EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties

Mikhail Tashkinov, Yulia Pirogova, Evgeniy Kononov, Aleksandr Shalimov, Vadim V. Silberschmidt

Mathematics · 24.12.2024 · 13 (1) · 7

DOI: 10.3390/math13010007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 24.12.2024. Verfasst von Mikhail Tashkinov und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: research project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative adversarial neural networks with a variational autoencoder (VAE-GANs) are actively used in the field of materials design. The synthesis of random structures with nonrepeated geometry and predetermined mechanical properties is important for solving various practical problems. Geometric parameters of such artificially generated random structures can vary within certain limits compared to the training dataset, causing unpredicted fluctuations in their resulting mechanical response. This study investigates the statistical variability of mechanical and morphological characteristics of random 3D models reconstructed from 2D images using a VAE-GAN neural network. A combined multitool method employing different mathematical and statistical instruments for comparison of the reconstructed models with their corresponding originals is proposed. It includes the analysis of statistical distributions of elastic properties, morphometric parameters, and stress values. The neural network was trained on two datasets, containing models created based on Gaussian random fields. Statistical fluctuations of the mechanical and morphological parameters of the reconstructed models are analyzed. The deviation of the effective elastic modulus of the reconstructed models from that of the original ones was less than 5.7% on average. The difference between the median values of ligament thickness and distance between ligaments ranged from 3.6 to 6.5% and 2.6 to 5.2%, respectively. The median value of the surface area of the reconstructed geometries was 4.6–8.1% higher compared to the original models. It is thus shown that mechanical properties of the NN-generated structures retain the statistical variability of the corresponding originals, while the variability of the morphology is highly affected by the training set and does not depend on the configuration of the input 2D image.

Förderung

  • research project

Zitieren

APA

Tashkinov, M., Pirogova, Y., Kononov, E., Shalimov, A., & Silberschmidt, V. V. (2024). Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties. Mathematics, 13(1), 7. https://doi.org/10.3390/math13010007

Vancouver

Tashkinov M, Pirogova Y, Kononov E, Shalimov A, Silberschmidt VV. Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties. Mathematics. 2024;13(1):7. doi:10.3390/math13010007

BibTeX
@article{Tashkinov2024,
  author = {Tashkinov, Mikhail and Pirogova, Yulia and Kononov, Evgeniy and Shalimov, Aleksandr and Silberschmidt, Vadim V.},
  title = {Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties},
  journal = {Mathematics},
  year = {2024},
  volume = {13},
  number = {1},
  pages = {7},
  doi = {10.3390/math13010007}
}
Kostenlos starten →