Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter

DOI10.1007/S00466-021-02009-1MaRDI QIDQ2037488zbMATH OpenOpenAlexWikidataFDO

Authors Duncan Field, Yanis Ammouche, Jose M. Peña, Antoine Jérusalem

Publication date 8 July 2021

Published in Computational Mechanics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/s00466-021-02009-1

zbMATH Keywords

machine learningfinite element methodcomputational homogenizationmagnetic resonance imagingrepresentative volume elementbrain white matter modeling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Biomechanical solid mechanics (74L15) Biomedical imaging and signal processing (92C55) Composite and mixture properties (74E30) Finite element methods applied to problems in solid mechanics (74S05) Effective constitutive equations in solid mechanics (74Q15)

Recommendations

• A three-dimensional prediction method of stiffness properties of composites based on deep learning
• Smart constitutive laws: inelastic homogenization through machine learning
• Finite element coupled positive definite deep neural networks mechanics system for constitutive modeling of composites
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• Efficient multiscale modeling of heterogeneous materials using deep neural networks

Cites work

• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 2200689 (Why is no real title available?)
• A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites
• Biomechanics of traumatic brain injury
• Brain tissue deforms similarly to filled elastomers and follows consolidation theory
• Clustering discretization methods for generation of material performance databases in machine learning and design optimization
• Computational homogenization of nonlinear elastic materials using neural networks
• Data-driven computational mechanics
• Derivation of heterogeneous material laws via data-driven principal component expansions
• Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap
• Extremely randomized trees
• Greedy function approximation: A gradient boosting machine.
• Microstructural material database for self-consistent clustering analysis of elastoplastic strain softening materials
• On fiber dispersion models: exclusion of compressed fibers and spurious model comparisons
• Random forests
• Self-consistent clustering analysis for multiscale modeling at finite strains
• Self-consistent clustering analysis: an efficient multi-scale scheme for inelastic heterogeneous materials
• Transfer learning of deep material network for seamless structure-property predictions

Cited in

(1)

• \(\mathrm{FE^{ANN}}\): an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining

Describes a project that uses

Uses Software

• AdaBoost.MH

This page was built for publication: Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2037488)