Accelerating CFD-driven training of transition and turbulence models for turbine flows by one-shot and real-time transformer integration
Open Access
- 29 November 2025
- journal article
- Published by Elsevier in Computers & Fluids
- Vol. 306
Abstract
No abstract availableFunding Information
- International Council of Shopping Centers
- Australian Research Council (FT190100072)
- H2020 European Research Council (CUP B83C22002830001)
- Indian Institute of Technology Jodhpur
- University of Melbourne
- European Commission
This publication has 20 references indexed in Scilit:
- Symbolic turbulence model development for complex-geometry flows exploiting language model-based transfer learningPhysics of Fluids, 2025
- Exploiting semantic backpropagation to impose near-wall scaling constraints in machine-learned symbolic subgrid-scale closuresPhysics of Fluids, 2025
- A Reformulation of the Laminar Kinetic Energy Model to Enable Multi-mode Transition PredictionsFlow, Turbulence and Combustion, 2024
- Multi-objective CFD-driven development of coupled turbulence closure modelsJournal of Computational Physics, 2022
- Towards robust and accurate Reynolds-averaged closures for natural convection via multi-objective CFD-driven machine learningInternational Journal of Heat and Mass Transfer, 2022
- RANS turbulence model development using CFD-driven machine learningJournal of Computational Physics, 2020
- Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertaintyPhysics of Fluids, 2015
- A One-Equation Local Correlation-Based Transition ModelFlow, Turbulence and Combustion, 2015
- On explicit algebraic stress models for complex turbulent flowsJournal of Fluid Mechanics, 1993
- A more general effective-viscosity hypothesisJournal of Fluid Mechanics, 1975