Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening
From MaRDI portal
Publication:2021962
DOI10.1016/j.cma.2021.113695zbMath1506.74449arXiv2010.11265OpenAlexW3131608859MaRDI QIDQ2021962
WaiChing Sun, Nikolaos N. Vlassis
Publication date: 27 April 2021
Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2010.11265
recurrent neural networkpolycrystalsmultiscaleisotropic yield functionphysics-informed constraintsSobolev training
Small-strain, rate-dependent theories of plasticity (including theories of viscoplasticity) (74C10) Finite element methods applied to problems in solid mechanics (74S05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30)
Related Items (24)
Multiscale modeling of inelastic materials with thermodynamics-based artificial neural networks (TANN) ⋮ Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties ⋮ Data-driven tissue mechanics with polyconvex neural ordinary differential equations ⋮ Machine learning constitutive models of elastomeric foams ⋮ Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity ⋮ Molecular dynamics inferred transfer learning models for finite‐strain hyperelasticity of monoclinic crystals: Sobolev training and validations against physical constraints ⋮ Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials ⋮ A comparative study on different neural network architectures to model inelasticity ⋮ A neural kernel method for capturing multiscale high-dimensional micromorphic plasticity of materials with internal structures ⋮ Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems ⋮ Geometric learning for computational mechanics. III: Physics-constrained response surface of geometrically nonlinear shells ⋮ \(\mathrm{FE^{ANN}}\): an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining ⋮ Incompressible rubber thermoelasticity: a neural network approach ⋮ Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria ⋮ Automated discovery of generalized standard material models with EUCLID ⋮ Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions ⋮ Predicting dynamic responses of continuous deformable bodies: a graph-based learning approach ⋮ A framework for neural network based constitutive modelling of inelastic materials ⋮ Enhancing phenomenological yield functions with data: challenges and opportunities ⋮ Modular machine learning-based elastoplasticity: generalization in the context of limited data ⋮ Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate ⋮ Geometric prior of multi-resolution yielding manifolds and the local closest point projection for nearly non-smooth plasticity ⋮ Finite electro-elasticity with physics-augmented neural networks ⋮ Bezier5YS and SHYqp: a general framework for generating data and for modeling symmetric and asymmetric orthotropic yield surfaces
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Artificial neural networks in numerical modelling of composites
- Learning constitutive relations from indirect observations using deep neural networks
- An outline of hypoplasticity
- Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
- Anisotropic additive plasticity in the logarithmic strain space: Modular kinematic formulation and implementation based on incremental minimization principles for standard materials.
- A micromorphically regularized Cam-Clay model for capturing size-dependent anisotropy of geomaterials
- Efficient and accurate two-scale FE-FFT-based prediction of the effective material behavior of elasto-viscoplastic polycrystals
- Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity
- \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials
- Data driven modeling of plastic deformation
- A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality
- FFT-based solver for higher-order and multi-phase-field fracture models applied to strongly anisotropic brittle materials
- A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
- A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
- Two-scale FE-FFT- and phase-field-based computational modeling of bulk microstructural evolution and macroscopic material behavior
- Implicit numerical integration of a three-invariant, isotropic/kinematic hardening cap plasticity model for geomaterials
- Inelastic constitutive relations for solids: An internal-variable theory and its application to metal plasticity
- Plasticity
- SANISAND: Simple anisotropic sand plasticity model
- A smooth hyperbolic approximation to the Mohr-Coulomb yield criterion
- Generalized plasticity and the modelling of soil behaviour
- Discrete micromechanics of elastoplastic crystals
- Numerical implementation of a neural network based material model in finite element analysis
- Some implications of work hardening and ideal plasticity
- Cam-Clay plasticity. IV: Implicit integration of anisotropic bounding surface model with nonlinear hyperelasticity and ellipsoidal loading function
This page was built for publication: Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening
