Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty
Abstract
Reynolds Averaged Navier Stokes (RANS) models are widely used in industry to predict fluid flows, despite their acknowledged deficiencies. Not only do RANS models often produce inaccurate flow predictions, but there are very limited diagnostics available to assess RANS accuracy for a given flow configuration. If experimental or higher fidelity simulation results are not available for RANS validation, there is no reliable method to evaluate RANS accuracy. This paper explores the potential of utilizing machine learning algorithms to identify regions of high RANS uncertainty. Three different machine learning algorithms were evaluated: support vector machines, Adaboost decision trees, and random forests. The algorithms were trained on a database of canonical flow configurations for which validated direct numerical simulation or large eddy simulation results were available, and were used to classify RANS results on a point-by-point basis as having either high or low uncertainty, based on the breakdown of specific RANS modeling assumptions. Classifiers were developed for three different basic RANS eddy viscosity model assumptions: the isotropy of the eddy viscosity, the linearity of the Boussinesq hypothesis, and the non-negativity of the eddy viscosity. It is shown that these classifiers are able to generalize to flows substantially different from those on whichmore »
- Authors:
-
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1235329
- Report Number(s):
- SAND-2015-2173J
Journal ID: ISSN 1070-6631; PHFLE6; 579403
- Grant/Contract Number:
- AC04-94AL85000
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Physics of Fluids
- Additional Journal Information:
- Journal Volume: 27; Journal Issue: 8; Journal ID: ISSN 1070-6631
- Publisher:
- American Institute of Physics
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Reynolds stress modeling; Navier Stokes equations; viscosity; databases; Eddy viscosity closure
Citation Formats
Ling, Julia, and Templeton, Jeremy Alan. Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty. United States: N. p., 2015.
Web. doi:10.1063/1.4927765.
Ling, Julia, & Templeton, Jeremy Alan. Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty. United States. https://doi.org/10.1063/1.4927765
Ling, Julia, and Templeton, Jeremy Alan. Tue .
"Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty". United States. https://doi.org/10.1063/1.4927765. https://www.osti.gov/servlets/purl/1235329.
@article{osti_1235329,
title = {Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty},
author = {Ling, Julia and Templeton, Jeremy Alan},
abstractNote = {Reynolds Averaged Navier Stokes (RANS) models are widely used in industry to predict fluid flows, despite their acknowledged deficiencies. Not only do RANS models often produce inaccurate flow predictions, but there are very limited diagnostics available to assess RANS accuracy for a given flow configuration. If experimental or higher fidelity simulation results are not available for RANS validation, there is no reliable method to evaluate RANS accuracy. This paper explores the potential of utilizing machine learning algorithms to identify regions of high RANS uncertainty. Three different machine learning algorithms were evaluated: support vector machines, Adaboost decision trees, and random forests. The algorithms were trained on a database of canonical flow configurations for which validated direct numerical simulation or large eddy simulation results were available, and were used to classify RANS results on a point-by-point basis as having either high or low uncertainty, based on the breakdown of specific RANS modeling assumptions. Classifiers were developed for three different basic RANS eddy viscosity model assumptions: the isotropy of the eddy viscosity, the linearity of the Boussinesq hypothesis, and the non-negativity of the eddy viscosity. It is shown that these classifiers are able to generalize to flows substantially different from those on which they were trained. As a result, feature selection techniques, model evaluation, and extrapolation detection are discussed in the context of turbulence modeling applications.},
doi = {10.1063/1.4927765},
journal = {Physics of Fluids},
number = 8,
volume = 27,
place = {United States},
year = {Tue Aug 04 00:00:00 EDT 2015},
month = {Tue Aug 04 00:00:00 EDT 2015}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 200 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Bayesian uncertainty quantification applied to RANS turbulence models
journal, December 2011
- Oliver, Todd A.; Moser, Robert D.
