摘要
本文试图通过神经网络重构二维低雷诺数翼型绕流非定常流场。首先通过局部径向基函数(LRBF)求解器求解不可压缩流动控制方程得到计算域内流场信息,然后随机选取一些时空域内的数据点(包含位置信息和速度信息)作为训练数据代入神经网络进行训练。先学习训练得到流动的雷诺数后进行流场的重构,并与LRBF求解器得到的数值结果进行对比。流动计算中雷诺数设置为200,攻角为20°,计算域离散采用局部节点加密技术以减少计算量。
Present paper attempts to reconstruct 2 D unsteady flow field using neural network when fluid flows past airfoils at low Reynolds number.First of all,the details of fluid domain are obtained by solving incompressible fluid governing equation using our own developed fluid solver based on local radial basis function(LRBF)method,and then some randomly selected tempo-spatial points(with velocities and pressure information)are fed into neural network to train.The training process of first step is to learn Reynolds number,continuing with reconstruction of fluid field and comparison with numerical results.The flow Reynolds number is set as 200,while angle of attack is 20°.Besides,the locally refined nodes distribution of spatial domain is to globally reduce the computing resource.
作者
王同生
孙中国
黄柱
席光
WANG Tong-Sheng;SUN Zhong-Guo;HUANG Zhu;XI Guang(School of Energy and Power Engineering,Xi'an Jiaotong University,Xi'an 710049,China;Center of Turbulence Research,Stanford University,California 94305-3024,USA)
出处
《工程热物理学报》
EI
CAS
CSCD
北大核心
2021年第5期1205-1212,共8页
Journal of Engineering Thermophysics
基金
国家自然科学基金(No.51790512)。
关键词
流场重构
神经网络
局部径向基函数
翼型绕流
reconstruction of flow field
neural network
local radial basis function
fluid flows past airfoils
