EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FEM-GAN: A Physics-Supervised Deep Learning Generative Model for Elastic Porous Materials

Albert Argilaga iD

Materials · 30.06.2023 · 16 (13) · 4740

DOI: 10.3390/ma16134740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 30.06.2023. Verfasst von Albert Argilaga. Beteiligte Einrichtung: MOE Key Laboratory of Soft Soils and Geoenvironmental Engineering, Zhejiang University, Hangzhou 310058, China. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

X-ray μCT imaging is a common technique that is used to gain access to the full-field characterization of materials. Nevertheless, the process can be expensive and time-consuming, thus limiting image availability. A number of existing generative models can assist in mitigating this limitation, but they often lack a sound physical basis. This work presents a physics-supervised generative adversarial networks (GANs) model and applies it to the generation of X-ray μCT images. FEM simulations provide physical information in the form of elastic coefficients. Negative X-ray μCT images of a Hostun sand were used as the target material. During training, image batches were evaluated with nonparametric statistics to provide posterior metrics. A variety of loss functions and FEM evaluation frequencies were tested in a parametric study. The results show, that in several test scenarios, FEM-GANs-generated images proved to be better than the reference images for most of the elasticity coefficients. Although the model failed at perfectly reproducing the three out-of-axis coefficients in most cases, the model showed a net improvement with respect to the GANs reference. The generated images can be used in data augmentation, the calibration of image analysis tools, filling incomplete X-ray μCT images, and generating microscale variability in multiscale applications.

Schlagwörter

Stichwörter der Autor:innen

FEM-GANsGANsX-ray CTelasticitygenerative modelingphysics-supervisedsacrifice template

Autor:innen und Institutionen

  • MOE Key Laboratory of Soft Soils and Geoenvironmental Engineering, Zhejiang University, Hangzhou 310058, China.

ORCID-Profile: Albert Argilaga

Zitieren

APA

Argilaga, A. (2023). FEM-GAN: A Physics-Supervised Deep Learning Generative Model for Elastic Porous Materials. Materials, 16(13), 4740. https://doi.org/10.3390/ma16134740

Vancouver

Argilaga A. FEM-GAN: A Physics-Supervised Deep Learning Generative Model for Elastic Porous Materials. Materials. 2023;16(13):4740. doi:10.3390/ma16134740

BibTeX
@article{Argilaga2023,
  author = {Argilaga, Albert},
  title = {FEM-GAN: A Physics-Supervised Deep Learning Generative Model for Elastic Porous Materials},
  journal = {Materials},
  year = {2023},
  volume = {16},
  number = {13},
  pages = {4740},
  doi = {10.3390/ma16134740}
}
Kostenlos starten →