Logo image
Back
Neural networks for nonlinear homogenization in multiscale structural optimization: Neural networks for nonlinear
Journal article   Open access   Peer reviewed

Neural networks for nonlinear homogenization in multiscale structural optimization: Neural networks for nonlinear

Nolan Black and Ahmad R. Najafi
Structural and multidisciplinary optimization, v 68(10), 204
26 Sep 2025
DOI: https://doi.org/10.1007/s00158-025-04133-5
Featured in Collection :   Research Supported by Drexel Libraries' OA Programs
url
https://doi.org/10.1007/s00158-025-04133-5View
Published, Version of Record (VoR)Open Access via Drexel Libraries Read and Publish Program 2025CC BY V4.0,  Open

Abstract

Computational Mathematics and Numerical Analysis Research Paper Theoretical and Applied Mechanics Engineering Engineering Design
Multiscale structural optimization considers the simultaneous design of macroscale (observable) and microscale (material) features. The multiscale design space demands complex models to capture physical effects between scales, while the extended design space introduces additional numerical complexity. In this work, surrogate models based on standard finite element approaches are presented as an attractive alternative to traditional models. Fast and efficient neural network (NN) surrogate models are trained to emulate the numerical homogenization of a hyperelastic material undergoing finite deformation within a multiscale structure. Computational homogenization techniques incorporating the first-order deformation gradient are applied to resolve the effective behavior of the nonlinear microstructural material, and several NN architectures and training strategies are compared to equivalent finite element models. The NN training strategies, incorporating both forward and backward passes, introduce a Sobolev loss function of relative error norms that improves upon the state of the art. Once trained, the NN surrogates are applied to multiscale design optimization for the minimization of nonlinear compliance and the minimization of complementary work. The efficiency of NN-based surrogate models enables the comparison of traditional topology optimization approaches with their multiscale alternatives in nonlinear design.

Metrics

9 Record Views

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Interdisciplinary Applications
Engineering, Multidisciplinary
Mechanics
Logo image