DATA MINING ANALYSIS ON AERODYNAMIC STEALTH DESIGN PRINCIPLES OF AIRFOIL PROFILES

In the multidisciplinary design of aerodynamic stealth for airfoil profiles, the diversity and coupling relationships among objectives and variables increase the computational cost and development cycle of the optimization design. This paper focuses on data mining using two types of algorithms: random forest and isometric mapping. The data mining considers many objectives: aerodynamic lift coefficient, drag coefficient, and lift-to-drag ratio, as well as vertical polarized radar cross-section and horizontal polarized radar cross-section. In the analysis of objectives and design variables, the aerodynamic and stealth performance of the airfoil profiles are greatly influenced by the curvature of the leading and trailing edges, followed by the chord length. Larger curvature of the leading edge reduces drag and improves stealth performance. Smaller curvature of the trailing edge improves the lift coefficient, lift-to-drag ratio, and stealth performance. Through data mining, specific reference ranges for design variables are provided to obtain airfoil profiles with superior aerodynamic stealth performance.