EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Neural network-augmented eddy viscosity closures for turbulent premixed jet flames

Priyesh Kakka, Jonathan F. MacArt

Combustion and Flame · 2025-08 · 278 · 114241

DOI: 10.1016/j.combustflame.2025.114241 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Combustion and Flame, 2025-08. Verfasst von Priyesh Kakka und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation, Office of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extending gradient-type turbulence closures to turbulent premixed flames is challenging due to the significant influence of combustion heat release. We incorporate a deep neural network (DNN) into Reynolds-averaged Navier--Stokes (RANS) models for the turbulent viscosity and thermal conductivity as nonlinear functions of the local flow state and thermochemical gradients. Our models are optimized over the RANS partial differential equations (PDEs) using an adjoint-based data assimilation procedure. Because we directly target the RANS solution, as opposed to the unclosed terms, successfully trained models are guaranteed to improve the in-sample accuracy of the DNN-augmented RANS predictions. We demonstrate the learned closures for in- and out-of-sample $\textit{a posteriori}$ RANS predictions of compressible, premixed, turbulent jet flames with turbulent Damk\"ohler numbers spanning the gradient- and counter-gradient transport regimes. The DNN-augmented RANS predictions have one to two orders of magnitude lower spatiotemporal mean-squared error than those using a baseline $k$--$\epsilon$ model, even for Damk\"ohler numbers far from those used for training. This demonstrates the accuracy, stability, and generalizability of the PDE-constrained modeling approach for turbulent jet flames over this relatively wide Damk\"ohler number range.

Förderung

  • National Science Foundation
  • Office of Science

Zitieren

APA

Kakka, P., & MacArt, J. F. (2025). Neural network-augmented eddy viscosity closures for turbulent premixed jet flames. Combustion and Flame, 278, 114241. https://doi.org/10.1016/j.combustflame.2025.114241

Vancouver

Kakka P, MacArt JF. Neural network-augmented eddy viscosity closures for turbulent premixed jet flames. Combustion and Flame. 2025;278:114241. doi:10.1016/j.combustflame.2025.114241

BibTeX
@article{Kakka2025,
  author = {Kakka, Priyesh and MacArt, Jonathan F.},
  title = {Neural network-augmented eddy viscosity closures for turbulent premixed jet flames},
  journal = {Combustion and Flame},
  year = {2025},
  volume = {278},
  pages = {114241},
  doi = {10.1016/j.combustflame.2025.114241}
}
Kostenlos starten →