- Journal of Physics: Conference Series, Vol. 318, Issue 4
Bayesian uncertainty analysis with applications to turbulence modeling
journal, September 2011
- Cheung, Sai Hung; Oliver, Todd A.; Prudencio, Ernesto E.
- Reliability Engineering & System Safety, Vol. 96, Issue 9
Bayesian estimates of parameter variability in the k–ε turbulence model
journal, February 2014
- Edeling, W. N.; Cinnella, P.; Dwight, R. P.
- Journal of Computational Physics, Vol. 258
Tuning a RANS k-e model for jet-in-crossflow simulations
report, September 2013
- Lefantzi, Sophia; Ray, Jaideep; Arunajatesan, Srinivasan
On predicting the turbulence‐induced secondary flows using nonlinear k ‐ε models
journal, July 1996
- Mompean, G.; Gavrilakis, S.; Machiels, L.
- Physics of Fluids, Vol. 8, Issue 7
Development and application of a cubic eddy-viscosity model of turbulence
journal, April 1996
- Craft, T. J.; Launder, B. E.; Suga, K.
- International Journal of Heat and Fluid Flow, Vol. 17, Issue 2
Progress in the development of a Reynolds-stress turbulence closure
journal, April 1975
- Launder, B. E.; Reece, G. J.; Rodi, W.
- Journal of Fluid Mechanics, Vol. 68, Issue 3
An explicit algebraic Reynolds stress model for incompressible and compressible turbulent flows
journal, January 2000
- Wallin, Stefan; Johansson, Arne V.
- Journal of Fluid Mechanics, Vol. 403
On explicit algebraic stress models for complex turbulent flows
journal, September 1993
- Gatski, T. B.; Speziale, C. G.
- Journal of Fluid Mechanics, Vol. 254
Turbulent channel and Couette flows using an anisotropic k-epsilon model
journal, March 1987
- Nisizima, Shoiti; Yoshizawa, Akira
- AIAA Journal, Vol. 25, Issue 3
RANS modeling of turbulent mixing for a jet in supersonic cross flow: model evaluation and uncertainty quantification
conference, January 2012
- Gorle, C.; Emory, M.; Iaccarino, Gianluca
- Proceeding of THMT-12. Proceedings of the Seventh International Symposium On Turbulence, Heat and Mass Transfer Palermo, Italy, 24-27 September, 2012
On the non-local geometry of turbulence
journal, April 2008
- Bermejo-Moreno, IvÁN; Pullin, D. I.
- Journal of Fluid Mechanics, Vol. 603
Quantification of Structural Uncertainties in the k -w Turbulence Model
conference, June 2012
- Dow, Eric; Wang, Qiqi
- 52nd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
Uncertainty Quantification of Structural Uncertainties in RANS Simulations of Complex Flows
conference, June 2012
- Dow, Eric; Wang, Qiqi
- 20th AIAA Computational Fluid Dynamics Conference
New Approaches in Turbulence and Transition Modeling Using Data-driven Techniques
conference, January 2015
- Duraisamy, Karthikeyan; Zhang, Ze J.; Singh, Anand Pratap
- 53rd AIAA Aerospace Sciences Meeting
Application of Supervised Learning to Quantify Uncertainties in Turbulence and Combustion Modeling
conference, January 2013
- Tracey, Brendan; Duraisamy, Karthik; Alonso, Juan
- 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition
A Machine Learning Strategy to Assist Turbulence Model Development
conference, January 2015
- Tracey, Brendan D.; Duraisamy, Karthikeyan; Alonso, Juan J.
- 53rd AIAA Aerospace Sciences Meeting
A numerical study of algebraic flux models for heat and mass transport simulation in complex flows
journal, October 2010
- Rossi, Riccardo
- International Journal of Heat and Mass Transfer, Vol. 53, Issue 21-22
A numerical study of scalar dispersion downstream of a wall-mounted cube using direct simulations and algebraic flux models
journal, October 2010
- Rossi, R.; Philips, D. A.; Iaccarino, G.
