A Surrogate ANN–BEM Framework for Aerodynamic Modeling of Smart Wind Turbine Blades

Naoual  Afif; Yassine  lakhal; Mohammed  Haiek; Fatima  Zahra Baghli; Samagassi  Soulaimane

doi:10.51646/jsesd.v14i2.1215

Authors

Naoual Afif Engineering and Applied Physics Team, Sultan Moulay Slimane University, Beni Mellal, Morocco. The Moroccan Association of Sciences and Techniques for Sustainable Development (MASTSD), Beni Mellal, Morocco https://orcid.org/0009-0002-8910-8749
Yassine lakhal Engineering and Applied Physics Team, Sultan Moulay Slimane University, Beni Mellal, Morocco. The Moroccan Association of Sciences and Techniques for Sustainable Development (MASTSD), Beni Mellal, Morocco. https://orcid.org/0000-0003-3278-237X
Mohammed Haiek Laboratory of Innovative Technologies, National School of Applied Sciences of Tangier. B.P. 1818, Tangier, Morocco. https://orcid.org/0000-0002-4518-5980
Fatima Zahra Baghli Engineering and Applied Physics Team, Sultan Moulay Slimane University, Beni Mellal, Morocco. The Moroccan Association of Sciences and Techniques for Sustainable Development (MASTSD), Beni Mellal, Morocco.
Samagassi Soulaimane Unité de Formation et de Recherche Laboratoire de Mécanique et informatique, Université Félix Houphouët-Boigny, Abidjan, Cote D’Ivoire. https://orcid.org/0000-0002-0240-1903

DOI:

https://doi.org/10.51646/jsesd.v14i2.1215

Keywords:

NACA, airfoil, artificial neural networks (ANN), morphing blade, smart blades

Abstract

Accurate prediction of aerodynamic coefficients is essential for the design and control of smart blades featuring morphing airfoils. This study presents a data-driven metamodel based on Artificial Neural Networks (ANNs) developed to predict the aerodynamic behavior of airfoils within the NACA series. The model accepts geometric descriptors of airfoils along with the angle of attack (AoA) as input and outputs corresponding lift (Cl) and drag (Cd) coefficients. A high-fidelity aerodynamic database was generated through systematic simulations across a wide range of AoAs and NACA profiles to train and validate the ANN. The model is trained on NACA 4-digit series profiles covering a wide range of AoA and geometric parameters. The ANN model achieved a mean squared error of 2.10805 e-3 and an R² above 0.997 on test data. The trained metamodel demonstrates excellent generalisation accuracy while drastically reducing computational requirements compared to conventional CFD or BEM-based methods. The model is particularly suited for integration into larger simulation frameworks, such as Blade Element Momentum (BEM) codes or adaptive control systems, enabling real-time performance estimation for morphing smart blades. This work contributes a scalable and efficient surrogate modelling approach for aerodynamic prediction across diverse airfoil geometries.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

M. Haiek, Y. Lakhal, N. B. S. Amrani, D. Sarsri, et S. Samagassi, « Metamodeling for predicting the behavior of airfoils of wind turbine blades: An integration of artificial neural networks », E3S Web of Conferences, vol. 469, p. 03002, 2024. https://doi.org/10.1051/e3sconf/202458203002

A. Najafian, A. Jahangirian, « Maximum annual energy production of a 1.5 MW wind turbine using optimum morphing blades at different control management scenarios », Energy Conversion and Management, vol. 326, p. 119429, févr. 2025. https://doi.org/10.1016/j.enconman.2024.119429

H. Abusannuga, « Verification of the self-starting problem of a Vertical Axis Wind Turbine with Inclined Blades », Solar Energy and Sustainable Development Journal, vol. 12, no 2, pp. 65–74, 2023. https://doi.org/10.51646/jsesd.v12i2.161

M. S. Abdullah, F. Ismail, « Optimization of Savonius rotor blade performance using Taguchi method: Experimental and 3D-CFD approach », Energy, vol. 303, p. 131801, sept. 2024. https:// doi.org/10.1016/j.energy.2024.131801

X. Hui, J. Bai, H. Wang, Y. Zhang, « Fast pressure distribution prediction of airfoils using deep learning », Aerospace Science and Technology, vol. 105, p. 105949, oct. 2020. https://doi. org/10.1016/j.ast.2020.105949

A. Teimourian, D. Rohacs, K. Dimililer, H. Teimourian, M. Yildiz, U. Kale, « Airfoil aerodynamic performance prediction using machine learning and surrogate modeling », Heliyon, vol. 10, no 8, p. e29377, 2024. https://doi.org/10.1016/j.heliyon.2024.e29377

Jiaqi Liu, Rongqian Chen, Jinhua Lou, Yue Hu, Yancheng You « Deep learning based aerodynamic shape optimization of rotor airfoils to suppress dynamic stall », Aerospace Science and Technology, Volume 133, 108089, February 2023 . https://doi.org/10.1016/j.ast.2022.108089

Xinshuai Zhang, Fangfang Xie, Tingwei Ji, Zaoxu Zhu, Yao Zheng « Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization », Computer Methods in Applied Mechanics and Engineering, Volume 373, 113485, January 2020. https://doi.org/10.1016/j. cma.2020.113485

Jichao Li , Xiaosong Du, Joaquim R.R.A. Martins, « Machine learning in aerodynamic shape optimization », Progress in Aerospace Sciences, Volume 134, 100849, October 2022. https://doi. org/10.1016/j.paerosci.2022.100849

M. Uyar, « Enhanced thermal and angular velocity-induced hybrid piezoelectric energy harvesting of smart turbine blades », Thermal Science and Engineering Progress, vol. 47, p. 102344, janv. 2024. https://doi.org/10.1016/j.tsep.2023.102344

J. Ding, Q. Liu, J. Ke, M. Deng, G. Yu, Y. Liang, « Development of a hybrid CFD-ANN method with multi-objective optimization for airfoil-finned PCHE used in Gen-IV nuclear systems », Progress in Nuclear Energy, vol. 175, p. 105346, 2024. https://doi.org/10.1016/j.pnucene.2024.105346

Y. Lakhal, M. Haiek, F. Z. Baghli, Y. A. El Kadi, M. Benchagra, and D. Sarsri, “Smart Flow Control of an Airfoil with Trailing Edge Flap for Wind Turbines Using a Fuzzy Logic Strategy,” IRECON, vol. 12, no. 5, p. 195, Sept. 2024, doi: 10.15866/irecon.v12i5.25100.

R. Meng, X. Chen, L. Chen, N. Xie, L. Wang, and B. Xu, “Aerodynamic and structural Cooptimization of offshore wind turbine blades using a novel adaptive surrogate-based optimization method,” Ocean Engineering, vol. 340, p. 122291, Nov. 2025, https://doi.org/10.1016/j. oceaneng.2025.122291

M. E. Elshaar et N. A. A. Qasem, « Enhanced prediction of airfoil’s drag coefficient using curve fitting and artificial neural network », Transportation Research Procedia, vol. 84, pp. 641– 648, 2025. https://doi.org/10.1016/j.trpro.2025.03.119

K. El Harti, M. Touil, R. Saadani, M. Rahmoune, M. «Vibration Control of Tapering E-FGM Porous Wind Turbine Blades Using Piezoelectric Materials », Solar Energy and Sustainable Development, 14 (2024), 67–77. https://doi.org/10.51646/jsesd.v14iSI_MSMS2E.402