Neural network approach for predicting aerodynamic performance of NACA airfoil at low Reynolds number

Mohamad Yamin, Zaid Al Kahfi Ramadhan

Abstract


In designing and developing airfoils, confirmation of proper design performance under various flow conditions is vital. Experimental studies using wind tunnels or numerical simulations can often utilize. In some cases, numerical studies have a weakness in computational time. This study focuses on predicting the drag coefficient of the airfoil using the CNN machine learning architecture. Starting with a numerical simulation of 500 types of NACA airfoils with a Reynolds number of 4000 using XLRF5 software to obtain image data, lift and drag coefficients. The training, test, and validation dataset uses numerical simulation results as labels. ReLU is the activation function used in this study, with Adam optimizer and MSE loss function. It achieved a relative error of 8% in predicting the drag coefficient. With the results obtained, aircraft designers can use the method to predict the drag coefficient value from various geometries.


Keywords


NACA Airfoil; Supervised learning; drag prediction; CNN; XLRF5

Full Text:

PDF

References


Subasi, “Chapter 3 - Machine learning techniques,†A. B. T.-P. M. L. for D. A. U. P. Subasi, Ed. Academic Press, 2020, pp. 91–202.

P. H. Winston, Artificial intelligence. Addison-Wesley Longman Publishing Co., Inc., 1992.

L. Zhu, W. Zhang, J. Kou, and Y. Liu, “Machine learning methods for turbulence modeling in subsonic flows around airfoils,†Phys. Fluids, vol. 31, no. 1, p. 15105, 2019.

A. Ouallane, A. Bahnasse, A. Bakali, and M. Talea, “Overview of Road Traffic Management Solutions based on IoT and AI,†Procedia Comput. Sci., vol. 198, pp. 518–523, 2022, doi: https://doi.org/10.1016/j.procs.2021.12.279.

M. Doumpos, C. Zopounidis, D. Gounopoulos, E. Platanakis, and W. Zhang, “Operational research and artificial intelligence methods in banking,†Eur. J. Oper. Res., 2022, doi: https://doi.org/10.1016/j.ejor.2022.04.027.

Krahe, M. Iberl, A. Jacob, and G. Lanza, “AI-based Computer Aided Engineering for automated product design - A first approach with a Multi-View based classification,†Procedia CIRP, vol. 86, pp. 104–109, 2019, doi: https://doi.org/10.1016/j.procir.2020.01.038

M.-H. Huang and R. T. Rust, “Artificial intelligence in service,†J. Serv. Res., vol. 21, no. 2, pp. 155–172, 2018.

N. Ahmadi, M. Romoser, and C. Salmon, “Improving the tactical scanning of student pilots: A gaze-based training intervention for transition from visual flight into instrument meteorological conditions,†Appl. Ergon., vol. 100, p. 103642, 2022, doi: https://doi.org/10.1016/j.apergo.2021.103642.

H. Zhu, “Research on intelligent analysis strategies to improve athletes’ psychological experience in the era of artificial intelligence,†Prog. Neuro-Psychopharmacology Biol. Psychiatry, p. 110597, 2022, doi: https://doi.org/10.1016/j.pnpbp.2022.110597

Y. P. Tsang and C. K. M. Lee, “Artificial intelligence in industrial design: A semi-automated literature survey,†Eng. Appl. Artif. Intell., vol. 112, p. 104884, 2022, doi: https://doi.org/10.1016/j.engappai.2022.104884.

K. K. Ramachandran, A. Apsara Saleth Mary, S. Hawladar, D. Asokk, B. Bhaskar, and J. R. Pitroda, “Machine learning and role of artificial intelligence in optimizing work performance and employee behavior,†Mater. Today Proc., vol. 51, pp. 2327–2331, 2022, doi: https://doi.org/10.1016/j.matpr.2021.11.544.

M. Desai, S. a Channiwala, and H. J. Nagarsheth, “Experimental and Computational Aerodynamic Investigations of a Car,†October, vol. 3, no. 4, pp. 359–368, 2008.

Jameson, “Optimum aerodynamic design using CFD and control theory,†in 12th computational fluid dynamics conference, 1995, p. 1729.

