Accelerated multiscale data-driven finite element analysis using mean-field homogenization method with knowledge transfer

DOI10.1016/J.JCP.2026.114870MaRDI QIDQ7268261zbMATH OpenFDO

Authors Wonjoo Lee, Suhan Kim, H. Shin

Publication date 17 June 2026

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2026.114870

zbMATH Keywords

multiscale analysistransfer learningfinite element analysismean-field homogenizationdata-driven multiscale finite element method

Mathematics Subject Classification ID

Numerical methods for partial differential equations, boundary value problems (65Nxx) Numerical and other methods in solid mechanics (74Sxx) Homogenization, determination of effective properties in solid mechanics (74Qxx)

Cites work

• A multilevel computational strategy for handling microscopic and macroscopic instabilities
• A multilevel finite element method (FE\(^{2}\)) to describe the response of highly nonlinear structures using generalized continua.
• A multiscale modeling technique for bridging molecular dynamics with finite element method
• Accelerated offline setup of homogenized microscopic model for multi‐scale analyses using neural network with knowledge transfer
• Accelerating the data-driven multiscale finite element analysis for elastoplastic materials by using proper orthogonal decomposition and transformer architecture
• Computational homogenization analysis in finite plasticity. Simulation of texture development in polycrystalline materials
• Computational plasticity for composite structures based on mathematical homogenization: Theory and practice
• Data-driven computational mechanics
• Data-driven computing in dynamics
• Data-driven fracture mechanics
• Data-driven multiscale finite element method: from concurrence to separation
• Data-driven multiscale method for composite plates
• Data-driven solvers for strongly nonlinear material response
• Deep learning framework for multiscale finite element analysis based on data-driven mechanics and data augmentation
• Integration efficiency for model reduction in micro-mechanical analyses
• Model-free data-driven inelasticity
• Multi-scale second-order computational homogenization of multi-phase materials: a nested finite element solution strategy
• Multiscale modeling of the thermomechanical behavior in heterogeneous media embedding phase change materials particles
• ON TRANSFER LEARNING OF NEURAL NETWORKS USING BI-FIDELITY DATA FOR UNCERTAINTY PROPAGATION
• Quantum computing enhanced distance-minimizing data-driven computational mechanics
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Temporal homogenization formula for viscoelastic–viscoplastic model subjected to local cyclic loading
• The variational multiscale method -- a paradigm for computational mechanics
• Variational framework for distance-minimizing method in data-driven computational mechanics

This page was built for publication: Accelerated multiscale data-driven finite element analysis using mean-field homogenization method with knowledge transfer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7268261)