Strain Energy

Strain energy, the energy stored in a deformed material, is a crucial concept for understanding material behavior and designing structures. Current research focuses on efficiently and accurately predicting strain energy and related quantities (stress, strain) using machine learning, particularly employing neural networks (including physics-informed and equivariant architectures) and generative models to overcome limitations of traditional methods like finite element analysis. These advancements are improving the modeling of complex materials, enabling more accurate simulations in diverse fields such as topology optimization and cardiovascular risk assessment, and facilitating the inverse design of materials with tailored properties.

Papers

September 23, 2024

Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials
Sifan Wang, Tong-Rui Liu, Shyam Sankaran, Paris Perdikaris
Solid Mechanic Heterogeneous Material Smartphone Microscope Strain Energy Stress Field

July 25, 2024

Learning Physics-Consistent Material Behavior Without Prior Knowledge
Zhichao Han, Mohit Pundir, Olga Fink, David S. Kammer
LeArning Abstract Prior Knowledge Strain Energy Stress Strain

December 12, 2023

Dynamically configured physics-informed neural network in topology optimization applications
Jichao Yin, Ziming Wen, Shuhao Li, Yaya Zhanga, Hu Wang
Physic Informed Neural Network Optimization Process Finite Element Topology Optimization Strain Energy

November 22, 2023

Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
Ehsan Ghane, Martin Fagerström, Mohsen Mirkhalaf
Recurrent Neural Network Formality Transfer Strain Energy Woven Composite

September 15, 2023

Neural Metamaterial Networks for Nonlinear Material Design
Yue Li, Stelian Coros, Bernhard Thomaszewski
Metamaterial Unit Strain Energy Inverse Material Design Metamaterial Neural Network Nonlinear Material Nonlinear Waveguide

September 11, 2023

Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields
Vahidullah Tac, Manuel K Rausch, Ilias Bilionis, Francisco Sahli Costabal, Adrian Buganza Tepole
Hyperelastic Material Strain Energy Diffusion Field

August 30, 2023

Segmenting mechanically heterogeneous domains via unsupervised learning
Quan Nguyen, Emma Lejeune
Unsupervised Learning Deformable Object Heterogeneous Domain Heterogeneous Material Strain Energy Heterogeneous Curvature

August 3, 2023

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment
Yasin Shokrollahi1, Pengfei Dong1, Xianqi Li, Linxia Gu
Deep Learning Model Continuous Chronic Stress Cardiovascular Disease Risk Strain Energy Stress Field Arterial Wall Strain Map

June 22, 2023

StrainTensorNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks
Teerachote Pakornchote, Annop Ektarawong, Thiparat Chotibut
Neural Network Crystal Structure Atomistic System Price Elasticity Equivariant Graph Strain Energy

May 17, 2023

Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiency
Hongrui Chen, Aditya Joglekar, Levent Burak Kara
Neural Network High Efficiency Topology Optimization Strain Energy

June 16, 2022

Automated analysis of continuum fields from atomistic simulations using statistical machine learning
Aruna Prakash, Stefan Sandfeld
General Analysis Statistical Learning Atomistic Simulation Constitutive Model Strain Energy Local Plasticity

Strain Energy

Papers

Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials

Learning Physics-Consistent Material Behavior Without Prior Knowledge

Dynamically configured physics-informed neural network in topology optimization applications

Recurrent neural networks and transfer learning for elasto-plasticity in woven composites

Neural Metamaterial Networks for Nonlinear Material Design

Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields

Segmenting mechanically heterogeneous domains via unsupervised learning

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment

StrainTensorNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks

Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiency

Automated analysis of continuum fields from atomistic simulations using statistical machine learning