EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Approaches to Close the Filtered Two-Fluid Model for Gas–Solid Flows: Models for Subgrid Drag Force and Solid Phase Stress

Baptiste Hardy, Stefanie Rauchenzauner, Pascal Fede, Simon Schneiderbauer, Olivier Simonin, Sankaran Sundaresan, Ali Ozel

Industrial & Engineering Chemistry Research · 08.05.2024 · 63 (18) · 8383-8400

DOI: 10.1021/acs.iecr.3c04652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Industrial & Engineering Chemistry Research, online erschienen am 24.04.2024. Verfasst von Baptiste Hardy und 6 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wallonie-Bruxelles International, Institut Carnot Isifor.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gas-particle flows are commonly simulated through two-fluid model at industrial-scale. However, these simulations need very fine grid to have accurate flow predictions, which is prohibitively demanding in terms of computational resources. To circumvent this problem, the filtered two-fluid model has been developed, where large-scale flow field is numerically resolved and small-scale fluctuations are accounted for through subgrid-scale modeling. In this study, we have performed fine-grid two-fluid simulations of dilute gas-particle flows in periodic domains and applied explicit filtering to generate datasets. Then, these datasets have been used to develop artificial neural network (ANN) models for closures such as the filtered drag force and solid phase stress for the filtered two-fluid model. The set of input variables for the subgrid drag force ANN model that has been found previously to work well for dense flow regimes is found to work as well for the dilute regime. In addition, we present a Galilean invariant tensor basis neural network (TBNN) model for the filtered solid phase stress which can capture nicely the anisotropic nature of the solid phase stress arising from subgrid-scale velocity fluctuations. Finally, the predictions provided by this new TBNN model are compared with those obtained from a simple eddy-viscosity ANN model.

Förderung

  • Wallonie-Bruxelles International
  • Institut Carnot Isifor

Zitieren

APA

Hardy, B., Rauchenzauner, S., Fede, P., Schneiderbauer, S., Simonin, O., Sundaresan, S., & Ozel, A. (2024). Machine Learning Approaches to Close the Filtered Two-Fluid Model for Gas–Solid Flows: Models for Subgrid Drag Force and Solid Phase Stress. Industrial & Engineering Chemistry Research, 63(18), 8383-8400. https://doi.org/10.1021/acs.iecr.3c04652

Vancouver

Hardy B, Rauchenzauner S, Fede P, Schneiderbauer S, Simonin O, Sundaresan S, et al. Machine Learning Approaches to Close the Filtered Two-Fluid Model for Gas–Solid Flows: Models for Subgrid Drag Force and Solid Phase Stress. Industrial & Engineering Chemistry Research. 2024;63(18):8383-8400. doi:10.1021/acs.iecr.3c04652

BibTeX
@article{Hardy2024,
  author = {Hardy, Baptiste and Rauchenzauner, Stefanie and Fede, Pascal and Schneiderbauer, Simon and Simonin, Olivier and Sundaresan, Sankaran and Ozel, Ali},
  title = {Machine Learning Approaches to Close the Filtered Two-Fluid Model for Gas–Solid Flows: Models for Subgrid Drag Force and Solid Phase Stress},
  journal = {Industrial & Engineering Chemistry Research},
  year = {2024},
  volume = {63},
  number = {18},
  pages = {8383--8400},
  doi = {10.1021/acs.iecr.3c04652}
}
Kostenlos starten →