基于深度学习的直升机旋翼翼型流场预测

Flow Field Prediction of Helicopter Rotor Airfoil Based on Deep Learning

本文提出了一种基于深度学习的直升机旋翼翼型流场预测方法。首先,采用计算流体力学(CFD)方法对样本集内的NACA系列翼型在不同马赫数和迎角状态下的流场进行预测,建立旋翼翼型流场数据库;然后,基于数据库训练卷积神经网络,建立旋翼翼型流场预测的人工智能方法;最后,针对测试集内翼型在不同马赫数和迎角状态下的流场进行预测,并与CFD计算结果对比。结果表明,深度学习方法可以有效地预测不同状态下旋翼翼型的流场特征,快速获取翼型流场数据,大幅减少了人为操作与CFD计算代价,在保证翼型流场预测精度的同时有效地提高了计算效率。

In this paper,a prediction method for flow field calculation of helicopter rotor airfoil based on deep learning is proposed.Firstly,CFD method was used to predict the flow field of NACA series airfoils in the sample set under different Mach numbes and angles of attack,establishing the flow field database of rotor airfoil.Then,the convolution neural network is trained based on database,and an artificial intelligence method for flow field prediction of rotor airfoil is built.Finally,the flow field of airfoil in the test set is predicted at different Mach numbers and angles of attack,and the predicted results were compared with the CFD calculation results.Results show that deep learning network can effectively predict characteristics of rotor airfoil and quickly obtain the flow field data of airfoil.It can greatly reduce the cost of manual operation and CFD calculation,and effectively improve the computational efficiency while ensuring the prediction accuracy of airfoil flow field.