Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network
Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network
复制标题
使用人工神经网络进行各向同性湍流大涡模拟的亚网格尺度模型
DOI：
10.1016/j.compfluid.2019.104319
复制
发表时间：
2019
影响因子：
2.8
通讯作者：
Jin Guodong
中科院分区：
文献类型：
--
作者：
Zhou Zhideng;He Guowei;Wang Shizhao;Jin Guodong
利用人工神经网络建立了亚网格应力张量与流场的关系，建立了一种新的亚网格应力张量模型，用于各向同性湍流的大涡模拟。通过对各向同性湍流的直接数值模拟（DNSs）的流场进行滤波操作，提供了训练和测试ANN所需的数据。我们使用速度梯度张量和滤波器宽度作为输入特征，SGS应力张量作为输出标签来训练神经网络，在训练好的神经网络模型的优先级中，通过计算能量传递率的相关系数和相对误差来比较从神经网络模型和DNS数据获得的SGS应力张量。相关系数大多大于0.9，人工神经网络模型可以准确地预测能量传递率在不同的雷诺数和过滤器的宽度，显示出显着的改进，比传统的模型，如梯度模型，Smagorinsky模型及其动态版本。一个真实的LES使用训练的神经网络模型进行后验验证。用改进的ANN模型计算的能谱与几种SGS模型进行了比较。改进的ANN模型得到的流体粒子对的拉格朗日统计量与过滤DNS的结果接近，优于Smagorinsky模型和动态Smagorinsky模型的结果。
An artificial neural network (ANN) is used to establish the relation between the resolved-scale flow field and the subgrid-scale (SGS) stress tensor, to develop a new SGS model for large-eddy simulation (LES) of isotropic turbulent flows. The data required for training and testing of the ANN are provided by performing filtering operations on the flow fields from direct numerical simulations (DNSs) of isotropic turbulent flows. We use the velocity gradient tensor together with filter width as input features and the SGS stress tensor as the output labels for training the ANN. In thea prioritest of the trained ANN model, the SGS stress tensors obtained from the ANN model and the DNS data are compared by computing the correlation coefficient and the relative error of the energy transfer rate. The correlation coefficients are mostly larger than 0.9, and the ANN model can accurately predict the energy transfer rate at different Reynolds numbers and filter widths, showing significant improvement over the conventional models, for example the gradient model, the Smagorinsky model and its dynamic version. A real LES using the trained ANN model is performed as thea posteriorivalidation. The energy spectrum computed by the improved ANN model is compared with several SGS models. The Lagrangian statistics of fluid particle pairs obtained from the improved ANN model almost approach those from the filtered DNS, better than the results from the Smagorinsky model and dynamic Smagorinsky model.