This paper presents a novel algorithm developed within the Efficient Global Optimization (EGO) framework, employing the Kriging model to optimize the aerodynamics of aircraft wings, with a specific focus on minimizing drag. While traditional methods such as wind tunnel testing and Computational Fluid Dynamics (CFD) have proven effective, they often incur high costs and extensive time commitments. The proposed algorithm is based on the Kriging model combined with Latin Hypercube Sampling (LHS) for initial design exploration, enhancing the process with both Constraint Expected Improvement (CEI) and Minimizing Surrogate Prediction criteria to refine optimization. This innovative approach markedly reduces both the computational time and associated costs compared with the traditional method, demonstrating substantial efficiency gains. The paper delves into both the theoretical and practical applications of the Kriging model in engineering optimization, showing its significant potential to advance aerodynamic optimization.