Flowfield Prediction of Airfoil Off-Design Conditions Based on a Modified Variational Autoencoder

Abstract

Multipoint optimization that considers the off-design flow conditions is usually applied to improve the robustness during airfoil aerodynamic optimization. Many deep learning models have been used for the rapid prediction of flowfields. However, the prediction accuracy may be insufficient, and the model generalization ability is questionable. Because a computational fluid dynamic evaluation of the cruise condition is usually necessary and affordable in industrial design, a novel deep learning model is proposed to use the cruise flowfield as a prior reference for the off-design condition prediction. A prior variational autoencoder is developed to extract features from the cruise flowfield and to generate new flowfields under other operation conditions. Physical-based loss functions based on aerodynamic force and conservation of mass are derived to minimize the prediction error. The results demonstrate that the proposed model can reduce the prediction error on test airfoils by 30% as compared to traditional models. The physical-based loss function can further reduce the prediction error by 4%. The proposed model illustrates a better balance between time cost and fidelity requirements as well as better generalization ability, which makes the model more feasible for industrial applications.