022)

Add to Collection

Article Materials Science, Multidisciplinary

Polyconvex anisotropic hyperelasticity with neural networks

Dominik K. Klein et al.

Summary: In this paper, two machine learning based constitutive models for finite deformations are proposed. They are hyperelastic, anisotropic, fulfill the polyconvexity condition, and have excellent predictive and generalization capabilities. The models are calibrated with challenging simulation data and show good results, demonstrating their reliability and applicability.

JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS (2022)

Add to Collection

Article Engineering, Multidisciplinary

On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling

Jan N. Fuhg et al.

Summary: This paper presents a physics-informed and data-driven constitutive modeling approach for isotropic and anisotropic hyperelastic materials at finite strain. The approach trains surrogate models that respect physical principles, and demonstrates surprising accuracy even beyond the limits of the training domain. The paper also introduces a sampling technique that generates space-filling points in the invariant space, improving the efficiency and reliability of the constitutive models.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Engineering, Multidisciplinary

A mechanics-informed artificial neural network approach in data-driven constitutive modeling

Faisal As'ad et al.

Summary: This paper proposes a mechanics-informed artificial neural network approach for learning constitutive laws of complex, nonlinear, elastic materials. The approach captures highly nonlinear strain-stress mappings while preserving fundamental principles of solid mechanics. It enforces physical constraints and demonstrates potential for multi-scale applications.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2022)

Add to Collection

Article Engineering, Multidisciplinary

Bayesian-EUCLID: Discovering hyperelastic material laws with uncertainties

Akshay Joshi et al.

Summary: In this paper, an unsupervised Bayesian learning framework is proposed for the discovery of parsimonious and interpretable constitutive laws. The method leverages full-field displacement and global reaction force data, and utilizes a large catalog of candidate functional features to construct constitutive model ansatz. The hierarchical Bayesian model with sparsity-promoting priors and Monte Carlo sampling efficiently solves the model selection task and discovers physically consistent constitutive equations.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Predicting stress-strain behavior of carbon nanotubes using neural networks

Valentina Kosmerl et al.

Summary: Artificial neural networks were used to predict stress-strain curves for carbon nanotubes of different configurations. The study compared three model architectures and found that they can accurately and quickly predict the curves, capturing even the smallest variations caused by thermal fluctuations. A sensitivity analysis revealed that the diameter and temperature are the most important parameters affecting the exclusion or prediction of thermal fluctuations.

NEURAL COMPUTING & APPLICATIONS (2022)

Add to Collection

Article Chemistry, Physical

Deep learning framework for carbon nanotubes: Mechanical properties and modeling strategies

Marko Canadija

Summary: Tensile tests were conducted on single-walled carbon nanotubes up to 4 nm in diameter using molecular dynamics, revealing the influence of nanotube chirality on mechanical properties. The development of an artificial neural network based on the dataset allowed for accurate predictions of mechanical properties using Deep Learning. The analysis of dataset size effects on prediction quality provided modeling strategies for future researchers.

CARBON (2021)

Add to Collection

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)

Add to Collection

Article Materials Science, Multidisciplinary

Thermodynamics-based Artificial Neural Networks for constitutive modeling

Filippo Masi et al.

Summary: TANNs is a physics-based neural network method for constitutive modeling, where thermodynamic principles are encoded into the network architecture using automatic differentiation. Its advantages include efficiency, robustness, accuracy in predictions, and maintaining thermodynamic consistency.

JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS (2021)

Add to Collection

Article Engineering, Multidisciplinary

Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening

Nikolaos N. Vlassis et al.

Summary: This study introduces a deep learning framework designed to train smoothed elastoplasticity models with interpretable components, and demonstrates that machine learning hardening laws can recover classical rules and discover new mechanisms, resulting in more robust and accurate forward predictions.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

Add to Collection

Article Mathematics, Interdisciplinary Applications

Constrained neural network training and its application to hyperelastic material modeling

Patrick Weber et al.

Summary: This paper presents a new approach to enhance neural network training with physical knowledge using constraint optimization techniques in computational mechanics for material behavior approximation. Specific constraints for hyperelastic materials are introduced to address issues like small training samples and noisy data. Experimental results demonstrate that training with physical constraints outperforms state-of-the-art techniques in terms of stability and convergence behavior within finite element simulations.

COMPUTATIONAL MECHANICS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Simulation of hyperelastic materials in real-time using deep learning

Andrea Mendizabal et al.

MEDICAL IMAGE ANALYSIS (2020)

Add to Collection

Article Materials Science, Multidisciplinary

Modeling stress-strain curves with neural networks: a scalable alternative to the return mapping algorithm

Maxime Lavech du Bos et al.

COMPUTATIONAL MATERIALS SCIENCE (2020)

Add to Collection

Article Engineering, Multidisciplinary

A virtual element method for isotropic hyperelasticity

Daniel van Huyssteen et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Add to Collection

Article Engineering, Multidisciplinary

A machine learning based plasticity model using proper orthogonal decomposition

Dengpeng Huang et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Add to Collection

Article Engineering, Multidisciplinary

Data-driven fracture mechanics

P. Carrara et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Add to Collection

Article Engineering, Multidisciplinary

Deep learned finite elements

Jaeho Jung et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Add to Collection

Article Engineering, Multidisciplinary

Geometric deep learning for computational mechanics Part I: anisotropic hyperelasticity

Nikolaos N. Vlassis et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Add to Collection

Article Engineering, Multidisciplinary

A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials

Zeliang Liu et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2019)

Add to Collection

Article Engineering, Multidisciplinary

Smart finite elements: A novel machine learning application

German Capuano et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2019)

Add to Collection

Article Multidisciplinary Sciences

A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis

Liang Liang et al.

JOURNAL OF THE ROYAL SOCIETY INTERFACE (2018)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Numerical characterisation of uncured elastomers by a neural network based approach

C. Zopf et al.

COMPUTERS & STRUCTURES (2017)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A material description based on recurrent neural networks for fuzzy data and its application within the finite element method

S. Freitag et al.

COMPUTERS & STRUCTURES (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Belief Networks Are Compact Universal Approximators

Nicolas Le Roux et al.

NEURAL COMPUTATION (2010)

Add to Collection

Review Polymer Science

A REVIEW OF VOLUME CHANGES IN RUBBERS: THE EFFECT OF STRETCHING

Jean-Benoit Le Cam

RUBBER CHEMISTRY AND TECHNOLOGY (2010)

Add to Collection

Article Engineering, Multidisciplinary

A mixed shell formulation accounting for thickness strains and finite strain 3d material models

Sven Klinkel et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2008)

Add to Collection

Article Polymer Science

Neural network based constitutive model for rubber material

Y Shen et al.

RUBBER CHEMISTRY AND TECHNOLOGY (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.