Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty

Physics of Fluids

Volumn 27, Issue 8, 2015, Pages

  Ling, J ^a   Templeton, J ^a  

^a SANDIA NATIONAL LABORATORIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE BOOSTING; CLASSIFICATION (OF INFORMATION); DECISION TREES; FORECASTING; LARGE EDDY SIMULATION; NAVIER STOKES EQUATIONS; PREDICTIVE ANALYTICS; SUPPORT VECTOR MACHINES; UNCERTAINTY ANALYSIS; VISCOSITY;

BOUSSINESQ HYPOTHESIS; EDDY VISCOSITY MODEL; FLOW CONFIGURATIONS; MODEL APPLICATION; RELIABLE METHODS; REYNOLDS - AVERAGED NAVIER-STOKES; REYNOLDS AVERAGED NAVIER-STOKES MODELS; SELECTION TECHNIQUES;

LEARNING SYSTEMS;

EID: 84938629868     PISSN: 10706631     EISSN: 10897666     Source Type: Journal    
DOI: 10.1063/1.4927765     Document Type: Article

References (52)

1. T. Oliver and R. Moser, "Bayesian uncertainty quantification applied to RANS turbulence models," J. Phys.: Conf. Ser. 318, 042032 (2011).
2. S. Cheung, T. Oliver, E. Prudencio, S. Prudhomme, and R. Moser, "Bayesian uncertainty analysis with applications to turbulence modeling," Reliab. Eng. Syst. Saf. 96, 1137 (2011).
3. W. Edeling, P. Cinnella, R. Dwight, and H. Bijl, "Bayesian estimates of parameter variability in the k-∈ turbulence model," Comput. Phys. 258, 73-94 (2014).
4. S. Lefantzi, J. Ray, S. Arunajatesan, and L. Dechant, "Tuning a RANS k-e model for jet-in-crossflow simulations," Sandia Technical Report SAND2013-8158, 2013.
5. S. Pope, Turbulent Flows (Cambridge University Press, 2000).
6. G. Mompean, S. Gavrilakis, L. Machiels, and M. Deville, "On predicting the turbulence-induced secondary flows using nonlinear k - ∈ models," Phys. Fluids 8, 1856 (1996).
7. T. Craft, B. Launder, and K. Suga, "Development and application of a cubic eddy-viscosity model of turbulence," Int. J. Heat Fluid Flow 17, 108-115 (1996).
8. B. Launder, G. Reece, andW. Rodi, "Progress in the development of a Reynolds-stress turbulence closure," J. Fluid Mech. 68, 537-566 (1975).
9. W. Rodi, "A new algebraic relation for calculating the Reynolds stresses," Ges. Angew. Math. Mech. Workshop Paris, Fr. 56, 219 (1976).
10. S. Wallin and A. Johansson, "An explicit algebraic Reynolds stress model for incompressible and compressible turbulent flows," J. Fluid Mech. 403, 89-132 (2000).
11. T. Gatski and C. Speziale, "On explicit algebraic stress models for complex turbulent flows," J. Fluid Mech. 254, 59-78 (1993).
12. S. Nisizima and A. Yoshizawa, "Turbulent channel and Couette flows using an anisotropic k-∈ model," AIAA J. 25, 414-420 (1987).
13. C. Gorle, M. Emory, and G. Iaccarino, "RANS modeling of turbulent mixing for a jet in supersonic crossflow: Model evaluation and uncertainty quantification," in Proceedings of the Seventh International Symposium on Turbulence, Heat and Mass Transfer (ICHMT Digital Library Online, Palermo, Italy, 2012).
14. I. Bermejo-Moreno and D. Pullin, "On the non-local geometry of turbulence," J. Fluid Mech. 603, 101-135 (2008).
15. E. Dow and Q. Wang, "Quantification of structural uncertainties in the k - ∈ turbulence model," AIAA Paper 2011-1762, 2011.
16. E. Dow and Q.Wang, "Uncertainty quantification of structural uncertainties in RANS simulations of complex flows," AIAA Paper 2011-3865, 2011.
17. K. Duraisamy and P. Durbin, "Transition modeling using data driven approaches," in Proceedings of the Summer Program (Center for Turbulence Research, Stanford University, Stanford, CA, 2014).
18. K. Duraisamy, Z. Shang, and A. Singh, "New approaches in turbulence and transition modeling using data-driven techniques," AIAA Paper 2015-1284, 2015.
19. B. Tracey, K. Duraisamy, and J. Alonso, "Application of supervised learning to quantify uncertainties in turbulence and combustion modeling," AIAA Paper 2013-0259, 2013.
20. B. Tracey, K. Duraisamy, and J. Alonso, "Amachine learning strategy to assist turbulence model development," AIAA Paper 2015-1287, 2015.
21. R. Rossi and G. Iaccarino, "Numerical simulation of scalar mixing from a point source over a wavy wall," in Center for Turbulence Research Annual Research Briefs (Center for Turbulence Research, Stanford University, Stanford, CA, 2009).
22. R. Rossi, "A numerical study of algebraic flux models for heat and mass transport simulation in complex flows," Int. J. Heat Mass Transfer 53, 4511-4525 (2010).
23. R. Rossi, D. Philips, and G. Iaccarino, "A numerical study of scalar dispersion downstream of a wall-mounted cube using direct simulations and algebraic flux models," Int. J. Heat Fluid Flow 31, 805-819 (2010).
