Numerical and data-driven modeling of spall failure in polycrystalline ductile materials

TL;DR

This paper develops and compares deep learning surrogate models, including U-FNO and 3D U-Net, to predict spall failure in polycrystalline materials under high strain rates, aiming to reduce computational costs in dynamic fracture simulations.

Contribution

The study introduces and evaluates three neural network architectures for predicting spall failure, highlighting U-FNO's accuracy and computational efficiency over FNO-3D.

Findings

U-FNO and 3D U-Net outperform FNO-3D in accuracy.

U-FNO achieves similar accuracy to 3D U-Net.

U-FNO requires nearly twice the training effort of 3D U-Net.

Abstract

Developing materials with tailored mechanical performance requires iteration over a large number of proposed designs. When considering dynamic fracture, experiments at every iteration are usually infeasible. While high-fidelity, physics-based simulations can potentially reduce experimental efforts, they remain computationally expensive. As a faster alternative, key dynamic properties can be predicted directly from microstructural images using deep-learning surrogate models. In this work, the spallation of ductile polycrystals under plate-impact loading at strain rates of O(10^6 s^-1) is considered. A physics-based numerical model that couples crystal plasticity and a cohesive zone model is used to generate data for the surrogate models. Three architectures - 3D U-Net, 3D Fourier Neural Operator (FNO-3D), and U-FNO were trained on the particle-velocity field data from the numerical model. The generalization of the models was evaluated using microstructures with varying grain sizes and aspect ratios. U-FNO and 3D U-Net performed significantly better than FNO-3D across all datasets. Furthermore, U-FNO and 3D U-Net exhibited comparable accuracy for every metric considered in this study. However, training the U-FNO requires almost twice the computational effort compared to the 3D U-Net, making it a desirable option for a surrogate model.