Feed-forward artificial neural network as surrogate model to predict lift and drag coefficient of NACA airfoil and searching of maximum lift-to-drag ratio

• Autorzy: Kieszek Rafał , Majcher Maciej , Syta Borys , Kozakiewicz Adam

Identyfikatory

DOI

10.15632/jtam-pl/189805

• Języki publikacji: EN

Abstrakty

EN

The problem of computation time in numerical calculations of aerodynamics has been studied by many research centres. In this work, a feed forward artificial neural network (FF-ANN) was used to determine the dependence of lift and drag coefficients on the angle of attack for NACA four-digit families. A panel method was used to generate the data needed to train the FF-ANNs. Optimisation using a genetic algorithm and a neural metamodel resulted in a non-standard NACA aerofoil for which the optimal angle of attack was determined with a maximum L/D ratio. The optimisation results were validated using the finite volume method.

Słowa kluczowe

EN

Artificial Neural Network; ANN; NACA airfoil; optimization; surrogate model; model reduction

• Wydawca: Polskie Towarzystwo Mechaniki Teoretycznej i Stosowanej
• Czasopismo: Journal of Theoretical and Applied Mechanics
• Rocznik: 2024
• Tom: Vol. 62 nr 3
• Strony: 521--534
• Opis fizyczny: Bibliogr. 26 poz., rys.

Twórcy

autor

Kieszek Rafał

• Military University of Technology, Faculty of Mechatronics, Armament and Aerospace, Warsaw, Poland

• https://orcid.org/0000-0002-7775-2564

autor

Majcher Maciej

• Military University of Technology, Faculty of Mechatronics, Armament and Aerospace, Warsaw, Poland

• https://orcid.org/0000-0002-4094-8766

autor

Syta Borys

• Military University of Technology, Faculty of Mechatronics, Armament and Aerospace, Warsaw, Poland

autor

Kozakiewicz Adam

• Military University of Technology, Faculty of Mechatronics, Armament and Aerospace, Warsaw, Poland

• https://orcid.org/0000-0002-1607-5715

Bibliografia

• 1. Abbott H., Doenhoff E., Lous S., Stivers J., 1945, Summary of airfoil data, National Ad-visory Commitee for Aeronautics Report, 824.
• 2. Aramendia I., Fernandez-Gamiz U., Zulueta E., Saenz-Aguirre A., Teso-Fz-Betoño D., 2019, Parametric study of a Gurney flap implementation in a DU91W (2) 250 airfoil, Energies, 12, 2, 294.
• 3. Bakewell H.P., Lumley J.L., 1967, Viscous sublayer and adjacent wall region in turbulent pipe flow, Physics Fluids, 10, 1880-1889.
• 4. Berkooz G., Holmes P., Lumley J.L., 1993, The proper orthogonal decomposition in the analysis of turbulent flows, Annual Review of Fluid Mechanics, 25, 539-575.
• 5. Butterweck A., Głuch J., 2014, Neural network simulator’s application to reference performance determination of turbine blading in the heat-flow diagnostics, [In:] Intelligent Systems in Technical and Medical Diagnostics, Springer, Berlin, Heidelberg.
• 6. Conn A.R., Gould N.I. Toint P., 1991, A globally convergent augmented Lagrangian algorithm for optimization with general constraints and simple bounds, SIAM Journal on Numerical Analysis, 28, 2, 545-572.
• 7. Dhileep K., et al., 2020, Numerical study of camber morphing in NACA0012 airfoil, AIAA Aviation 2020 Forum, 2781.
• 8. Drela M., 1989, XFOIL: An analysis and design system for low Reynolds number airfoils, [In:] Low Reynolds Number Aerodynamics. Proceedings of the Conference Noire Dame, Indiana, USA, Springer Berlin Heidelberg, 1-12.
• 9. Fukami K., Fukagata K., Taira K., 2021, Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows, Journal of Fluid Mechanics, 909.
• 10. Günel O., Ko E. Yavuz T. 2016, CFD vs. XFOIL of airfoil analysis at low Reynolds numbers, IEEE International Conference on Renewable Energy Research and Applications (ICRERA), 628-632.
• 11. Hsiao F.B., Bai C.J., Chong W.T., 2013, The performance test of three different horizontal axis wind turbine (HAWT) blade shapes using experimental and numerical methods, Energies, 6, 6, 2784-2803.
• 12. https://web.stanford.edu/ cantwell/AA200 Course Material/The%20NACA%20airfoil%20series.pdf, [Online 2021.10.25].
• 13. Khan A.Y., Ahmad Z., Sultan T., Alshahrani S., Hayat K., Imran M., 2022, Optimization of photovoltaic panel array configurations to reduce lift force using genetic algorithm and CFD, Energies, 15, 24, 9580.
• 14. Kharal A., Saleem A., 2012, Neural networks based airfoil generation for a given Cp using Bezier-PARSEC parameterization, Aerospace Science and Technology, 23, 1, 330-344.
• 15. López-Briones Y.F., Sánchez-Rivera L.M., Arias-Montano A., 2020, Aerodynamic analysis for the mathematical model of a dual-system UAV, 17th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE).
• 16. Oliveira R.F. de, 2021, https://github.com/theolivenbaum/XFOILinterface [Online 2021.12.02].
• 17. Porta Ko A., Smidt S., Schmehl R., Mandru M., 2023, Optimisation of a multi-element airfoil for a fixed-wing airborne wind energy system, Energies, 16, 8, 3521.
• 18. Saad M.M.M., Mohd S.B., Zulkafli M.F., Shibani W.M, 2017, Numerical analysis for comparison of aerodynamic characteristics of six airfoils, AIP Conference Proceedings, AIP Publishing.
• 19. San O., Maulik R., 2018, Neural network closures for nonlinear model order reduction, Advances in Computational Mathematics, 44, 1717-1750.
• 20. Sessarego M., Feng J., Ramos-García N., Horcas S.G., 2020, Design optimization of a curved wind turbine blade using neural networks and an aero-elastic vortex method under turbulent inflow, Renewable Energy, 146, 1524-1535.
• 21. Sekar V., Jiang Q., Shu, C., Khoo B.C., 2019, Fast flow field prediction over airfoils using deep learning approach, Physics of Fluids, 31, 5, 057103.
• 22. Sobieczky H., 1999, Parametric airfoils and wings, [In:] Recent Development of Aerodynamic Design Methodologies, Fujii K., Dulikravich G.S. (Edit.), Notes on Numerical Fluid Mechanics (NNFM), vol 65, Vieweg+Teubner Verlag.
• 23. Sun G., Sun Y., Wang S., 2015, Artificial neural network based inverse design: Airfoils and wings, Aerospace Science and Technology, 42, 415-428.
• 24. Thirumalainambi R., Bardina J., 2003, Training data requirement for a neural network to predict aerodynamic coefficients, [In:] Independent Component Analyses, Wavelets, and Neural Networks, International Society for Optics and Photonics, 92-103.
• 25. Verma N., Baloni B.D., 2021, Artificial neural network-based meta-models for predicting the aerodynamic characteristics of two-dimensional airfoils for small horizontal axis wind turbine, Clean Technologies and Environmental Policy, 24, 2, 563-577.
• 26. Viquerat J., Hachem E., 2020, A supervised neural network for drag prediction of arbitrary 2D shapes in laminar flows at low Reynolds number, Computers and Fluids, 210, 104645.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).