Machine learning methods for turbulence modeling in subsonic flows around airfoils
Machine learning methods for turbulence modeling in subsonic flows around airfoils
复制标题
机翼周围亚音速流动湍流建模的机器学习方法
DOI：
10.1063/1.5061693
复制
发表时间：
2018-06
影响因子：
4.6
通讯作者：
Yilang Liu
中科院分区：
文献类型：
--
作者：
Linyang Zhu;Weiwei Zhang;Jiaqing Kou;Yilang Liu
在未来的几十年里，雷诺平均纳维尔-斯托克斯（RANS）方法仍将在航空航天工程中发挥重要作用。尽管RANS模型被广泛使用，但模型之间的不一致性和较大的差异降低了模拟复杂流动的可靠性。因此，近年来，数据驱动湍流模型引起了流体力学界的广泛关注。基于实验/数值模拟结果，该方法旨在通过机器学习技术修改或构建特定目的的湍流模型。本文将SA模型计算的结果作为训练数据。与低雷诺数湍流不同，高雷诺数湍流数据具有明显的尺度效应，这给数据驱动的数值模拟带来了困难。为了提高拟合精度，将流场划分为近壁区、尾迹区和远场区，并对每个区域分别建立模型。本文采用径向基函数神经网络（RBFNN）和一些辅助优化算法来重构平均变量与涡粘性之间的映射函数。由于该模型反映了局部流动特性与湍流涡粘性的关系，因此与翼型形状和流动条件无关。本文中的训练数据仅由NACA 0012翼型的三个亚音速流场计算产生。将该方法与N-S方程耦合，计算了不同流动工况和两种不同翼型的涡粘性等值线、壁面法向沿着速度分布和表面摩擦系数分布等，与SA模型进行了比较，结果显示了合理的精度和更好的效率，表明了数据驱动方法在湍流模拟中的积极前景。
Reynolds-Averaged Navier-Stokes(RANS) method will still play a vital role in the following several decade in aerospace engineering. Although RANS models are widely used, empiricism and large discrepancies between models reduce the reliability of simulating complex flows. Therefore, in recent years, data-driven turbulence model has aroused widespread concern in fluid mechanics. Based on the experimental/numerical simulation results, this approach aims to modify or construct the turbulence model for specific purposes by machine learning technologies. In this paper, we take the results calculated by SA model as training data. Different from low Reynolds number turbulent flows, the data from high Reynolds number flows shows an apparent scaling effect, thus leading to difficulties in the data-driven modeling. In order to improve the fitting accuracy, we divided the flow field into near-wall region, wake region, and far-field region, and built individual model for every region. In this paper, we adopted the radial basis function neural network (RBFNN) and some auxiliary optimization algorithms to reconstruct a mapping function between mean variables and the eddy viscosity. Since this model reflects the relationship between local flow characteristics and turbulent eddy viscosity, it is independent on the airfoil shape and flow condition. The training data in this paper is generated from only three subsonic flow calculations of NACA0012 airfoil. By coupling the proposed approach with N-S equations, we calculated various flow cases as well as two different airfoils and showed the eddy viscosity contours, velocity profiles along the normal direction of wall and skin friction coefficient distributions, etc. Compared with the SA model, the results show a reasonable accuracy and better efficiency, which indicates the positive prospect of data-driven methods in turbulence modeling.
登录
查看更多内容
DOI：
--
发表时间：
1997-04
期刊：
--
影响因子：
--
作者：
J. Bardina;P. Huang;T. Coakley
通讯作者：
J. Bardina;P. Huang;T. Coakley
DOI：
10.1109/ijcnn.2004.1380131
发表时间：
2004-07
期刊：
2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
影响因子：
--
作者：
M. K. Muezzinoglu;J. Zurada
通讯作者：
M. K. Muezzinoglu;J. Zurada
影响因子：
2.5
作者：
Weiwei Zhang;B. Wang;Zhengyin Ye;Jingge Quan
通讯作者：
Weiwei Zhang;B. Wang;Zhengyin Ye;Jingge Quan
影响因子：
2.5
作者：
Weiwei Zhang;J. Kou;Ziyi Wang
通讯作者：
Weiwei Zhang;J. Kou;Ziyi Wang
DOI：
--
发表时间：
1991-01
期刊：
--
影响因子：
--
作者：
J. Brock
通讯作者：
J. Brock