PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures

TL;DR

PolyCrysDiff is a novel conditional latent diffusion framework that enables realistic, controllable, and computable 3D microstructure generation of polycrystalline materials, facilitating better understanding and design of their properties.

Contribution

We introduce PolyCrysDiff, the first end-to-end diffusion-based method for controllable 3D polycrystalline microstructure generation, outperforming existing approaches in fidelity and controllability.

Findings

PolyCrysDiff faithfully reproduces grain morphology and orientation distributions.

It achieves an R^2 over 0.972 on grain attribute control.

Generated microstructures are validated through crystal plasticity simulations.

Abstract

The three-dimensional (3D) microstructures of polycrystalline materials exert a critical influence on their mechanical and physical properties. Realistic, controllable construction of these microstructures is a key step toward elucidating structure-property relationships, yet remains a formidable challenge. Herein, we propose PolyCrysDiff, a framework based on conditional latent diffusion that enables the end-to-end generation of computable 3D polycrystalline microstructures. Comprehensive qualitative and quantitative evaluations demonstrate that PolyCrysDiff faithfully reproduces target grain morphologies, orientation distributions, and 3D spatial correlations, while achieving an $R^2$ over 0.972 on grain attributes (e.g., size and sphericity) control, thereby outperforming mainstream approaches such as Markov random field (MRF)- and convolutional neural network (CNN)-based methods. The computability and physical validity of the generated microstructures are verified through a series of crystal plasticity finite element method (CPFEM) simulations. Leveraging PolyCrysDiff's controllable generative capability, we systematically elucidate how grain-level microstructural characteristics affect the mechanical properties of polycrystalline materials. This development is expected to pave a key step toward accelerated, data-driven optimization and design of polycrystalline materials.