Fast simulation of airfoil flow field via deep neural network

TL;DR

This paper introduces a deep learning framework that significantly accelerates airfoil flow field simulations, achieving speeds thousands of times faster than traditional CFD methods while maintaining accuracy.

Contribution

The work presents a novel deep neural network architecture with attention modules for rapid and accurate airfoil flow field prediction, validated by integration with CFD solvers.

Findings

Flow field prediction speeds are three orders of magnitude faster than CFD.

Integrated CFD and deep learning approach accelerates simulation threefold.

Model generalizes well to different NACA airfoils.

Abstract

Computational Fluid Dynamics (CFD) has become an indispensable tool in the optimization design, and evaluation of aircraft aerodynamics. However, solving the Navier-Stokes (NS) equations is a time-consuming, memory demanding and computationally expensive task. Artificial intelligence offers a promising avenue for flow field solving. In this work, we propose a novel deep learning framework for rapidly reconstructing airfoil flow fields. Channel attention and spatial attention modules are utilized in the downsampling stage of the UNet to enhance the feature learning capabilities of the deep learning model. Additionally, integrating the predicted flow field values generated by the deep learning model into the NS equation solver validates the credibility of the flow field prediction results. The NACA series airfoils were used to validate the prediction accuracy and generalization of the deep learning model. The experimental results represent the deep learning model achieving flow field prediction speeds three orders of magnitude faster than CFD solver. Furthermore, the CFD solver integrated with deep learning model demonstrates a threefold acceleration compared to CFD solver. By extensively mining historical flow field data, an efficient solution is derived for the rapid simulation of aircraft flow fields.