Neurodynamic analysis of NACA 0012 airfoil and wing using Bayesian regularisation
DOI:
https://doi.org/10.47264/idea.nasij/6.1.1Keywords:
Computational intelligence, Fluid dynamics, Aerodynamics, Artificial neural network, Artificial intelligence, Data-driven analysisAbstract
This paper proposes a novel neural network-based approach with Bayesian regularisation for analysing air foils and wings. Here, the established NACA0012 airfoil, a standard in aviation and aerospace engineering, is used. Empirical methods, various software, and computational fluid dynamics (CFD) simulations have been commonly employed in airfoil analysis. To forecast and model the aerodynamic characteristics of the NACA0012 airfoil and its wing counterparts, this study presents a data-driven approach utilising artificial neural networks (ANNs). Datasets are first generated using software xflr5, followed by AI-based Bayesian regularisation (AI-BR). Approximations in analyses were demonstrated using three data sets: training (80%), testing (10%), and validation (10%), with 20 neurons. Large-scale Simulink results on mean-squared error, error histograms, and regression analyses further emphasise the proposed AI-BR's competence, dependability, and accuracy. A direct and immediate way to assess the accuracy of models or measurements is to use an absolute error (AE) plot, which shows the differences between estimated and actual values. The findings support the effectiveness of integrating ANNs with Bayesian regularisation in aerodynamic analysis. The approach not only enhances prediction accuracy but also opens new avenues for future investigations into more complex aerodynamic models.
References
Abbasi, A. Z., Rafiq, A., Alshammari, B. M., & Jaghdam, I. H. (2025a). An advanced image encryption scheme based on generalised triangle group and neural networks. Ain Shams Engineering Journal, 16(8), 103488. https://doi.org/10.1016/j.asej.2025.103488
Abbasi, A. Z., Aamir, M., Sattar, M., Abdullah, N., Abdennaji, T. S., Alshammri, B. M., & Kolsi, L. (2025b). Modelling and prediction of 3D Carreau Fluid behaviour using machine learning for Cattaneo Christov double diffusion with variable conductivity. Case Studies in Thermal Engineering, 106302. https://doi.org/10.1016/j.csite.2025.106302
Aamir, M., Alshehery, S., Abbasi, A. Z., Sohail, M. U., Khan, N., Mesloub, A., ... & Kolsi, L. (2025). Analysis for 3D thermal conducting micropolar nanofluid via artificial neural network. The European Physical Journal Plus, 140(2), 100. https://link.springer.com/article/10.1140/epjp/s13360-025-06022-8
Abbott, I. H., & von Doenhoff, A. E. (1959). Including a summary of Airfoil data. New York.
Ananda, G. K., Sukumar, P. P., & Selig, M. S. (2015). Measured aerodynamic characteristics of wings at low Reynolds numbers. Aerospace Science and Technology, 42, 392-406. https://doi.org/10.1016/j.ast.2014.11.016
Anand, A., Safdar, M. M., Marepally, K., & Baeder, J. D. (2025). A comprehensive review of neural network training approaches for airfoil design and optimization. In AIAA SCITECH 2025 Forum (p. 0271). https://doi.org/10.2514/6.2025-0271
Boulkeraa, T., Ghenaiet, A., Mendez, S., & Mohammadi, B. (2014). A numerical optimization chain combining computational fluid dynamics and surrogate analysis for the aerodynamic design of airfoils. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 228(11), 1964-1981. https://doi.org/10.1177/0954410013506159
Camacho, E. A., Silva, A. R., & Marques, F. D. (2025). Predicting airfoil dynamic stall loads using neural networks. Aerospace Science and Technology, 165, 110466. https://doi.org/10.1016/j.ast.2025.110466
Chen, Q., Sabir, Z., Mehmood, M. A., & Baskonus, H. M. (2025). A machine learning radial basis deep neural network for solving the fractional chaotic financial system. Journal of Computational and Applied Mathematics, 116936. https://doi.org/10.1016/j.cam.2025.116936
Cuerno-Rejado, C., López-Martínez, G., Escudero-Arahuetes, J. L., & López-Díez, J. (2001). Experimental aerodynamic characteristics of NACA 0012 airfoils with simulated glaze and rime ice. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 215(4), 229-240. https://doi.org/10.1243/0954410011533211
Del Pino, C., Parras, L., Felli, M., & Fernandez-Feria, R. (2011). Structure of trailing vortices: Comparison between particle image velocimetry measurements and theoretical models. Physics of Fluids, 23(1). https://doi.org/10.1063/1.3537791
Fincham, J. H. S., & Friswell, M. I. (2015). Aerodynamic optimisation of a camber morphing aerofoil. Aerospace Science and Technology, 43, 245-255. https://doi.org/10.1016/j.ast.2015.02.023
Karay, M., Sabir, Z., Akkilic, A. N., & Bulut, H. (2025). A stochastic neural network for the numerical solutions of the nonlinear fractional order Zika virus model using reservoirs and human motion. Computational Biology and Chemistry, 108629. https://doi.org/10.1016/j.compbiolchem.2025.108629
Laitone, E. V. (1997). Wind tunnel tests of wings at Reynolds numbers below 70,000. Experiments in fluids, 23(5), 405-409.
Ngo, H. T., & Barlow, L. E. (2002). U.S. Patent No. 6,394,397. Patent and Trademark Office.
Sabir, Z., & Abdelkawy, M. A. (2025). A novel combination of sigmoid and radial basis neural networks for the monkeypox transmission system. Engineering Applications of Artificial Intelligence, 158, 111512. https://doi.org/10.1016/j.engappai.2025.111512
Sheldahl, R. E., & Klimas, P. C. (1981). Aerodynamic characteristics of seven symmetrical airfoil sections through 180-degree angle of attack for use in aerodynamic analysis of vertical axis wind turbines (No. SAND-80-2114). Sandia National Labs., Albuquerque, NM (USA).
Wassing, S., Langer, S., & Bekemeyer, P. (2025). Physics-informed neural networks for inviscid transonic flows around an airfoil. Physics of Fluids, 37(8). https://doi.org/10.1063/5.0276518
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mamoon Aamir, Husnain Raza Qasim
This work is licensed under a Creative Commons Attribution 4.0 International License.
Please click here for details about the Licensing and Copyright policies of NASIJ.