- International Journal of Heat and Fluid Flow, Vol. 31, Issue 5
Numerical analysis and modeling of plume meandering in passive scalar dispersion downstream of a wall-mounted cube
journal, October 2013
- Rossi, R.; Iaccarino, G.
- International Journal of Heat and Fluid Flow, Vol. 43
Near Wall Modeling for Trailing Edge Slot Film Cooling
journal, September 2014
- Ling, Julia; Rossi, Riccardo; Eaton, John K.
- Journal of Fluids Engineering, Vol. 137, Issue 2
Turbulent transport in an inclined jet in crossflow
journal, October 2013
- Coletti, F.; Benson, M. J.; Ling, J.
- International Journal of Heat and Fluid Flow, Vol. 43
Direct numerical simulation of turbulent channel flow up to Reτ=590
journal, April 1999
- Moser, Robert D.; Kim, John; Mansour, Nagi N.
- Physics of Fluids, Vol. 11, Issue 4
Reynolds number dependence of mean flow structure in square duct turbulence
journal, February 2010
- Pinelli, Alfredo; Uhlmann, Markus; Sekimoto, Atsushi
- Journal of Fluid Mechanics, Vol. 644
Flow topologies and turbulence scales in a jet-in-cross-flow
journal, April 2015
- Ruiz, A. M.; Lacaze, G.; Oefelein, J. C.
- Physics of Fluids, Vol. 27, Issue 4
Bayesian calibration of a k-ε turbulence model for predictive jet-in-crossflow simulations
conference, June 2014
- Ray, Jaideep; Lefantzi, Sophia; Arunajatesan, Srinivasan
- 44th AIAA Fluid Dynamics Conference
Estimation of k-ε parameters using surrogate models and jet-in-crossflow data
report, November 2014
- Lefantzi, Sophia; Ray, Jaideep; Arunajatesan, Srinivasan
SIERRA/Fuego: A Multi-Mechanics Fire Environment Simulation Tool
conference, November 2012
- Domino, Stefan; Moen, Chris; Burns, Shawn
- 41st Aerospace Sciences Meeting and Exhibit
Validation of an FSI Modeling Framework for Internal Captive Carriage Applications
conference, May 2013
- Arunajatesan, Srinivasan; Ross, Michael R.; Garrett, Tyler J.
- 19th AIAA/CEAS Aeroacoustics Conference
Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling
journal, November 2003
- Svetnik, Vladimir; Liaw, Andy; Tong, Christopher
- Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 6
Distributed Pasting of Small Votes
book, January 2002
- Chawla, N. V.; Hall, L. O.; Bowyer, K. W.
- Multiple Classifier Systems
Creating ensembles of classifiers
conference, January 2001
- Chawla, N.; Eschrich, S.; Hall, L. O.
- Proceedings 2001 IEEE International Conference on Data Mining
The return to isotropy of homogeneous turbulence
journal, June 2001
- Choi, Kwing-So; Lumley, John L.
- Journal of Fluid Mechanics, Vol. 436
Anisotropy analysis of turbulent swirl flow
journal, January 2014
- Radenkovic, Darko; Burazer, Jela; Novkovic, Djordje
- FME Transaction, Vol. 42, Issue 1
A more general effective-viscosity hypothesis
journal, November 1975
- Pope, S. B.
- Journal of Fluid Mechanics, Vol. 72, Issue 02
Combination of multiple classifiers using local accuracy estimates
conference, January 1996
- Woods, K.; Bowyer, K.; Kegelmeyer, W. P.
- Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A Comparison of Ensemble Creation Techniques
book, January 2004
- Banfield, Robert E.; Hall, Lawrence O.; Bowyer, Kevin W.
