CycleMLP++: An efficient and flexible modeling framework for subsonic airfoils

Abstract

Artificial intelligence techniques are considered an effective means to accelerate flow field simulations. However, current deep learning methods struggle to achieve generalization to flow field resolutions while ensuring computational efficiency. This paper presents a deep learning approach for rapid prediction of two types of subsonic flow fields with different resolutions. Unlike convolutional neural networks, Cycle fully-connected integrates features across different channel dimensions, reducing the sensitivity of the deep learning model to resolution while improving computational efficiency. Additionally, to ensure consistency between the input and output resolutions of the deep learning model, a memory pooling strategy is proposed, which ensures accurate reconstruction of flow fields at any resolution. The experimental results demonstrate that the proposed deep learning model can produce results comparable to traditional numerical simulations within a matter of seconds. Notably, the model exhibits adaptability to flow fields of any resolution, providing an effective solution for the development of large-scale models in fluid mechanics.