X. Wang, J. Kou, and W. Zhang, “Unsteady aerodynamic modeling based on fuzzy scalar radial basis function neural networks,†Proc. Inst. Mech. Eng. Part G J. Aerosp. Eng., vol. 233, no. 14, pp. 5107–5121, 2019.

Celik, “RANS/LES/DES/DNS: The future prospects of turbulence modeling.†2005.

H.-J. Yoo, “Deep convolution neural networks in computer vision: a review,†IEIE Trans. Smart Process. Comput., vol. 4, no. 1, pp. 35–43, 2015.

Y. LeCun and Y. Bengio, “Convolutional networks for images, speech, and time series,†Handb. brain theory neural networks, vol. 3361, no. 10, p. 1995, 1995.

R. L. Fearn, “Airfoil aerodynamics using panel methods,†Math. J., vol. 10, no. 4, p. 15, 2008.

İ. H. GÜZELBEY, Y. ERASLAN, and M. H. DOĞRU, “Numerical investigation of different airfoils at low Reynolds number in terms of aerodynamic performance of sailplanes by using XFLR5,†Karadeniz Fen Bilim. Derg., vol. 8, no. 1, pp. 47–65, 2018.

H. Abbott, A. E. Von Doenhoff, and L. Stivers Jr, “Summary of airfoil data,†1945.

F. Škultéty, B. Badánik, M. Bartoš, and B. Kandera, “Design of Controllable Unmanned Rescue Parachute Wing,†Transp. Res. Procedia, vol. 35, pp. 220–229, 2018, doi: https://doi.org/10.1016/j.trpro.2018.12.026.

Gharali and D. A. Johnson, “Dynamic stall simulation of a pitching airfoil under unsteady freestream velocity,†J. Fluids Struct., vol. 42, pp. 228–244, 2013, doi: https://doi.org/10.1016/j.jfluidstructs.2013.05.005.

R. J. McGhee, Experimental results for the Eppler 387 airfoil at low Reynolds numbers in the Langley low-turbulence pressure tunnel, vol. 4062. National Aeronautics and Space Administration, Scientific and Technical …, 1988.

Morgado, R. Vizinho, M. A. R. Silvestre, and J. C. Páscoa, “XFOIL vs CFD performance predictions for high lift low Reynolds number airfoils,†Aerosp. Sci. Technol., vol. 52, pp. 207–214, 2016.

Viquerat and E. Hachem, “A supervised neural network for drag prediction of arbitrary 2D shapes in laminar flows at low Reynolds number,†Comput. Fluids, vol. 210, 2020, doi: 10.1016/j.compfluid.2020.104645.

F. Chollet, Deep learning with Python. Simon and Schuster, 2021.

Mahesh, “Machine learning algorithms-a review,†Int. J. Sci. Res. (IJSR).[Internet], vol. 9, pp. 381–386, 2020.

O. Sharma, “A new activation function for deep neural network,†in 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon), 2019, pp. 84–86.

S. Mastromichalakis, “ALReLU: A different approach on Leaky ReLU activation function to improve Neural Networks Performance,†arXiv Prepr. arXiv2012.07564, 2020.

R. Caruana, S. Lawrence, and C. Giles, “Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping,†Adv. Neural Inf. Process. Syst., vol. 13, 2000.

N. M. Josuttis, “The C++ standard library: a tutorial and reference,†2012.

W. Python, “Python,†Python Releases Wind., vol. 24, 2021.

F. Chollet, Deep learning mit python und keras: das praxis-handbuch vom entwickler der keras-bibliothek. MITP-Verlags GmbH & Co. KG, 2018.

N. Hasabnis, “Auto-tuning TensorFlow threading model for CPU backend,†in 2018 IEEE/ACM Machine Learning in HPC Environments (MLHPC), 2018, pp. 14–25.

Nandy and M. Biswas, “Reinforcement learning with keras, tensorflow, and chainerrl,†in Reinforcement Learning, Springer, 2018, pp. 129–




DOI: http://dx.doi.org/10.30811/jpl.v20i2.3065

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Lisensi Creative Commons

Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional .

 

Alamat Surat :

Politeknik Negeri Lhokseumawe
Jl. Banda Aceh-Medan Km 280
Buketrata, Lhokseumawe, 24301, Aceh, Indonesia