Multiscale deep learning for woven composites

Woven composites exhibit a complex hierarchical structure with multiple heterogeneous sub-scales, stemming from microscale fiber arrangements and mesoscale interlacing patterns, necessitating sophisticated modeling approaches to accurately capture their intricate multiscale nature.
In our recently published paper, we are proposing a data-driven approach for multi-scale modelling of elastic woven composites where a heterogenous meso-structure and a wide variety of micro-structures are considered. Open access to the paper: https://www.sciencedirect.com/science/article/pii/S0020768323003499