- Multiple Classifier Systems
Diagnosing extrapolation: tree-based density estimation
conference, January 2004
- Hooker, Giles
- Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '04
Analysis of Turbulent Scalar Flux Models for a Discrete Hole Film Cooling Flow
journal, October 2015
- Ling, Julia; Ryan, Kevin J.; Bodart, Julien
- Journal of Turbomachinery, Vol. 138, Issue 1
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides
journal, September 2020
- Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna
- Scientific Reports, Vol. 10, Issue 1
Turbulent Flows
journal, October 2001
- Pope, Stephen B.
- Measurement Science and Technology, Vol. 12, Issue 11
Combination of multiple classifiers using local accuracy estimates
journal, April 1997
- Woods, K.; Kegelmeyer, W. P.; Bowyer, K.
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, Issue 4
Works referencing / citing this record:
Uncertainty and global sensitivity analysis of bladed disk statics with material anisotropy and root geometry variations
journal, October 2019
- Rajasekharan, Rahul; Petrov, Evgeny
- Engineering Reports, Vol. 1, Issue 3
Prediction of Reynolds stresses in high-Mach-number turbulent boundary layers using physics-informed machine learning
journal, December 2018
- Wang, Jian-Xun; Huang, Junji; Duan, Lian
- Theoretical and Computational Fluid Dynamics, Vol. 33, Issue 1
A Priori Assessment of Prediction Confidence for Data-Driven Turbulence Modeling
journal, March 2017
- Wu, Jin-Long; Wang, Jian-Xun; Xiao, Heng
- Flow, Turbulence and Combustion, Vol. 99, Issue 1
Zonal Eddy Viscosity Models Based on Machine Learning
journal, February 2019
- Matai, R.; Durbin, P. A.
- Flow, Turbulence and Combustion, Vol. 103, Issue 1
The Current State of High-Fidelity Simulations for Main Gas Path Turbomachinery Components and Their Industrial Impact
journal, February 2019
- Sandberg, Richard D.; Michelassi, Vittorio
- Flow, Turbulence and Combustion, Vol. 102, Issue 4
Progress Variable Variance and Filtered Rate Modelling Using Convolutional Neural Networks and Flamelet Methods
journal, April 2019
- Nikolaou, Z. M.; Chrysostomou, C.; Vervisch, L.
- Flow, Turbulence and Combustion, Vol. 103, Issue 2
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
journal, October 2016
- Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy
- Journal of Fluid Mechanics, Vol. 807
A neural network approach for the blind deconvolution of turbulent flows
journal, October 2017
- Maulik, R.; San, O.
- Journal of Fluid Mechanics, Vol. 831
Subgrid modelling for two-dimensional turbulence using neural networks
journal, November 2018
- Maulik, R.; San, O.; Rasheed, A.
- Journal of Fluid Mechanics, Vol. 858
Deep learning of vortex-induced vibrations
journal, December 2018
- Raissi, Maziar; Wang, Zhicheng; Triantafyllou, Michael S.
- Journal of Fluid Mechanics, Vol. 861
Sub-grid scale model classification and blending through deep learning
journal, May 2019
- Maulik, Romit; San, Omer; Jacob, Jamey D.
- Journal of Fluid Mechanics, Vol. 870
Construction of reduced-order models for fluid flows using deep feedforward neural networks
journal, June 2019
- Lui, Hugo F. S.; Wolf, William R.
