Applications of machine learning for aerodynamic characteristics modeling

Mathematical modeling of aerodynamic data plays an important role in the performance evaluation of a flight vehicle. There are two kinds of aerodynamic characteristics modeling methods, i.e., the rational modeling method based on physical mechanism and the "black-box" modeling methods. In this paper, three types of "black-box" modeling methods including the classification and regression tree method(CART), the shallow learning method, and the deep learning method are investigated. The CART method and three shallow learning methods including Kriging method, radial basis function(RBF) neural network method, and support vector machines(SVM) method are applied to the aerodynamic data modeling of rocket, the unsteady aerodynamic characteristics modeling for delta wing with large angle of attack, the aerodynamic heat data fusion of wind tunnel test and CFD. The advantage and shortage of these modeling methods are compared. A deep learning neural network model of airfoil's aerodynamic coefficients is built. It considers the influence of airfoil picture and flow parameters such as Mach number, angle of attack on the prediction results at the same time through a "synthetic picture".It could significantly expand the applied range of the deep learning modeling method in aerodynamic research field.