Fast sparse flow field prediction around airfoils via multi-head perceptron based deep learning architecture

TL;DR

This paper introduces a deep learning approach combining CNN and multi-head perceptron to rapidly predict sparse flow fields around airfoils, significantly reducing computation time compared to traditional CFD methods.

Contribution

It proposes a novel multi-head perceptron architecture that improves prediction accuracy for sparse flow fields around airfoils over standard multi-layer perceptrons.

Findings

Multi-head perceptron outperforms multi-layer perceptron in prediction accuracy.

The method predicts aerodynamic coefficients in seconds.

The approach reduces computational time compared to CFD.

Abstract

In order to obtain the information about flow field, traditional computational fluid dynamics methods need to solve the Navier-Stokes equations on the mesh with boundary conditions, which is a time-consuming task. In this work, a data-driven method based on convolutional neural network and multi-head perceptron is used to predict the incompressible laminar steady sparse flow field around the airfoils. Firstly, we use convolutional neural network to extract the geometry parameters of the airfoil from the input gray scale image. Secondly, the extracted geometric parameters together with Reynolds number, angle of attack and flow field coordinates are used as the input of the multi-layer perceptron and the multi-head perceptron. The proposed multi-head neural network architecture can predict the aerodynamic coefficients of the airfoil in seconds. Furthermore, the experimental results show that for sparse flow field, multi-head perceptron can achieve better prediction results than multi-layer perceptron.