Search papers, labs, and topics across Lattice.
PolyCrysDiff, a conditional latent diffusion framework, is introduced for generating computable 3D polycrystalline microstructures, enabling end-to-end control over grain morphologies, orientation distributions, and spatial correlations. The method achieves high fidelity in reproducing target microstructural characteristics, demonstrated by an $R^2$ over 0.972 on grain attribute control, surpassing MRF- and CNN-based approaches. Crystal plasticity finite element method (CPFEM) simulations validate the computability and physical validity of the generated structures, allowing for systematic investigation of microstructure-property relationships.
Ditch the Markov Random Fields: a new diffusion model generates realistic 3D polycrystalline material structures with unprecedented control and accuracy, opening doors to accelerated materials design.
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.
