Neural integration for constitutive equations using small data

DOI10.1016/j.cma.2023.116698arXiv2311.07849OpenAlexW4390122301MaRDI QIDQ6153835

Itai Einav, Filippo Masi

Publication date: 19 March 2024

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

Full work available at URL: https://arxiv.org/abs/2311.07849

zbMATH Keywords

thermodynamicssmall dataconstitutive modellingdeep learning

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Computer science (68-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Granular solid hydrodynamics
• Smart constitutive laws: inelastic homogenization through machine learning
• Recurrent neural networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
• Multiscale modeling of inelastic materials with thermodynamics-based artificial neural networks (TANN)
• Data-driven tissue mechanics with polyconvex neural ordinary differential equations
• Hydrodynamic derivation of the work input to fully and partially saturated soils
• Unsupervised discovery of interpretable hyperelastic constitutive laws
• A proposal on machine learning via dynamical systems
• Interfacing finite elements with deep neural operators for fast multiscale modeling of mechanics problems
• Automated discovery of generalized standard material models with EUCLID
• A new neural network-based model for hysteretic behavior of materials
• The Method of Virtual Power in Continuum Mechanics. Part 2: Microstructure
• Comparison of neural closure models for discretised PDEs