Alternative Artificial Neural Network Structures for Turbulent Flow Velocity Field Prediction

Turbulence in fluids has been a popular research topic for many years due to its influence on a wide range of applications. Computational Fluid Dynamics (CFD) tools are able to provide plenty of information about this phenomenon, but their computational cost often makes the use of these tools unfeasible. For that reason, in recent years, turbulence modelling using Artificial Neural Networks (ANNs) is becoming increasingly popular. These networks typically calculate directly the desired magnitude, having input information about the computational domain. In this paper, a Convolutional Neural Network (CNN) for predicting different magnitudes of turbulent flows around different geometries by approximating the equations of the Reynolds-Averaged Navier-Stokes (RANS)-based realizable k-ε two-layer turbulence model is proposed. Using that CNN, alternative network structures are proposed to predict the velocity fields of a turbulent flow around different geometries on a rectangular channel, with a preliminary stage to predict pressure and vorticity fields before calculating the velocity fields, and the obtained results are compared with the ones obtained with the basic structure. The results demonstrate that the proposed structures clearly outperform the basic one, especially when the flow becomes uncertain. In addition, considering the results, the best network configuration is proposed. That network is tested with a domain with multiple geometries and a domain with a narrowing of the channel, which are domains with different conditions from the training ones, showing fairly accurate predictions.

[1]  Hassan Ghassemi,et al.  Performance predicting of 2D and 3D submerged hydrofoils using CFD and ANNs , 2017 .

[2]  Gang Sun,et al.  Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimization , 2019, Aerospace Science and Technology.

[3]  Luning Sun,et al.  Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data , 2019, Computer Methods in Applied Mechanics and Engineering.

[4]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[5]  A. Mohan,et al.  Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence , 2019, 1903.00033.

[6]  Botros N. Hanna,et al.  Coarse-Grid Computational Fluid Dynamics (CG-CFD) Error Prediction using Machine Learning. , 2017, 1710.09105.

[7]  Donghyun You,et al.  Prediction of laminar vortex shedding over a cylinder using deep learning , 2017 .

[8]  Xinshuai Zhang,et al.  Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization , 2021, Computer Methods in Applied Mechanics and Engineering.

[9]  Nils Thuerey,et al.  Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows , 2018, AIAA Journal.

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Xiangyang Wang,et al.  Aerodynamic shape optimization using a novel optimizer based on machine learning techniques , 2019, Aerospace Science and Technology.

[12]  Nam Dinh,et al.  Computationally Efficient CFD Prediction of Bubbly Flow using Physics-Guided Deep Learning , 2019, International Journal of Multiphase Flow.

[13]  L. Guibas,et al.  A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries , 2020, ArXiv.

[14]  Jan S. Hesthaven,et al.  An artificial neural network as a troubled-cell indicator , 2018, J. Comput. Phys..

[15]  L. Richardson,et al.  The Deferred Approach to the Limit. Part I. Single Lattice. Part II. Interpenetrating Lattices , 1927 .

[16]  Liang Deng,et al.  A CNN-based shock detection method in flow visualization , 2019, Computers & Fluids.

[17]  Wei Li,et al.  Convolutional Neural Networks for Steady Flow Approximation , 2016, KDD.

[18]  T. Shih,et al.  A new k-ϵ eddy viscosity model for high reynolds number turbulent flows , 1995 .

[19]  Sauro Succi,et al.  Deep learning for turbulent channel flow , 2018, 1812.02241.

[20]  Liang Deng,et al.  Key time steps selection for CFD data based on deep metric learning , 2019 .

[21]  A. Dengel,et al.  DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks , 2020, ArXiv.

[22]  Jie Liu,et al.  A CNN-based vortex identification method , 2018, J. Vis..