| dc.description.abstract | The paper proposes novel approaches to achieve rapid and accurate inference of aerodynamic performance parameters for airfoil optimization design using deep learning methods, compared with expensive computational fluid dynamics (CFD) simulation tools. Two deep neural networks are proposed, and they were tested for aerodynamic performance prediction (APPN), including the lift and drag coefficients and the surface pressure distribution. The network framework is constructed using a convolutional neural network (CNN) and a fully connected neural network (FCN). To enhance the prediction capability of the two networks under varying operating conditions including various angles of attack (AOAs), Mach numbers, and Reynolds numbers (R), a flexible and practical parameterization method called the signed distance function (SDF) is utilized to represent the geometric information and then merged with the Reynolds number for input to the network models. The prediction results show that the proposed models have clear advantages, including fast convergence, high prediction accuracy, and remarkable extensionality. Moreover, the predicted aerodynamic coefficients of an airfoil can be obtained within 13 ms, 4 orders of magnitudes faster than CFD solvers. The prediction relative errors of the lift and drag coefficients are lower than 1.5%, and that of the pressure distribution is less than 1.2%. This work indicates that deep learning–based network models can offer great potential as practical tools for aerodynamic design and optimization and for flow control in the future. | |