24. R. Rossi and G. Iaccarino, "Numerical analysis and modeling of a plume meandering in passive scalar dispersion downstream of a wall-mounted cube," Int. J. Heat Fluid Flow 43, 137-148 (2013).
25. J. Ling, R. Rossi, and J. Eaton, "Near wall modeling for trailing edge slot film cooling," J. Fluids Eng. 137, 021103 (2015).
26. J. Bodart, F. Coletti, I. Bermejo-Moreno, and J. Eaton, "High-fidelity simulation of a turbulent inclined jet in a crossflow," in Center for Turbulence Research Annual Research Briefs (Center for Turbulence Research, Stanford University, Stanford, CA, 2013).
27. J. Ling, K. Ryan, J. Bodart, and J. Eaton, "Analysis of turbulent scalar flux models for a discrete hole film cooling flow," in ASME Turbo Expo 2015 (ASME Turbo Expo, Montreal, Canada, 2015).
28. F. Coletti, M. Benson, J. Ling, C. Elkins, and J. Eaton, "Turbulent transport in an inclined jet in crossflow," Int. J. Heat Fluid Flow 43, 149-160 (2013).
29. R. Moser, J. Kim, and N. Mansour, "Direct numerical simulation of turbulent channel flow up to Ret = 590," Phys. Fluids 11, 943-945 (1999).
30. A. Pinelli, M. Uhlmann, A. Sekimoto, and G. Kawahara, "Reynolds number dependence of mean flow structure in square duct turbulence," J. Fluid Mech. 644, 107-122 (2010).
31. A. Ruiz, J. Oefelein, and G. Lacaze, "Flow topologies and turbulence scales in a jet-in-cross-flow," Phys. Fluids 27, 045101 (2015).
32. J. Ray, S. Lefantzi, S. Arunajatesan, and L. Dechant, "Bayesian calibration of a k - ∈ turbulence model for predictive jet-in-crossflow simulations," AIAA Paper 2014-2085, 2014.
33. S. Lefantzi, J. Ray, S. Arunajatesan, and L. Dechant, "Estimation of k-∈ parameters using surrogate models and jet-incrossflow data," Sandia Technical Report SAND2015-0707, 2015.
34. S. Domino, C. Moen, S. Burns, and G. Evans, "SIERRA/Fuego: A multi-mechanics fire environment simulation tool," AIAA Paper 2003-149, 2003.
35. S. Arunajatesan, M. Ross, M. Barone, and T. Garret, "Validation of an FSI modeling framework for internal captive carriage applications," AIAA Paper 2013-2157, 2013.
36. C. Cortes and V. Vapnik, "Support-vector networks," Mach. Learn. 20, 273-297 (1995).
37. R. Schapire and Y. Freund, Boosting: Foundations and Algorithms (MIT Press, Cambridge, MA, 2012).
38. L. Breiman, "Random forests," Mach. Learn. 45, 5-32 (2001).
39. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, "Scikit-learn: Machine learning in Python," J. Mach. Learn. Res. 12, 2825-2830 (2011).
40. L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees (Wadsworth, Belmont, CA, 1984).
41. V. Svetnik, A. Liaw, C. Tong, J. Culberson, R. Sheridan, and B. Feuston, "Random forest: A classification and regression tool for compound classification and QSAR modeling," J. Chem. Inf. Comput. Sci. 43, 1947-1958 (2003).
42. T. Joachims, "Making large scale SVM learning practical," Doctoral thesis, Universitat Dortmund, Dortmund, Germany, 1999, LS 08 Kunstliche Intelligenz.
43. N. Chawla, L. Hall, K. Bowyer, T. Moore, and W. Kegelmeyer, "Distributed pasting of small votes," in Multiple Classifier Systems (Springer, 2002), Vol. 2364, pp. 52-61.
44. N. Chawla, S. Eschrich, and L. Hall, "Creating ensembles of classifiers," in Proceedings of the IEEE International Conference on Data Mining (IEEE, San Jose, CA, 2001), pp. 580-581.
45. K. Choi and J. Lumley, "The return to isotropy of homogeneous turbulence," J. Fluid Mech. 436, 59-84 (2001).
46. D. Radenkovic, J. Burazer, and D. Novkovic, "Anisotropy analysis of turbulent swirl flow," FME Trans. 42, 19-25 (2014).
47. S. Pope, "A more general effective-viscosity hypothesis," J. Fluid Mech. 72, 331-340 (1975).
48. J.Weston, S. Mukherjee, O. Chapelle, M. Pontil, T. Poggio, andV.Vapnik, "Feature selection for SVMs," NIPS 12, 668-674 (2000).
49. K. Woods, K. Bowyer, and W. Kegelmeyer, "Combination of multiple classifiers using local accuracy estimates," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, San Francisco, CA, 1996), pp. 391-396.
50. R. Banfield, L. Hall, K. Bowyer, D. Bhadoria, W. Kegelmeyer, and S. Eschrich, "A comparison of ensemble creation techniques," Mult. Classifier Syst. 223-232 (2004).
51. P. Mahalanobis, "On the generalized distance in statistics," Proc. Natl. Inst. Sci. India 2, 49-55 (1936).
52. G. Hooker, "Diagnosing extrapolation: Tree-based density estimation," in Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, New York, NY, 2004), pp. 569-574.