An indirect training approach for implicit constitutive modelling using recurrent neural networks and the virtual fields method

DOI10.1016/J.CMA.2024.116961MaRDI QIDQ6497200zbMATH OpenFDO

Authors Rúben Lourenço, Petia Georgieva, E. Cueto, António Andrade-Campos

Publication date 6 May 2024

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

zbMATH Keywords

artificial neural networkrecurrent neural networkvirtual fields methodgated-recurrent unitimplicit constitutive modelindirect training

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Mechanics of deformable solids (74-XX)

Recommendations

• A mechanics‐informed artificial neural network approach in data‐driven constitutive modeling
• Learning solutions of thermodynamics-based nonlinear constitutive material models using physics-informed neural networks
• Constrained neural network training and its application to hyperelastic material modeling

Cites work

• scientific article; zbMATH DE number 4085137 (Why is no real title available?)
• scientific article; zbMATH DE number 1322734 (Why is no real title available?)
• Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
• Advanced discretization techniques for hyperelastic physics-augmented neural networks
• Applying the virtual fields method to the identification of elasto-plastic constitutive parameters
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Automated discovery of generalized standard material models with EUCLID
• Finite-element-model updating using computational intelligence techniques. Applications to structural dynamics
• Learning constitutive relations from indirect observations using deep neural networks
• Learning constitutive relations using symmetric positive definite neural networks
• Learning viscoelasticity models from indirect data using deep neural networks
• Multilayer feedforward networks are universal approximators
• Neural network constitutive modelling for nonlinear characterization of anisotropic materials
• Numerical implementation of a neural network based material model in finite element analysis
• Sensitivity-based virtual fields for the non-linear virtual fields method
• \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials

Cited in

(2)

• A thermodynamics-informed neural network for elastoplastic constitutive modeling of granular materials
• A Bayesian framework for constitutive model identification via use of full field measurements, with application to heterogeneous materials

This page was built for publication: An indirect training approach for implicit constitutive modelling using recurrent neural networks and the virtual fields method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6497200)