Data-driven anisotropic finite viscoelasticity using neural ordinary differential equations
From MaRDI portal
Publication:6097591
Abstract: We develop a fully data-driven model of anisotropic finite viscoelasticity using neural ordinary differential equations as building blocks. We replace the Helmholtz free energy function and the dissipation potential with data-driven functions that a priori satisfy physics-based constraints such as objectivity and the second law of thermodynamics. Our approach enables modeling viscoelastic behavior of materials under arbitrary loads in three-dimensions even with large deformations and large deviations from the thermodynamic equilibrium. The data-driven nature of the governing potentials endows the model with much needed flexibility in modeling the viscoelastic behavior of a wide class of materials. We train the model using stress-strain data from biological and synthetic materials including humain brain tissue, blood clots, natural rubber and human myocardium and show that the data-driven method outperforms traditional, closed-form models of viscoelasticity.
Recommendations
- Learning viscoelasticity models from indirect data using deep neural networks
- Data-driven tissue mechanics with polyconvex neural ordinary differential equations
- A mechanics-informed deep learning framework for data-driven nonlinear viscoelasticity
- Viscoelastic constitutive artificial neural networks (vCANNs) -- a framework for data-driven anisotropic nonlinear finite viscoelasticity
Cites work
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- A generic physics-informed neural network-based constitutive model for soft biological tissues
- A mechanics‐informed artificial neural network approach in data‐driven constitutive modeling
- A new viscoelastic constitutive model for continuous media at finite thermomechanical changes
- A theory of finite viscoelasticity and numerical aspects
- An efficient and accurate method for modeling nonlinear fractional viscoelastic biomaterials
- Anisotropic finite strain viscoelasticity: constitutive modeling and finite element implementation
- Constrained neural network training and its application to hyperelastic material modeling
- Data-driven tissue mechanics with polyconvex neural ordinary differential equations
- Generalized parameter identification for finite viscoelasticity
- Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity
- Learning viscoelasticity models from indirect data using deep neural networks
- Long-time integration of parametric evolution equations with physics-informed DeepONets
- Modeling the anisotropic finite-deformation viscoelastic behavior of soft fiber-reinforced composites
- Nonlinear dependence of viscosity in modeling the rate-dependent response of natural and high damping rubbers in compression and shear: experimental identification and numerical verification
- Polyconvexity of generalized polynomial-type hyperelastic strain energy functions for near-incompressibility.
- Predicting the mechanical properties of biopolymer gels using neural networks trained on discrete fiber network data
- Recurrent neural networks (RNNs) learn the constitutive law of viscoelasticity
- Unsupervised discovery of interpretable hyperelastic constitutive laws
Cited in
(12)- A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
- Learning viscoelasticity models from indirect data using deep neural networks
- Theory and implementation of inelastic constitutive artificial neural networks
- On sparse regression, \(L_p\)-regularization, and automated model discovery
- An Eulerian constitutive model for rate-dependent inelasticity enhanced by neural networks
- Deep learning in computational mechanics: a review
- A mechanics-informed deep learning framework for data-driven nonlinear viscoelasticity
- Viscoelastic constitutive artificial neural networks (vCANNs) -- a framework for data-driven anisotropic nonlinear finite viscoelasticity
- A comparative study on different neural network architectures to model inelasticity
- Viscoelasticty with physics-augmented neural networks: model formulation and training methods without prescribed internal variables
- Incremental neural controlled differential equations for modeling of path-dependent material behavior
- Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics
This page was built for publication: Data-driven anisotropic finite viscoelasticity using neural ordinary differential equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097591)
