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

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.