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

Area of Science:

• Aerospace Engineering
• Computational Fluid Dynamics
• Machine Learning

Background:

• Unmanned Aerial Vehicle (UAV) performance is critically dependent on airfoil design for maneuverability, stability, and efficiency.
• Selecting optimal airfoil profiles is essential for enhancing UAV capabilities in diverse applications.

Purpose of the Study:

• To evaluate and optimize the aerodynamic performance of NACA 2412, NACA 4415, and NACA 0012 airfoils for UAVs.
• To identify the most suitable airfoil profile for challenging UAV operational environments.
• To leverage computational and machine learning methods for airfoil design optimization.

Main Methods:

• Computational Fluid Dynamics (CFD) simulations were employed to analyze airfoil characteristics.
• XFOIL simulations were utilized to assess lift, drag, and stall behavior across various flight conditions.
• A hybrid Artificial Intelligence (AI) model combining artificial neural networks (ANN) and genetic algorithms (GA) was developed for optimization.

Main Results:

• NACA 4415 demonstrated superior aerodynamic performance, achieving the highest lift-to-drag ratio and favorable stall characteristics.
• CFD and XFOIL analyses confirmed smoother airflow and delayed flow separation for NACA 4415, contributing to its efficiency.
• The ANN-GA model identified optimal parameters (angle of attack and Reynolds number) for maximum airfoil efficiency, with the ANN accurately predicting performance.

Conclusions:

• NACA 4415 is highly suitable for UAVs requiring high efficiency and stability, especially in demanding conditions.
• Combining CFD, XFOIL, and AI models offers a powerful approach for optimizing UAV airfoil designs.
• The findings provide valuable insights for enhancing UAV efficiency and agility in sectors like precision agriculture and infrastructure monitoring.