Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. The Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.

[1]  G. F. Smith.  On isotropic integrity bases , 1965 .

[2]  S. Pope.  A more general effective-viscosity hypothesis , 1975, Journal of Fluid Mechanics.

[3]  T. Gatski,et al.  On explicit algebraic stress models for complex turbulent flows , 1992, Journal of Fluid Mechanics.

[4]  B. Launder,et al.  Development and application of a cubic eddy-viscosity model of turbulence , 1996 .

[5]  John Kim,et al.  DIRECT NUMERICAL SIMULATION OF TURBULENT CHANNEL FLOWS UP TO RE=590 , 1999 .

[6]  Arne V. Johansson,et al.  An explicit algebraic Reynolds stress model for incompressible and compressible turbulent flows , 2000, Journal of Fluid Mechanics.

[7]  Michele Milano,et al.  Neural network modeling for near wall turbulent flow , 2002 .

[8]  Stefan P. Domino,et al.  SIERRA/Fuego: A Multi-Mechanics Fire Environment Simulation Tool , 2003 .

[9]  K. S. Ball,et al.  Dynamical eigenfunction decomposition of turbulent channel flow , 1991, physics/0608257.

[10]  F. Durst,et al.  Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches , 2007 .

[11]  Gianluca Iaccarino,et al.  A numerical study of scalar dispersion downstream of a wall-mounted cube using direct simulations and algebraic flux models , 2010 .

[12]  Alfredo Pinelli,et al.  Reynolds number dependence of mean flow structure in square duct turbulence , 2010, Journal of Fluid Mechanics.

[13]  Uwe Ehrenstein,et al.  Instability of streaks in wall turbulence with adverse pressure gradient , 2011, Journal of Fluid Mechanics.

[14]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[15]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[16]  Brendan D. Tracey,et al.  Application of supervised learning to quantify uncertainties in turbulence and combustion modeling , 2013 .

[17]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[18]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Srinivasan Arunajatesan,et al.  Bayesian calibration of a k-e turbulence model for predictive jet-in-crossflow simulations. , 2014 .

[20]  Brendan D. Tracey,et al.  A Machine Learning Strategy to Assist Turbulence Model Development , 2015 .

[21]  Guilhem Lacaze,et al.  Flow topologies and turbulence scales in a jet-in-cross-flow , 2015 .

[22]  Julia Ling,et al.  Analysis of Turbulent Scalar Flux Models for a Discrete Hole Film Cooling Flow , 2015 .

[23]  J. Templeton.  Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty , 2015 .

[24]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[25]  Karthikeyan Duraisamy,et al.  Machine Learning Methods for Data-Driven Turbulence Modeling , 2015 .

[26]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[27]  Uncertainty Analysis and Data-Driven Model Advances for a Jet-in-Crossflow , 2016 .

[28]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[29]  Karthik Duraisamy,et al.  A paradigm for data-driven predictive modeling using field inversion and machine learning , 2016, J. Comput. Phys..

[30]  Julia Ling,et al.  Machine learning strategies for systems with invariance properties , 2016, J. Comput. Phys..

[31]  Julia Ling,et al.  Analysis of Turbulent Scalar Flux Models for a Discrete Hole Film Cooling Flow , 2015 .

[32]  Guilhem Lacaze,et al.  UNCERTAINTY ANALYSIS AND DATA-DRIVEN MODEL ADVANCES FOR A JET-IN-CROSSFLOW , 2016 .