帮助 关于我们

返回检索结果

Application of deep learning method to Reynolds stress models of channel flow based on reduced-order modeling of DNS data

查看参考文献28篇

Zhang Zhen 1,2   Song Xudong 3   Ye Shuran 1,2   Wang Yiwei 1,2 *   Huang Chenguang 1,2   An Yiran 3   Chen Yaosong 3  
文摘 Recently, the methodology of deep learning is used to improve the calculation accuracy of the Reynolds-averaged Navier-Stokes (RANS) model. In this paper, a neural network is designed to predict the Reynolds stress of a channel flow of different Reynolds numbers. The rationality and the high efficiency of the neural network is validated by comparing with the results of the direct numerical simulation (DNS), the large eddy simulation (LES), and the deep neural network (DNN) of other studies. To further enhance the prediction accuracy, three methods are developed by using several algorithms and simplified models in the neural network. In the method 1, the regularization is introduced and it is found that the oscillation and the overfitting of the results are effectively prevented. In the method 2, y~+ is embedded in the input variable while the combination of the invariants is simplified in the method 3. From the predicted results, it can be seen that by using the first two methods, the errors are reduced. Moreover, the method 3 shows considerable advantages in the DNS trend and the smoothness of a curve. Consequently, it is concluded that the DNNs can predict effectively the anisotropic Reynolds stress and is a promising technique of the computational fluid dynamics.
来源 Journal of Hydrodynamics ,2019,31(1):58-65 【核心库】
DOI 10.1007/s42241-018-0156-9
关键词 Deep neural network ; channel flow ; turbulence model ; Reynolds stress
地址

1. Institute of Mechanics, Chinese Academy of Sciences, Key Laboratory for Mechanics in Fluid Solid Coupling Systems, Chinese Academy of Sciences, Beijing, 100190  

2. College of Engineering Science, University of Chinese Academy of Sciences, Beijing, 100049  

3. College of Engineering, Peking University, Beijing, 100871

语种 英文
文献类型 研究性论文
ISSN 1001-6058
基金 supported by the National Key R&D Program
文献收藏号 CSCD:6426636

参考文献 共 28 共2页

1.  Vandriest E R. On turbulent flow near a wall. Journal of the Aeronautical Sciences,1956,23(11):1007-1011 CSCD被引 29 次    
2.  Feiereisen W J. Numerical simulation of a compressible homogeneous, turbulent shear flow. Doctoral Thesis,1981 CSCD被引 1 次    
3.  Benzi R. On the statistical properties of two-dimensional decaying turbulence. Europhysics Letters,1987,3(7):811-818 CSCD被引 1 次    
4.  Brachet M E. Small-scale dynamics of high-reynolds-number two-dimensional turbulence. Physical Review Letters,1986,57(6):683-686 CSCD被引 1 次    
5.  Gilbert A D. Spiral structures and spectra in two-dimensional turbulence. Journal of Fluid Mechanics,1988,193:475-497 CSCD被引 2 次    
6.  Pope S B. Turbulent flows,2001 CSCD被引 18 次    
7.  Rodi W. On the simulation of turbulent flow past bluff bodies. Journal of Wind Engineering and Industrial Aerodynamics,1993,46/47:3-19 CSCD被引 2 次    
8.  Speziale C G. A review of Reynolds stress models for turbulent shear flows. 20th Symposium on Naval Hydrodynamics,1995 CSCD被引 1 次    
9.  Spalart P R. Philosophies and fallacies in turbulence modeling. Progress in Aerospace Sciences,2015,74:1-15 CSCD被引 11 次    
10.  Dutta R. Five-equation and robust three-equation method for solution verification of large eddy simulations. Journal of Hydrodynamics,2018,30(1):23-33 CSCD被引 5 次    
11.  Cheng H Y. URANS simulations of the tip-leakage cavitating flow with verification and validation procedures. Journal of Hydrodynamics,2018,30(3):531-534 CSCD被引 4 次    
12.  Wang C C. Numerical simulation of transient turbulent cavitating flows with special emphasis on shock wave dynamics considering the water/vapor compressibility. Journal of Hydrodynamics,2018,30(4):573-591 CSCD被引 9 次    
13.  Hinton G. Reducing the dimensionality of data with neural networks. Science,2006,313(5786):504-507 CSCD被引 1819 次    
14.  Tracey B. Application of supervised learning to quantify uncertainties in turbulence and combustion modeling. 51st AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition.2013-0259,2013 CSCD被引 1 次    
15.  Ling J. Uncertainty analysis and data-driven model advances for a jet-in-crossflow. Journal of Turbomachinery,2016,139(2):021008 CSCD被引 5 次    
16.  Ling J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. Journal of Fluid Mechanics,2016,807:155-166 CSCD被引 108 次    
17.  Kutz J N. Deep earning in fluid dynamics. Journal of Fluid Mechanics,2017,814:1-4 CSCD被引 48 次    
18.  Wang J X. Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data. Physical Review Fluids,2017,2(3):1-22 CSCD被引 38 次    
19.  Xiao H. Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: A data-driven, physics-informed Bayesian approach. Journal of Computational Physics,2016,324(C):115-136 CSCD被引 22 次    
20.  Lecun Y. Deep learning. Nature,2015,521(7553):436 CSCD被引 3424 次    
引证文献 16 篇

1 Huang Biao A review of transient flow structure and unsteady mechanism of cavitating flow Journal of Hydrodynamics,2019,31(3):429-444
CSCD被引 26 次

2 张伟伟 机器学习在湍流模型构建中的应用进展 空气动力学学报,2019,37(3):444-454
CSCD被引 28 次

显示所有16篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号