Airfoil Shape Optimization for Enhanced Aerodynamic Efficiency Using a Dual-Branch Deep Network Integrated with Genetic Algorithms

Airfoils are the key component of aircraft that are used to generate lift force to support its weight. Optimization of airfoils can significantly enhance their aerodynamic efficiency. The present study introduces a novel method of airfoil optimization that integrates Genet-ic Algorithms (GA) with Deep Learning (DL). The dataset was generated using XFOIL by varying angle of attack and Reynold’s number for various airfoil geometries. The geometry of airfoils was represented by Bezier Curve parametrization in the dataset. The generated dataset was used to train a Dual Branch Fully Connected Hybrid Activated Deep Network (DBFC-HA DN) model. The novel approach involves the integration of the trained model with the Genetic Algorithm (GA) to find the optimized solution (geometry) of the airfoil bounded within a pre-defined angle of attack range that is based on a reference airfoil. CFD analyses have been performed to verify the results of the proposed model. For NACA 65(2)-415, a 24.45% increase in lift-to-drag ratio was identified using CFD analysis at 0º angle of attack. The results were also validated using wind tunnel testing. The approach presented in the study saves computational cost and time for the optimisation of airfoils as compared to CFD and provides a basis for its use in the optimisation of airfoil performance for the relevant aerospace engineering applications.