Data-driven approach for dynamic homogenization using meta learning

DOI10.1016/J.CMA.2022.115672MaRDI QIDQ2096905zbMATH OpenOpenAlexFDO

Authors Aarohi Shah, J. J. Rimoli

Publication date 11 November 2022

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

Full work available at URL https://doi.org/10.1016/j.cma.2022.115672

zbMATH Keywords

dynamic problemsmachine learningnonlinear problemsperiodic structuresreduced-order models

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Homogenization and oscillations in dynamical problems of solid mechanics (74Q10)

Recommendations

• Finite and spectral cell method for wave propagation in heterogeneous materials
• Designing phononic crystal with anticipated band gap through a deep learning based data-driven method
• Computational design of innovative mechanical metafilters via adaptive surrogate-based optimization
• Characterization of heterogeneous solids via wave methods in computational microelasticity
• Efficient multiscale modeling of heterogeneous materials using deep neural networks

Cites work

• A geometric multiscale finite element method for the dynamic analysis of heterogeneous solids
• A new iterative order reduction(IOR) method for eigensolutions of large structures
• An adaptive concurrent multiscale method for microstructured elastic solids
• Computational homogenization of locally resonant acoustic metamaterial panels towards enriched continuum beam/shell structures
• Deep learning
• scientific article; zbMATH DE number 3540340 (Why is no real title available?)
• scientific article; zbMATH DE number 3627589 (Why is no real title available?)
• scientific article; zbMATH DE number 1465030 (Why is no real title available?)
• scientific article; zbMATH DE number 2162107 (Why is no real title available?)
• scientific article; zbMATH DE number 5253803 (Why is no real title available?)
• Model order reduction for linear and nonlinear systems: a system-theoretic perspective
• Model reduction using dynamic and iterated IRS techniques
• Multiscale modeling of complex dynamic problems: an overview and recent developments
• On nonlinear dynamic analysis using substructuring and mode superposition
• Pattern recognition and machine learning.
• Preprocessing and postprocessing for materials based on the homogenization method with adaptive finite element methods
• Smart constitutive laws: inelastic homogenization through machine learning
• Smart finite elements: a novel machine learning application
• Transient analysis of nonlinear locally resonant metamaterials via computational homogenization
• Transient computational homogenization for heterogeneous materials under dynamic excitation

Cited in

(3)

• Transfer learning of recurrent neural network‐based plasticity models
• Learned Gaussian quadrature for enriched solid finite elements
• Gaussian process regression as a surrogate model for the computation of dispersion relations

Describes a project that uses

Uses Software

• Keras
• Adam

This page was built for publication: Data-driven approach for dynamic homogenization using meta learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2096905)