Unmanned aircraft vehicles/unmanned aerial systems digital twinning: Data-driven lift and drag prediction for airfoil design

Abstract

This study investigates the innovative application of neural networks algorithms in the aviation industry's mechanical design process, motivated by the pursuit of creating a more accurate and efficient method for performance prediction. Traditional approaches, such as computational fluid dynamics (CFD) simulations based on solving Navier-Stokes’s equations, demand substantial computational power and often exhibit limited accuracy, particularly when compared with complex geometries. The state-of-the-art review unveils a growing research trend advocating for data-driven methodologies to revolutionize design practices, addressing the limitations of conventional techniques. The primary objective of this study is to explore how neural network algorithms can overcome the drawbacks of CFD simulations, offering a more effective alternative for predicting the performance of airfoils. To achieve this objective, we conducted a performance analysis of airfoils using neural network algorithms. The results presented a promising avenue for a more accurate and efficient performance prediction method through digital twinning. The study highlights the advantageous features of neural network methods in unmanned aircraft vehicles (UAV) component mechanical design, showcasing their potential to outperform traditional methods and offering practical recommendations for integration into the design process.