Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity
From MaRDI portal
Publication:2678490
Recommendations
- A machine learning based plasticity model using proper orthogonal decomposition
- Graph-based representation of history-dependent material response in the data-driven computational mechanics framework
- A neural kernel method for capturing multiscale high-dimensional micromorphic plasticity of materials with internal structures
- Geometric learning for computational mechanics. III: Physics-constrained response surface of geometrically nonlinear shells
- Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity
Cites work
- A configurational force for adaptive re-meshing of gradient-enhanced poromechanics problems with history-dependent variables
- A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
- A finite micro-rotation material point method for micropolar solid and fluid dynamics with three-dimensional evolving contacts and free surfaces
- A heteroencoder architecture for prediction of failure locations in porous metals using variational inference
- A kd-tree-accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
- A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
- A multiscale overlapped coupling formulation for large-deformation strain localization
- A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks
- A nonlocal multiscale discrete-continuum model for predicting mechanical behavior of granular materials
- A physics-constrained data-driven approach based on locally convex reconstruction for noisy database
- A recurrent neural network for modelling dynamical systems
- A semi-implicit discrete-continuum coupling method for porous media based on the effective stress principle at finite strain
- Artificial neural networks in numerical modelling of composites
- Computational homogenization of nonlinear elastic materials using neural networks
- Concurrent AtC coupling based on a blend of the continuum stress and the atomistic force
- Data-driven fracture mechanics
- Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
- Generalized plasticity and the modelling of soil behaviour
- Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity
- Inelastic constitutive relations for solids: An internal-variable theory and its application to metal plasticity
- Lie-group interpolation and variational recovery for internal variables
- Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks
- Machine learning constitutive models of elastomeric foams
- Model-free data-driven inelasticity
- Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
- Multi-scale computational homogenization: trends and challenges
- Multilayer feedforward networks are universal approximators
- Plastic Internal Variables Formalism of Cyclic Plasticity
- Reconstruction equations and the Karhunen-Loève expansion for systems with symmetry
- Reducing the Dimensionality of Data with Neural Networks
- Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening
- Strain-driven homogenization of inelastic microstructures and composites based on an incremental variational formulation
- The reduced model multiscale method (R3M) for the nonlinear homogenization of hyperelastic media at finite strains
Cited in
(9)- A microstructure-based graph neural network for accelerating multiscale simulations
- Recurrent neural networks and transfer learning for predicting elasto-plasticity in woven composites
- Uncertainty quantification of graph convolution neural network models of evolving processes
- Unsupervised machine learning classification for accelerating \(\mathrm{FE}^2\) multiscale fracture simulations
- Geometric learning for computational mechanics. III: Physics-constrained response surface of geometrically nonlinear shells
- Surrogate modeling for the homogenization of elastoplastic composites based on RBF interpolation
- Viscoelasticty with physics-augmented neural networks: model formulation and training methods without prescribed internal variables
- Modular machine learning-based elastoplasticity: generalization in the context of limited data
- Micromechanics-based deep-learning for composites: challenges and future perspectives
Describes a project that uses
Uses Software
This page was built for publication: Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2678490)
