Prediction of Film Cooling Effectiveness on a Gas Turbine Blade Leading Edge Using ANN and CFD
-
J. O. Dávalos
,
G. Urquiza
Abstract
In this work, the area-averaged film cooling effectiveness (AAFCE) on a gas turbine blade leading edge was predicted by employing an artificial neural network (ANN) using as input variables: hole diameter, injection angle, blowing ratio, hole and columns pitch. The database used to train the network was built using computational fluid dynamics (CFD) based on a two level full factorial design of experiments. The CFD numerical model was validated with an experimental rig, where a first stage blade of a gas turbine was represented by a cylindrical specimen. The ANN architecture was composed of three layers with four neurons in hidden layer and Levenberg-Marquardt was selected as ANN optimization algorithm. The AAFCE was successfully predicted by the ANN with a regression coefficient R2<0.99 and a root mean square error RMSE=0.0038. The ANN weight coefficients were used to estimate the relative importance of the input parameters. Blowing ratio was the most influential parameter with relative importance of 40.36 % followed by hole diameter. Additionally, by using the ANN model, the relationship between input parameters was analyzed.
Funding statement: Consejo Nacional de Ciencia y Tecnología, (Grant / Award Number: ‘206393’).
Nomenclature
- A
Area (m2)
- b
bias
- f
Hyperbolic tangent sigmoid transfer function
- g
Lineal function
- I
relative importance
- In
input variable
- int
intercept
- M
blowing ratio
- N
neurons
- Out
ANN output
- Q
number of data points
- q
index of data
- s
slope
- T
temperature (°C)
- u
normalized value
- U
input data
- v
velocity (m/s)
- W
weight
- x
tangential distance
- y
Axial distance
- Subscripts
- ANN
artificial neural network
- aw
adiabatic wall
- c
cooling
- o
output
- i
input
- m
Mainstream or number of neurons in hidden layer
- min
minimum
- max
maximum
- s
number of neurons in hidden layer
- h
number of neurons in input layer
- l
number of neurons in output layer
- Greek letters
- η
cooling effectiveness
density (kg/m3)
Acknowledgments
The authors would like to acknowledge to the CONACYT 206393 project for the financial support.
References
1. Bogard DG, Thole KA. Gas turbine film cooling. J Propul Power 2006;22(2):249–70.10.2514/1.18034Search in Google Scholar
2. Bernsdorf S, Rose Martin G, Abhari R. Modeling of film cooling-part 1: experimental study of flow structure. J Turbomach 2006;128(1):141–9.10.1115/1.2098768Search in Google Scholar
3. Narzary D, Liu K, Rallabandi A, Han JC. Influence of coolant density on turbine blade film cooling using pressure sensitive paint technique. J Turbomach 2011;134(3):031006–10.10.1115/GT2010-22781Search in Google Scholar
4. Moritz N, Kusterer K, Bohn D, Sugimoto T, Tanaka R, Taniguchi T. Conjugate calculation of a film cooled blade for improvement of the leading edge cooling calculation. Propul Power Res 2013;2(1):1–9.10.1016/j.jppr.2012.10.005Search in Google Scholar
5. Zhu HR, Liu ZG. Investigation on the influence of various mainstream pressure gradients on the film cooling performances of cylindrical hole and expansion shaped holes. Int J Turbo Jet Engines 2014;31(1):1–12.10.1515/tjj-2013-0029Search in Google Scholar
6. Xingdan Z, Jingzhou Z, Xiaoming T. An experimental investigation of showerhead film cooling performance on a turbine blade. Procedia Eng 2014;99:634–45.10.1016/j.proeng.2014.12.583Search in Google Scholar
7. Colban W, Thole KA, Haendler MA. Comparison of cylindrical and fan-shaped film-cooling holes on a vane endwall at low and high freestream turbulence levels. J Turbomach 2008;130(3):031007–9.10.1115/1.2720493Search in Google Scholar
8. Kim Y, Kim SM. Influence of shaped injection holes on a turbine blade leading edge film cooling. Int J Heat Mass Transfer 2012;47(2):245–56.10.1016/j.ijheatmasstransfer.2003.07.008Search in Google Scholar
9. Abdullah K, Funazaki O, Takeomi I. Experimental investigations on aero-thermal interaction of film cooling airs ejected from multiple holes: shallow hole angle. In: Proceedings of ASME Turbo Expo 2013: Turbine Technical Conference and Exposition, GT2013-95346, 2013.Search in Google Scholar
10. Liu C, Zhu H, Zhang X, Xu D, Zhang Z. Experimental investigation on the leading edge film cooling of cylindrical and laid-back holes with different radial holes. Int J Heat Mass Transfer 2014;71:615–25.10.1016/j.ijheatmasstransfer.2013.12.050Search in Google Scholar
11. Yu Z, Xu T, Li J, Ma L, Xu T. Comparison of a series of double chamber model with various hole angles for enhancing cooling effectiveness. Int Commun Heat Mass Transfer 2013;44:38–44.10.1016/j.icheatmasstransfer.2013.03.002Search in Google Scholar
