Physically enhanced training for modeling rate-independent plasticity with feedforward neural networks

DOI10.1007/s00466-023-02316-9MaRDI QIDQ6084775

Werner Wagner, Patrick Weber, Steffen Freitag

Publication date: 2 December 2023

Published in: Computational Mechanics (Search for Journal in Brave)

zbMATH Keywords

stabilityconvergenceinfinitesimal strain tensorgradient-based optimization algorithmmaterial constraint

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials) (74C05) Numerical and other methods in solid mechanics (74S99)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning from hints in neural networks
• Computational inelasticity
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Finite element concepts for finite elastoplastic strains and isotropic stress response in shells: Theoretical and computational analysis
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• An advanced shell model for the analysis of geometrical and material nonlinear shells
• Learning constitutive relations using symmetric positive definite neural networks
• A machine learning based plasticity model using proper orthogonal decomposition
• A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
• Constrained neural network training and its application to hyperelastic material modeling
• A robust non-linear mixed hybrid quadrilateral shell element
• A mixed shell formulation accounting for thickness strains and finite strain 3d material models
• A new neural network-based model for hysteretic behavior of materials
• Numerical implementation of a neural network based material model in finite element analysis
• Material Modeling via Thermodynamics-Based Artificial Neural Networks
• Learning representations by back-propagating errors
• Convergence Conditions for Ascent Methods
• Convergence Conditions for Ascent Methods. II: Some Corrections
• Approximation by superpositions of a sigmoidal function
• A mechanics‐informed artificial neural network approach in data‐driven constitutive modeling

This page was built for publication: Physically enhanced training for modeling rate-independent plasticity with feedforward neural networks