EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine-Learning Strategies for Transition–Turbulence Modeling for Low-Pressure Turbines With Unsteady Inflow Conditions

Yue Gu, Yuan Fang, Harshal D. Akolekar, Roberto Pacciani, Michele Marconcini, Andrew S. H. Ooi, Richard D. Sandberg

Journal of Turbomachinery · 01.11.2026 · 148 (11)

DOI: 10.1115/1.4072569 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Turbomachinery, online erschienen am 25.08.2026. Verfasst von Yue Gu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsteady flow behavior induced by wake–blade interactions is crucial for the operational efficiency, aerodynamic stability, and fatigue life of low-pressure turbines (LPTs), and yet remains challenging to capture with (unsteady) Reynolds-averaged Navier–Stokes (RANS) calculations. This article focuses on a more reliable estimation of unsteady wake-induced losses, arising primarily from wake mixing and boundary-layer transition under periodic disturbances. To achieve this, the computational fluid dynamics-driven training framework is, for the first time, tailored to LPT flow unsteadiness, enabling revisions of both the transition and turbulence models. First, new physics-related features are incorporated into turbulence closure formulations for automated wake-region differentiation, and a new transition-model output is introduced to capture unsteady wake-induced transition. Second, model evaluation metrics are supplemented with phase-lock averaged cost functions to ensure consistent improvement throughout the entire unsteady cycle. The integration of transition and turbulence modeling components is achieved in a sequential manner. A comprehensive assessment of both transition and turbulence models is performed using metrics of time-averaged and phase-lock averaged flow features along with secondary statistics, all of which demonstrate solid improvements over the baseline. Detailed model interpretation is also presented to reveal underlying physical insights. Moreover, a posteriori validation with the machine-learnt transition–turbulence model on different incoming wake frequencies exhibits robust performance, significantly improving the prediction of both wake losses and transition behavior, not only in a mean sense but also for individual phases. This study highlights the potential of RANS-model development for unsteady multi-stage turbomachinery configurations and provides physical insights into wake-induced unsteadiness in LPTs.

Förderung

  • European Commission

Zitieren

APA

Gu, Y., Fang, Y., Akolekar, H. D., Pacciani, R., Marconcini, M., Ooi, A. S. H., & Sandberg, R. D. (2026). Machine-Learning Strategies for Transition–Turbulence Modeling for Low-Pressure Turbines With Unsteady Inflow Conditions. Journal of Turbomachinery, 148(11). https://doi.org/10.1115/1.4072569

Vancouver

Gu Y, Fang Y, Akolekar HD, Pacciani R, Marconcini M, Ooi ASH, et al. Machine-Learning Strategies for Transition–Turbulence Modeling for Low-Pressure Turbines With Unsteady Inflow Conditions. Journal of Turbomachinery. 2026;148(11). doi:10.1115/1.4072569

BibTeX
@article{Gu2026,
  author = {Gu, Yue and Fang, Yuan and Akolekar, Harshal D. and Pacciani, Roberto and Marconcini, Michele and Ooi, Andrew S. H. and Sandberg, Richard D.},
  title = {Machine-Learning Strategies for Transition–Turbulence Modeling for Low-Pressure Turbines With Unsteady Inflow Conditions},
  journal = {Journal of Turbomachinery},
  year = {2026},
  volume = {148},
  number = {11},
  doi = {10.1115/1.4072569}
}
Kostenlos starten →