Description

This paper proposes a machine learning framework for accurately predicting the aerodynamic lift-to-drag ratio (CL/CD) of multi-stepped airfoils under varied flow conditions. Experimental wind-tunnel data were collected for multiple step configurations, and a stacked ensemble model combining XGBoost, Support Vector Regression (SVR), and K-Nearest Neighbors (KNN) with a Random Forest meta-learner was developed for prediction. The proposed model achieved a test R2 of 0.9951 and a tenfold cross-validation R2 of 0.9872 ± 0.0043, demonstrating superior accuracy compared to individual regressors. This approach provides a fast, data-driven alternative to conventional CFD simulations, enabling reliable prediction of aerodynamic performance and efficient airfoil optimization.

URL

https://doi.org/10.1007/s42401-025-00422-5

DOI

https://doi.org/10.1007/s42401-025-00422-5

Brief

KeyWords