An official website of the United States government
Optimization and uncertainty quantification have been playing an increasingly important role in computational hemodynamics. However, existing methods based on principled modeling and classic numerical techniques have faced significant challenges, particularly when it comes to complex three-dimensional (3D) patient-specific shapes in the real world. First, it is notoriously challenging to parameterize the input space of arbitrary complex 3D geometries. Second, the process often involves massive forward simulations, which are extremely computationally demanding or even infeasible. We propose a novel deep learning surrogate modeling solution to address these challenges and enable rapid hemodynamic predictions. Specifically, a statistical generative model for 3D patient-specific shapes is developed based on a small set of baseline patient-specific geometries. An unsupervised shape correspondence solution is used to enable geometric morphing and scalable shape synthesis statistically. Moreover, a simulation routine is developed for automatic data generation by automatic meshing, boundary setting, simulation, and post-processing. An efficient supervised learning solution is proposed to map the geometric inputs to the hemodynamics predictions in latent spaces. Numerical studies on aortic flows are conducted to demonstrate the effectiveness and merit of the proposed techniques.
more »
« less
This content will become publicly available on May 1, 2026
Exascale granular microstructure reconstruction in 3D volumes of arbitrary geometries with generative learning
Reconstructing 3D granular microstructures within volumes of arbitrary geometries from limited 2D image data is crucial for predicting the material properties, as well as performances of structural components accounting for material microstructural effects. We present a novel generative learning framework that enables exascale reconstruction of granular microstructures within complex 3D geometric volumes. Building upon existing transfer learning techniques using pre-trained convolutional neural networks (CNN), we introduce several key innovations to overcome the difficulties inherent in arbitrary geometries. Our framework incorporates periodic boundary conditions using circular padding techniques, ensuring continuity and representativeness of the reconstructed microstructures. We also introduce a novel seamless transition reconstruction (STR) method that creates statistically equivalent transition zones to integrate multiple pre-existing 3D microstructure volumes. Based on STR, we propose a cost-effective strategy for reconstructing microstructures within complex geometric volumes, minimizing computational waste. Validation through numerical experiments using kinetic Monte Carlo simulations demonstrates accurate reproduction of grain statistics, including grain size distributions and morphology. A case study involving the reconstruction of a 4-blade propeller microstructure illustrates the method’s capability to efficiently handle complex geometries. The proposed framework significantly reduces computational demands while maintaining high reconstruction quality, paving the way for scalable microstructure reconstruction in materials design and analysis.
more »
« less
- Award ID(s):
- 2142290
- PAR ID:
- 10639923
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Acta materialia
- Volume:
- 289
- ISSN:
- 1873-2453
- Subject(s) / Keyword(s):
- Granular microstructure Stochastic reconstruction Deep learning Kinetic Monte Carlo Exascale computing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We introduce a novel method for reconstructing the 3D geometry of botanical trees from single photographs. Faithfully reconstructing a tree from single-view sensor data is a challenging and open problem because many possible 3D trees exist that fit the tree's shape observed from a single view. We address this challenge by defining a reconstruction pipeline based on three neural networks. The networks simultaneously mask out trees in input photographs, identify a tree's species, and obtain its 3D radial bounding volume - our novel 3D representation for botanical trees. Radial bounding volumes (RBV) are used to orchestrate a procedural model primed on learned parameters to grow a tree that matches the main branching structure and the overall shape of the captured tree. While the RBV allows us to faithfully reconstruct the main branching structure, we use the procedural model's morphological constraints to generate realistic branching for the tree crown. This constraints the number of solutions of tree models for a given photograph of a tree. We show that our method reconstructs various tree species even when the trees are captured in front of complex backgrounds. Moreover, although our neural networks have been trained on synthetic data with data augmentation, we show that our pipeline performs well for real tree photographs. We evaluate the reconstructed geometries with several metrics, including leaf area index and maximum radial tree distances.more » « less
-
Abstract The deformation behavior of Ti-6Al-4V titanium alloy is significantly influenced by slip localized within crystallographic slip bands. Experimental observations reveal that intense slip bands in Ti-6Al-4V form at strains well below the macroscopic yield strain and may serially propagate across grain boundaries, resulting in long-range localization that percolates through the microstructure. These connected, localized slip bands serve as potential sites for crack initiation. Although slip localization in Ti-6Al-4V is known to be influenced by various factors, an investigation of optimal microstructures that limit localization remains lacking. In this work, we develop a novel strategy that integrates an explicit slip band crystal plasticity technique, graph networks, and neural network models to identify Ti-6Al-4V microstructures that reduce the propensity for strain localization. Simulations are conducted on a dataset of 3D polycrystals, each represented as a graph to account for grain neighborhood and connectivity. The results are then used to train neural network surrogate models that accurately predict localization-based properties of a polycrystal, given its microstructure. These properties include the ratio of slip accumulated in the band to that in the matrix, fraction of total applied strain accommodated by slip bands, and spatial connectivity of slip bands throughout the microstructure. The initial dataset is enriched by synthetic data generated by the surrogate models, and a grid search optimization is subsequently performed to find optimal microstructures. Describing a 3D polycrystal with only a few features and a combination of graph and neural network models offer robustness compared to the alternative approaches without compromising accuracy. We show that while each material property is optimized through a unique microstructure solution, elongated grain shape emerges as a recurring feature among all optimal microstructures. This finding suggests that designing microstructures with elongated grains could potentially mitigate strain localization without compromising strength.more » « less
-
Abstract Biomineralized materials are sophisticated material systems with hierarchical 3D material architectures, which are broadly used as model systems for fundamental mechanical, materials science, and biomimetic studies. The current knowledge of the structure of biological materials is mainly based on 2D imaging, which often impedes comprehensive and accurate understanding of the materials’ intricate 3D microstructure and consequently their mechanics, functions, and bioinspired designs. The development of 3D techniques such as tomography, additive manufacturing, and 4D testing has opened pathways to study biological materials fully in 3D. This review discusses how applying 3D techniques can provide new insights into biomineralized materials that are either well known or possess complex microstructures that are challenging to understand in the 2D framework. The diverse structures of biomineralized materials are characterized based on four universal structural motifs. Nacre is selected as an example to demonstrate how the progression of knowledge from 2D to 3D can bring substantial improvements to understanding the growth mechanism, biomechanics, and bioinspired designs. State‐of‐the‐art multiscale 3D tomographic techniques are discussed with a focus on their integration with 3D geometric quantification, 4D in situ experiments, and multiscale modeling. Outlook is given on the emerging approaches to investigate the synthesis–structure–function–biomimetics relationship.more » « less
-
A cornerstone of materials science is that material properties are determined by their microstructure. While the community has already developed a wide variety of approaches to describe microstructure, most of these are tailored to specific material systems or classes. This work proposes a way to quantitatively measure the similarity of microstructures based on the geometry of the grain boundary network, a feature which is fundamental to and characteristic of all polycrystalline materials. Specifically, a distance on all single-phase polycrystalline microstructures is proposed such that two microstructures that are close with regard to the distance have grain boundary networks that are statistically similar in all geometric respects below a user-specified length scale. Given a pair of micrographs, the distance is approximated by sampling windows from the micrographs, defining a distance between pairs of windows, and finding a window matching that minimizes the sum of the pairwise window distances. The approach is used to compare a variety of synthetic microstructures and to develop a procedure to query a proof-of-concept database suitable for general single-phase polycrystalline microstructures.more » « less
