Artificial neural network approach to large-eddy simulation of compressible isotropic turbulence
Artificial neural network approach to large-eddy simulation of compressible isotropic turbulence
复制标题
可压缩各向同性湍流大涡模拟的人工神经网络方法
DOI：
10.1103/physreve.99.053113
复制
发表时间：
2019
影响因子：
2.4
通讯作者：
Ma Chao
中科院分区：
文献类型：
--
作者：
Xie Chenyue;Wang Jianchun;Li Ke;Ma Chao
采用数据驱动框架，建立了可压缩各向同性湍流大涡模拟的亚格子模型。采用基于局部模板几何的人工神经网络(ANN)对未闭合的SGS项进行预测。输入特征是基于过滤速度和温度的一阶和二阶导数，这些导数出现在SGS应力和热流的二阶Taylor近似中。结果表明，本文提出的ANN-7模型比梯度模型具有更好的优先性能。与最优先的梯度模型相比，ANN-7模型的相关系数较大，相对误差较小。在后验分析中，ANN-7模型在速度、温度谱函数和结构函数以及瞬时流动结构的预报上明显优于动态Smagorinsky模型和动态混合模型。人工神经网络是一种很有前途的工具，可以用来理解SGS非闭合项的物理基础，但需要进一步改进。
A subgrid-scale (SGS) model for large-eddy simulation (LES) of compressible isotropic turbulence is constructed by using a data-driven framework. An artificial neural network (ANN) based on local stencil geometry is employed to predict the unclosed SGS terms. The input features are based on the first-order and second-order derivatives of filtered velocity and temperature which appear in the second-order Taylor approximation of the SGS stress and heat flux. It is shown that the proposed ANN-7 model performs better than the gradient model in thea prioritest. The correlation coefficient is larger and the relative error is smaller for ANN-7 model as compared to those of the gradient model in thea prioritest. In ana posteriorianalysis, the performance of ANN-7 model shows advantage over the dynamic Smagorinsky model and dynamic mixed model in the prediction of spectra and structure functions of velocity and temperature, and instantaneous flow structures. Artificial neural network is a promising tool for understanding the physical fundamentals of SGS unclosed terms with further improvement.