A form of supervised machine learning was applied to highly resolved large-eddy simulation (LES) data to develop non linear 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 (EASM) and heat-flux closures based on either the gradient diffusion or the generalized gradient diffusion approaches. Following a-priori assessment, the new models were used for steady RANS calculations of both thin and thick trailing-edge slot geometries, testing their performance and robustness. Overall, the best agreement with LES data was found when training the RANS model in the near wall region where high levels of anisotropy exist and using the mean squared error of the anisotropy tensor as cost function. In the case of the thin lip geometry, combining an improved EASM model with the standard eddy-diffusivity model predicted the adiabatic wall effectiveness in good agreement with the LES and experimental data. Crucially, the obtained model was also applied to different blowing ratios of the thin lip geometry and a significant improvement in the predictive accuracy of adiabatic wall effectiveness was observed for those cases not previously seen in the training process. For the thick lip case the match with reference values deteriorated due to the presence of large-scale, relative to the slot height, vortex shedding. The machine-learning algorithm was therefore also used to ‘learn’ an appropriate closure for the turbulent heat flux vector. The constructed scalar flux model, in conjunction with a trained RANS model, was found to have the capability to further improve the prediction of the adiabatic wall effectiveness.
Skip Nav Destination
ASME Turbo Expo 2018: Turbomachinery Technical Conference and Exposition
June 11–15, 2018
Oslo, Norway
Conference Sponsors:
- International Gas Turbine Institute
ISBN:
978-0-7918-5108-1
PROCEEDINGS PAPER
Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot Available to Purchase
R. D. Sandberg,
R. D. Sandberg
University of Melbourne, Parkville, Australia
Search for other works by this author on:
R. Tan,
R. Tan
University of Melbourne, Parkville, Australia
Search for other works by this author on:
J. Weatheritt,
J. Weatheritt
University of Melbourne, Parkville, Australia
Search for other works by this author on:
A. Ooi,
A. Ooi
University of Melbourne, Parkville, Australia
Search for other works by this author on:
A. Haghiri,
A. Haghiri
University of Melbourne, Parkville, Australia
Search for other works by this author on:
V. Michelassi,
V. Michelassi
Baker Hughes, a GE company, Florence, Italy
Search for other works by this author on:
G. Laskowski
G. Laskowski
General Electric Aviation, Lynn, MA
Search for other works by this author on:
R. D. Sandberg
University of Melbourne, Parkville, Australia
R. Tan
University of Melbourne, Parkville, Australia
J. Weatheritt
University of Melbourne, Parkville, Australia
A. Ooi
University of Melbourne, Parkville, Australia
A. Haghiri
University of Melbourne, Parkville, Australia
V. Michelassi
Baker Hughes, a GE company, Florence, Italy
G. Laskowski
General Electric Aviation, Lynn, MA
Paper No:
GT2018-75444, V05AT12A007; 13 pages
Published Online:
August 30, 2018
Citation
Sandberg, RD, Tan, R, Weatheritt, J, Ooi, A, Haghiri, A, Michelassi, V, & Laskowski, G. "Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot." Proceedings of the ASME Turbo Expo 2018: Turbomachinery Technical Conference and Exposition. Volume 5A: Heat Transfer. Oslo, Norway. June 11–15, 2018. V05AT12A007. ASME. https://doi.org/10.1115/GT2018-75444
Download citation file:
58
Views
Related Proceedings Papers
Related Articles
Applying Machine Learnt Explicit Algebraic Stress and Scalar Flux Models to a Fundamental Trailing Edge Slot
J. Turbomach (October,2018)
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)
Related Chapters
Automatic Classification of Persian Texts Employing Keywords
International Conference on Computer Research and Development, 5th (ICCRD 2013)
Machine Learning Methods for Data Assimilation
Intelligent Engineering Systems through Artificial Neural Networks, Volume 20
Boosting Classification Accuracy with Samples Chosen from a Validation Set
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17