Multiscale Analysis of Woven Composites Using Hierarchical Physically Recurrent Neural Networks
arXiv:2503.04901 · doi:10.1016/j.cma.2026.118939
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. Adopting HPRNNs for both scale transitions can avoid nonphysical behavior often observed in predictions from pure data-driven recurrent neural networks and transformer networks. 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.
27 pages, and 17 figures
References in corpus (7)
- Physics informed neural networks for continuum micromechanics
- Distributed physics informed neural network for data-efficient solution to partial differential equations
- Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate
- Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
- A Neural Network Transformer Model for Composite Microstructure Homogenization
- Symmetry-enforcing neural networks with applications to constitutive modeling
- Single- to multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: application to data-driven constitutive modeling