- Journal of Fluid Mechanics, Vol. 872
Prediction of turbulent heat transfer using convolutional neural networks
journal, November 2019
- Kim, Junhyuk; Lee, Changhoon
- Journal of Fluid Mechanics, Vol. 882
Hydrodynamic object identification with artificial neural models
journal, August 2019
- Lakkam, Sreetej; Balamurali, B. T.; Bouffanais, Roland
- Scientific Reports, Vol. 9, Issue 1
Using field inversion to quantify functional errors in turbulence closures
journal, April 2016
- Singh, Anand Pratap; Duraisamy, Karthik
- Physics of Fluids, Vol. 28, Issue 4
Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder
journal, April 2018
- Jin, Xiaowei; Cheng, Peng; Chen, Wen-Li
- Physics of Fluids, Vol. 30, Issue 4
Machine learning methods for turbulence modeling in subsonic flows around airfoils
journal, January 2019
- Zhu, Linyang; Zhang, Weiwei; Kou, Jiaqing
- Physics of Fluids, Vol. 31, Issue 1
Fast flow field prediction over airfoils using deep learning approach
journal, May 2019
- Sekar, Vinothkumar; Khoo, Boo Cheong
- Physics of Fluids, Vol. 31, Issue 5
Application of two-branch deep neural network to predict bubble migration near elastic boundaries
journal, October 2019
- Ma, Xiaojian; Wang, Chen; Huang, Biao
- Physics of Fluids, Vol. 31, Issue 10
Direct Numerical Simulation of Turbulent Flow Inside a Differentially Heated Composite Cavity
journal, May 2019
- Martínez, Javier; Merzari, Elia; Acton, Michael
- Nuclear Technology, Vol. 206, Issue 2
Reynolds-Averaged Turbulence Modeling Using Deep Learning with Local Flow Features: An Empirical Approach
journal, February 2020
- Chang, Chih-Wei; Fang, Jun; Dinh, Nam T.
- Nuclear Science and Engineering, Vol. 194, Issue 8-9
Modeling subgrid-scale force and divergence of heat flux of compressible isotropic turbulence by artificial neural network
journal, October 2019
- Xie, Chenyue; Li, Ke; Ma, Chao
- Physical Review Fluids, Vol. 4, Issue 10
A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows
journal, December 2017
- Milani, Pedro M.; Ling, Julia; Saez-Mischlich, Gonzalo
- Journal of Turbomachinery, Vol. 140, Issue 2
Kernel-Smoothed Proper Orthogonal Decomposition–Based Emulation for Spatiotemporally Evolving Flow Dynamics Prediction
journal, December 2019
- Chang, Yu-Hung; Zhang, Liwei; Wang, Xingjian
- AIAA Journal, Vol. 57, Issue 12
Future Directions in Computational Fluid Dynamics
conference, June 2017
- Witherden, Freddie D.; Jameson, Antony
- 23rd AIAA Computational Fluid Dynamics Conference
Towards Integrated Field Inversion and Machine Learning With Embedded Neural Networks for RANS Modeling
conference, January 2019
- Holland, Jonathan R.; Baeder, James D.; Duraisamy, Karthik
- AIAA Scitech 2019 Forum
A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows
conference, August 2017
- Milani, Pedro M.; Ling, Julia; Saez-Mischlich, Gonzalo
- ASME Turbo Expo 2017: Turbomachinery Technical Conference and Exposition, Volume 5A: Heat Transfer
Deep Learning of Vortex Induced Vibrations
text, January 2018
- Raissi, Maziar; Wang, Zhicheng; Triantafyllou, Michael
- engrXiv
A neural network approach for the blind deconvolution of turbulent flows
text, January 2017
- Maulik, Romit; San, Omer
- arXiv
Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
text, January 2018
- Wu, Jin-Long; Xiao, Heng; Paterson, Eric
- arXiv
Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning
text, January 2018
- Wang, Jian-Xun; Huang, Junji; Duan, Lian
- arXiv
Sub-grid scale model classification and blending through deep learning
text, January 2018
- Maulik, Romit; San, Omer; Jacob, Jamey D.
- arXiv
Construction of Reduced Order Models for Fluid Flows Using Deep Feedforward Neural Networks
text, January 2019
- Lui, Hugo F. S.; Wolf, William R.
- arXiv
Modal Analysis of Fluid Flows: Applications and Outlook
preprint, January 2019
- Taira, Kunihiko; Hemati, Maziar S.; Brunton, Steven L.
- arXiv
Hydrodynamic object identification with artificial neural models
text, January 2019
- Lakkam, Sreetej; T., Balamurali B.; Bouffanais, Roland
- arXiv