Machine learning was applied to large-eddy simulation (LES) data to develop nonlinear turbulence stress and heat flux closures with increased prediction accuracy for trailing-edge cooling slot cases. The LES data were generated for a thick and a thin trailing-edge slot and shown to agree well with experimental data, thus providing suitable training data for model development. A gene expression programming (GEP) based algorithm was used to symbolically regress novel nonlinear explicit algebraic stress models and heat-flux closures based on either the gradient diffusion or the generalized gradient diffusion approaches. Steady Reynolds-averaged Navier–Stokes (RANS) calculations were then conducted with the new explicit algebraic stress models. The best overall agreement with LES data was found when selecting the near wall region, where high levels of anisotropy exist, as training region, and using the mean squared error of the anisotropy tensor as cost function. For the thin lip geometry, the adiabatic wall effectiveness was predicted in good agreement with the LES and experimental data when combining the GEP-trained model with the standard eddy-diffusivity model. Crucially, the same model combination also produced significant improvement in the predictive accuracy of adiabatic wall effectiveness for different blowing ratios (BRs), despite not having seen those in the training process. For the thick lip case, the match with reference values deteriorated due to the presence of large-scale, relative to slot height, vortex shedding. A GEP-trained scalar flux model, in conjunction with a trained RANS model, was found to significantly improve the prediction of the adiabatic wall effectiveness.
Skip Nav Destination
Article navigation
October 2018
Research-Article
Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot
R. D. Sandberg,
R. D. Sandberg
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
e-mail: richard.sandberg@unimelb.edu.au
University of Melbourne,
Parkville 3010, VIC, Australia
e-mail: richard.sandberg@unimelb.edu.au
Search for other works by this author on:
R. Tan,
R. Tan
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
Search for other works by this author on:
J. Weatheritt,
J. Weatheritt
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
Search for other works by this author on:
A. Ooi,
A. Ooi
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
Search for other works by this author on:
A. Haghiri,
A. Haghiri
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
Search for other works by this author on:
G. Laskowski
G. Laskowski
Search for other works by this author on:
R. D. Sandberg
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
e-mail: richard.sandberg@unimelb.edu.au
University of Melbourne,
Parkville 3010, VIC, Australia
e-mail: richard.sandberg@unimelb.edu.au
R. Tan
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
J. Weatheritt
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
A. Ooi
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
A. Haghiri
Department of Mechanical Engineering,
University of Melbourne,
Parkville 3010, VIC, Australia
University of Melbourne,
Parkville 3010, VIC, Australia
V. Michelassi
G. Laskowski
1Corresponding author.
Contributed by the International Gas Turbine Institute (IGTI) of ASME for publication in the JOURNAL OF TURBOMACHINERY. Manuscript received August 15, 2018; final manuscript received August 21, 2018; published online September 28, 2018. Editor: Kenneth Hall.
J. Turbomach. Oct 2018, 140(10): 101008 (11 pages)
Published Online: September 28, 2018
Article history
Received:
August 15, 2018
Revised:
August 21, 2018
Citation
Sandberg, R. D., Tan, R., Weatheritt, J., Ooi, A., Haghiri, A., Michelassi, V., and Laskowski, G. (September 28, 2018). "Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot." ASME. J. Turbomach. October 2018; 140(10): 101008. https://doi.org/10.1115/1.4041268
Download citation file:
Get Email Alerts
Related Articles
Machine Learning for the Development of Data-Driven Turbulence Closures in Coolant Systems
J. Turbomach (August,2022)
Reynolds-Averaged Navier–Stokes Equations for Turbulence Modeling
Appl. Mech. Rev (July,2009)
A DATA DRIVEN METHOD FOR THE DERIVATION OF EXPLICIT ALGEBRAIC REYNOLDS STRESS MODELS APPLIED TO THE WAKE LOSSES OF LOW-PRESSURE TURBINE CASCADES
J. Turbomach (January,0001)
A Large-Eddy Simulation–Linear-Eddy Model Study of Preferential Diffusion Processes in a Partially Premixed Swirling Combustor With Synthesis Gases
J. Eng. Gas Turbines Power (March,2017)
Related Proceedings Papers
Related Chapters
Completing the Picture
Air Engines: The History, Science, and Reality of the Perfect Engine
Mathematical Background
Vibrations of Linear Piezostructures
The Impact of Long-Term Memory in the Iterated Prisoner's Dilemma
Intelligent Engineering Systems through Artificial Neural Networks