A priori screening of data-enabled turbulence models

Chen，Peng E.S.1; Bin，Yuanwei2,3; Yang，Xiang I.A.2; Shi，Yipeng3,4; Abkar，Mahdi5; Park，George I.6

2023-12-01

10.1103/PhysRevFluids.8.124606

Physical Review Fluids   影响因子和分区

2469-990X

Assessing the compliance of a white-box turbulence model with known turbulent knowledge is straightforward. It enables users to screen conventional turbulence models and identify apparent inadequacies, thereby allowing for a more focused and fruitful validation and verification. However, comparing a black-box machine-learning model to known empirical scalings is not straightforward. Unless one implements and tests the model, it would not be clear if a machine-learning model, trained at finite Reynolds numbers preserves the known high Reynolds number limit. This is inconvenient, particularly because model implementation involves retraining and reinterfacing. This work attempts to address this issue, allowing fast a priori screening of machine-learning models that are based on feed-forward neural networks (FNN). The method leverages the mathematical theorems we present in the paper. These theorems offer estimates of a network's limits even when the exact weights and biases are unknown. For demonstration purposes, we screen existing machine-learning wall models and RANS models for their compliance with the log layer physics and the viscous layer physics in an a priori manner. In addition, the theorems serve as essential guidelines for future machine-learning models.

EI ; SCI

英语

第一

20240115306464

Feedforward neural networks ; Machine learning ; Reynolds number

Fluid Flow, General:631.1 ; Artificial Intelligence:723.4

2-s2.0-85180971320

Scopus

1.Department of Mechanics and Aerospace Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.Mechanical Engineering,Pennsylvania State University,16802,United States
3.College of Engineering,Peking University,Beijing,100871,China
4.State Key Laboratory of Turbulence and Complex Systems,Beijing,100871,China
5.Department of Mechanical and Production Engineering,Aarhus University,Aarhus N,8200,Denmark
6.Department of Mechanical Engineering and Applied Mechanics,University of Pennsylvania,Philadelphia,19104,United States

Chen，Peng E.S.,Bin，Yuanwei,Yang，Xiang I.A.,et al. A priori screening of data-enabled turbulence models[J]. Physical Review Fluids,2023,8(12).

Chen，Peng E.S.,Bin，Yuanwei,Yang，Xiang I.A.,Shi，Yipeng,Abkar，Mahdi,&Park，George I..(2023).A priori screening of data-enabled turbulence models.Physical Review Fluids,8(12).

Chen，Peng E.S.,et al."A priori screening of data-enabled turbulence models".Physical Review Fluids 8.12(2023).