Work

Multiscale analysis of woven composites using hierarchical physically recurrent neural networks

Year: 2026

Type: article

Abstract: Multiscale homogenization of woven composites requires detailed micromechanical evaluations, leading to high computational costs. Data-driven surrogate models based on neural networks address this challenge but often suffer from big data requirements, limited interpretability, and poor extrapolation capabilities. This study introduces a Hierarchical Physically Recurrent Neural Network (HPRNN) employing two levels of surrogate modeling. First, Physically Recurrent Neural Networks (PRNNs) are trained to capture the nonlinear elasto-plastic behavior of warp and weft yarns using micromechanical data. In a second scale transition, a physics-encoded meso-to-macroscale model integrates these yarn surrogates with the matrix constitutive model, embedding physical properties directly into the latent space. By adopting HPRNNs, nonphysical behavior often observed in predictions from pure data-driven recurrent neural networks and transformer networks can be avoided. This results in better generalization under complex cyclic loading conditions. The framework offers a computationally efficient and explainable solution for multiscale modeling of woven composites.

Source: Computer Methods in Applied Mechanics and Engineering

DOI: 10.1016/j.cma.2026.118939

Authors: Ehsan Ghane, Marina A. Maia, Iuri B.C.M. Rocha, Martin Fagerström, Mohsen Mirkhalaf

Institutions: University of Gothenburg, Delft University of Technology, Chalmers University of Technology

Language: English

Topic: Composite Material Mechanics

Subfield: Mechanics of Materials

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,830

Funders: Technische Universiteit Delft, VINNOVA, Vetenskapsrådet, Göteborgs Universitet