12. Naghashnejad N, Amanifard N, Deylami HM. A predictive model based on a 3D computational approach for film cooling effectiveness over a flat plate using GMDH-Type neural networks. Heat Mass Transfer 2014;50(1):139–49.10.1007/s00231-013-1239-3Search in Google Scholar
13. Wang W, Gao J, Xu L, Shi X. Experimental study and prediction of film cooling effectiveness for a guide vane in heavy gas turbines, In: Proceedings of the 15th International heat Transfer Conference, Paper No. IHTC-9965, 2014.10.1615/IHTC15.hte.009965Search in Google Scholar
14. Wang C, Zhang J, Zhou J, Alting SA. Prediction of film cooling effectiveness based on support vector machines. Appl Therm Eng 2015;84:82–93.10.1016/j.applthermaleng.2015.03.024Search in Google Scholar
15. Lee K, Choi D, Kim K. Optimization of ejection angles of doubled-jet-film-cooling holes using RBNN model. Int J Therm Sci 2013;73:69–78.10.1016/j.ijthermalsci.2013.05.015Search in Google Scholar
16. Dyson TE, Bogard DG, Piggush JD, Kohli A. Overall effectiveness for a film cooled turbine blade leading edge with varying hole pitch. J Turbomach 2013;135(3):031011.10.1115/1.4006872Search in Google Scholar
17. Lim CH, Pullan G, Ireland P. Influence of film cooling hole angles and geometries on aerodynamic loss and net heat flux reduction, In: Asme 2011 Turbo Expo: Turbine technical conference and exposition GT2011-45721, 2011.10.1115/GT2011-45721Search in Google Scholar
18. Han JC, Rallabandi AP. Turbine blade film cooling using PSP technique. Front Heat Mass Transfer 2010;1(1):1–21.10.5098/hmt.v1.1.3001Search in Google Scholar
19. Gomes RA, Niehius R. Film cooling on highly loaded blades with main flow separation-part II: overall film cooling effectiveness. J Turbomach 2012;135(1):011044–9.10.1115/1.4006569Search in Google Scholar
20. Teng S, Sohn DK, Han JC. Unsteady wake effects on film temperature and effectiveness distributions for a gas turbine blade. J Turbomach 2000;122(2):340–7.10.1115/1.555457Search in Google Scholar
21. Gao Z, Narzary D, Han JC. Upstream vortex effect on turbine platform film cooling with typical purge flow. J Thermophys Heat Transfer 2012;26(1):75–84.10.2514/1.42411Search in Google Scholar
22. Li X, Wang T. Effects of various modeling schemes on mist film cooling simulation. J Heat Transfer 2007;129(4):472–82.10.1115/1.2709959Search in Google Scholar
23. Van den Braembussche RA. Numerical optimization for advanced turbomachinery design. In: Dominique Thévenin and Gábor Janiga Optimization and computational fluid dynamics. Berlin: Springer, 2008:147–90.10.1007/978-3-540-72153-6_6Search in Google Scholar
24. Garson GD. Interpreting neural-network connection weights. AI Expert 1991;6(4):47–51.Search in Google Scholar
© 2018 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Jet Engines – The New Masters of Advanced Flight Control
- Prediction of Film Cooling Effectiveness on a Gas Turbine Blade Leading Edge Using ANN and CFD
- Sustainability Metrics of a Small Scale Turbojet Engine
- Coupling Network Computing Applications in Air-cooled Turbine Blades Optimization
- Performance Enhancement of One and Two-Shaft Industrial Turboshaft Engines Topped With Wave Rotors
- Semi-Immersive Virtual Turbine Engine Simulation System
- A Novel Modeling Method for Aircraft Engine Using Nonlinear Autoregressive Exogenous (NARX) Models Based on Wavelet Neural Networks
- Defining the Ecological Coefficient of Performance for an Aircraft Propulsion System
- Investigation on the Accuracy of Superposition Predictions of Film Cooling Effectiveness
- Computational Investigations in Rectangular Convergent and Divergent Ribbed Channels
Articles in the same Issue
- Frontmatter
- Jet Engines – The New Masters of Advanced Flight Control
- Prediction of Film Cooling Effectiveness on a Gas Turbine Blade Leading Edge Using ANN and CFD
- Sustainability Metrics of a Small Scale Turbojet Engine
- Coupling Network Computing Applications in Air-cooled Turbine Blades Optimization
- Performance Enhancement of One and Two-Shaft Industrial Turboshaft Engines Topped With Wave Rotors
- Semi-Immersive Virtual Turbine Engine Simulation System
- A Novel Modeling Method for Aircraft Engine Using Nonlinear Autoregressive Exogenous (NARX) Models Based on Wavelet Neural Networks
- Defining the Ecological Coefficient of Performance for an Aircraft Propulsion System
- Investigation on the Accuracy of Superposition Predictions of Film Cooling Effectiveness
- Computational Investigations in Rectangular Convergent and Divergent Ribbed Channels
