Journal article 9 views
A generalised theory for physics-augmented neurals networks in finite strain thermo-electro-mechanics
R. Ortigosa,
J. Martınez-Frutos,
A. Perez-Escolar,
I. Castanar,
Niklas Hellmer,
Antonio Gil 
Computer Methods in Applied Mechanics and Engineering
Swansea University Authors:
Niklas Hellmer, Antonio Gil
Abstract
This manuscript introduces a novel neural network-based computational framework for constistutive modelling of thermo-electro-mechanically coupled materials at finite strains, with four key innovations: (i) It supports calibration of neural network models with various input forms, such as Ψnn(F, E0,...
| Published in: | Computer Methods in Applied Mechanics and Engineering |
|---|---|
| Published: |
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa68679 |
| Abstract: |
This manuscript introduces a novel neural network-based computational framework for constistutive modelling of thermo-electro-mechanically coupled materials at finite strains, with four key innovations: (i) It supports calibration of neural network models with various input forms, such as Ψnn(F, E0, θ), enn(F, D0, η), Υnn(F, E0, η), or Γnn(F, D0, θ), with F representing the deformation gradient tensor, E0 and D0 the electric field and electric displacement field, respectively and finally, θ and η, the temperature and entropy fields. These models comply with physical laws and material symmetries by utilizing isotropic or anisotropic invariants corresponding to the material’s symmetry group. (ii) A calibration approach is developed for the case of experimental data, where entropy η is typically unmeasurable. (iii) The framework accommodates models like enn(F, D0, η), specially convenient for the imposition of polyconvexity across the three physics involved. A detailed calibration study is conducted evaluating various neural network architectures and considering a large variety of ground truth thermo-electro-mechanical constitutive models. The results demonstrate excellent predictive performance on larger datasets, validated through complex finite element simulations using both ground truth and neural network-based models. Crucially, the framework can be straightforwardly extended to scenarios involving other physics. |
|---|---|
| College: |
Faculty of Science and Engineering |