Abstract
<title>Abstract</title> <p>High-speed aircraft require advanced aerodynamic designs to achieve improved flight efficiency, reduced drag, and enhanced stability under complex flow conditions. Conventional aerodynamic optimization methods based on Computational Fluid Dynamics (CFD) are accurate but computationally expensive and time-consuming. This study proposes an AI-based aerodynamic shape optimization framework that integrates CFD simulations, machine learning-based surrogate modeling, and multi-objective optimization techniques. The framework predicts key aerodynamic parameters, including lift coefficient, drag coefficient, and lift-to-drag ratio, while significantly reducing computational cost. Physics-informed learning is incorporated to improve prediction reliability and maintain consistency with aerodynamic principles. The proposed approach enables rapid exploration of aerodynamic design spaces and supports the development of efficient high-speed aircraft configurations. The framework provides a scalable and intelligent methodology for next-generation aerospace design, offering improved optimization efficiency, reduced design time, and enhanced aerodynamic performance.</p>