Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 8;15(1):11998.
doi: 10.1038/s41598-025-95848-4.

Aerodynamic analysis and ANN-based optimization of NACA airfoils for enhanced UAV performance

Sanan H Khan  1 , Mohd Danish  2 , Md Ayaz  2 , Afsar Husain  3 , Shamma Saeed  3 , Shamma Abdulla  3 , Shama Shaheen  3 , Alia Saeed  3 , Ahmed Thaher  3
Affiliations

Aerodynamic analysis and ANN-based optimization of NACA airfoils for enhanced UAV performance

Sanan H Khan et al. Sci Rep. .

Abstract

The performance of unmanned aerial vehicles (UAVs) is strongly dependent on the design of their airfoils, particularly in applications necessitating high maneuverability, stability, and efficiency. This study analyzed three National Advisory Committee for Aeronautics (NACA) airfoil profiles: NACA 2412, NACA 4415, and NACA 0012, using a combination of computational fluid dynamics (CFD), XFOIL simulations, and a hybrid artificial neural network-genetic algorithm (ANN-GA) model. This study aimed to evaluate and optimize the aerodynamic performance of these airfoils under various flight conditions. Through CFD simulations and XFOIL analysis, we explored the lift, drag, and stall characteristics of each airfoil at different angles of attack and Reynolds numbers. The NACA 4415 airfoil consistently outperformed the others, achieving the highest lift-to-drag ratio ([Formula: see text]) and exhibiting favorable stall behavior. Thus, it is particularly well-suited for UAVs operating in challenging environments. Further, streamline and velocity profile analyses confirmed that NACA 4415 exhibited a smooth airflow and delayed flow separation, thereby contributing to its superior aerodynamic efficiency. Using the hybrid ANN-GA model, we optimized key parameters, such as the angle of attack and Reynolds number with optimal values of [Formula: see text] and 770,801, respectively, for maximum efficiency. Additionally, the ANN model demonstrated a high accuracy in predicting the aerodynamic performance, closely matching the results of the CFD simulations. Overall, this study highlighted the potential of combining computational techniques and machine- learning models to optimize UAV airfoil designs. These findings offer valuable insights for improving the efficiency and agility of UAVs, particularly in industries such as precision agriculture, infrastructure inspection, and environmental monitoring.

Keywords: Aerodynamic optimization; Computational fluid dynamics (CFD); Hybrid ANN-GA; NACA airfoils; UAVs.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Airfoil profiles considered for the UAV design.
Fig. 2
Fig. 2
CFD mesh and boundary conditions for airfoil analysis.
Fig. 3
Fig. 3
Estimating the optimum number of neurons: (a) MSE versus Number of neurons in a hidden layer and (b) R versus Number of neurons in a hidden layer.
Fig. 4
Fig. 4
Developed ANN model architecture.
Fig. 5
Fig. 5
Flowchart of hybrid ANN-GA model.
Fig. 6
Fig. 6
Angle of attack versus formula image for NACA 2412, NACA 4415, and NACA 0012 profiles at different Reynolds numbers.
Fig. 7
Fig. 7
Pressure contours from CFD simulations for NACA 2412, NACA 4415, and NACA 0012 profiles at various angles of attack (formula image, formula image, formula image, and formula image).
Fig. 8
Fig. 8
Streamline patterns for NACA 2412, NACA 0012, and NACA 4415 airfoils at angles of attack of formula image, formula image, and formula image.
Fig. 9
Fig. 9
Velocity profiles for NACA 2412, NACA 0012, and NACA 4415 airfoils at angles of attack of formula image, formula image, and formula image. The colors represent velocity magnitude, with red indicating higher velocities and blue indicating lower velocities.
Fig. 10
Fig. 10
Variation in formula image with (a) maximum formula image, and (b) optimum AOA.
Fig. 11
Fig. 11
Variation in formula image with maximum formula image and optimum AOA for (a) NACA 2412, (b) NACA 4415, and (c) NACA 0012.
Fig. 12
Fig. 12
Comparison of prediction accuracy of ANN model with the CFD data at (a) formula image, (b) formula image, (c) formula image.
See this image and copyright information in PMC

References

    1. Floreano, D. & Wood, R. J. Science, technology and the future of small autonomous drones. Nature521(7553), 460–466 (2015). - PubMed
    1. Agha Hassnain Mohsan, S., Qamar Hakimah Othman, N., Li, Y., Alsharif, M. H. & Khan, M. A. Unmanned aerial vehicles (UAVs): Practical aspects, applications, open challenges, security issues, and future trends. Intell. Serv. Robot.16(1), 109–137 (2023). - PMC - PubMed
    1. Ahmed, F., Mohanta, J. C., Keshari, A. & Yadav, P. S. Recent advances in unmanned aerial vehicles: A review. Arab. J. Sci. Eng.47(7), 7963–7984 (2022). - PMC - PubMed
    1. Tsouros, D. C., Bibi, S. & Sarigiannidis, P. G. A review on UAV-based applications for precision agriculture. Information10(11), 349 (2019).
    1. Niu, S., Nie, Z., Li, G. & Zhu, W. Multi-altitude corn tassel detection and counting based on UAV RGB imagery and deep learning. Drones8(5), 198 (2024).

LinkOut - more resources