Machine Learning Based Predictions of Airfoil Aerodynamic Coefficients for Reynolds Number Extrapolations

Abstract

Abstract This study investigates the application of various machine learning (ML) algorithms for predicting two critical aerodynamic coefficients, i.e. the maximum lift coefficient (C l max ) and the minimum drag coefficient (C d min ), for wind turbine airfoils at any given Reynolds number. We propose to use clustering techniques to group similar airfoil shapes and use the created partitions to predict unseen airfoil properties utilizing their similarity. Here, we also represent airfoils in the PARSEC low dimensional space, rather than high dimensional airfoil points space, to remedy the small number of training data. For this purpose, an extended experimental airfoil database is created and used for training models based on five different ML algorithms. We observe that the Decision Tree Ensemble (DTE), Random Forest (RF) and multi-layer perceptron (MLP) models emerge as the most effective predictors for C l max and C d min . Testing these two ML models on three additional airfoil cases not included in the training database shows that the C l max prediction performance is generally reasonable, with error levels being around 5% on average. In contrast, the prediction error levels for C d min are usually higher, with an average of around 15%.