Machine-learning for turbulence and heat-flux model development: A review of challenges associated with distinct physical phenomena and progress to date

被引:35
作者
Sandberg, Richard D. [1 ]
Zhao, Yaomin [1 ,2 ]
机构
[1] Univ Melbourne, Dept Mech Engn, Melbourne, Vic 3010, Australia
[2] Peking Univ, Coll Engn, Ctr Appl Phys & Technol, HEDPS, Beijing 100871, Peoples R China
基金
澳大利亚研究理事会; 中国国家自然科学基金;
关键词
Turbulent flows; Turbulent heat transfer; RANS; Machine learning; Data-driven methods; ALGEBRAIC STRESS MODELS; DEEP NEURAL-NETWORKS; DATA-DRIVEN; FORM UNCERTAINTIES; 2-EQUATION MODEL; SEPARATED FLOW; TRANSITION; SIMULATIONS; PREDICTION; EQUATIONS;
D O I
10.1016/j.ijheatfluidflow.2022.108983
中图分类号
O414.1 [热力学];
学科分类号
摘要
This review paper surveys some of the progress made to date in the use of machine learning (ML) for turbulence and heat transfer modeling. We start by identifying the challenges that various flow phenomena pose to closure modeling. These range from the misalignment between the turbulence stress tensor with the strain rates, that cannot be captured by linear stress-strain relationships, to non-constant turbulence Prandtl numbers, the coupling of multiple closures and deterministic unsteadiness, to name a few. We then introduce several machine learning concepts and frameworks for turbulence stress and heat-flux closure modeling, with a focus on model consistency. Various examples are then provided where applications of ML methods have to some degree succeeded at addressing the identified modeling challenges. We close by outlining some of the remaining challenges, in particular around the generalizability of ML-based models. Overall, further advances in ML techniques and availability of high-quality data sets will see this exciting research direction thrive and promises to lead to improved models with a wider range of applicability.
引用
收藏
页数:18
相关论文
共 125 条
[11]   Discovering governing equations from data by sparse identification of nonlinear dynamical systems [J].
Brunton, Steven L. ;
Proctor, Joshua L. ;
Kutz, J. Nathan .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (15) :3932-3937
[12]   Physics-informed neural networks (PINNs) for fluid mechanics: a review [J].
Cai, Shengze ;
Mao, Zhiping ;
Wang, Zhicheng ;
Yin, Minglang ;
Karniadakis, George Em .
ACTA MECHANICA SINICA, 2021, 37 (12) :1727-1738
[13]   The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling [J].
Cruz, Matheus A. ;
Thompson, Roney L. ;
Sampaio, Luiz E. B. ;
Bacchi, Raphael D. A. .
COMPUTERS & FLUIDS, 2019, 192
[14]   TRANSPORT EQUATIONS IN TURBULENCE [J].
DALY, BJ ;
HARLOW, FH .
PHYSICS OF FLUIDS, 1970, 13 (11) :2634-&
[15]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199
[16]  
Duraisamy K., 2015, 53 AIAA AEROSPACE SC, P1284
[18]   Turbulence Modeling in the Age of Data [J].
Duraisamy, Karthik ;
Iaccarino, Gianluca ;
Xiao, Heng .
ANNUAL REVIEW OF FLUID MECHANICS, VOL 51, 2019, 51 :357-377
[19]   SEPARATED FLOW COMPUTATIONS WITH THE K-EPSILON-UPSILON(2) MODEL [J].
DURBIN, PA .
AIAA JOURNAL, 1995, 33 (04) :659-664
[20]   Transition beneath vortical disturbances [J].
Durbin, Paul ;
Wu, Xiaohua .
ANNUAL REVIEW OF FLUID MECHANICS, 2007, 39 (107-128) :107-128