×

Applying Bayesian optimization with Gaussian process regression to computational fluid dynamics problems. (English) Zbl 07524785

Summary: Bayesian optimization (BO) based on Gaussian process regression (GPR) is applied to different CFD (computational fluid dynamics) problems which can be of practical relevance. The problems are i) shape optimization in a lid-driven cavity to minimize or maximize the energy dissipation, ii) shape optimization of the wall of a channel flow in order to obtain a desired pressure-gradient distribution along the edge of the turbulent boundary layer formed on the other wall, and finally, iii) optimization of the controlling parameters of a spoiler-ice model to attain the aerodynamic characteristics of the airfoil with an actual surface ice. The diversity of the optimization problems, independence of the optimization approach from any adjoint information, the ease of employing different CFD solvers in the optimization loop, and more importantly, the relatively small number of the required flow simulations reveal the flexibility, efficiency, and versatility of the BO-GPR approach in CFD applications. It is shown that to ensure finding the global optimum of the design parameters of the size up to 8, less than 90 executions of the CFD solvers are needed. Furthermore, it is observed that the number of flow simulations does not significantly increase with the number of design parameters. The associated computational cost of these simulations can be affordable for many optimization cases with practical relevance.

MSC:

90Cxx Mathematical programming
76Mxx Basic methods in fluid mechanics
76Dxx Incompressible viscous fluids

Software:

GPy; GPyOpt; ANSYS; Nek5000; Gmsh; EGO
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] ANSYS Inc., ICEM CFD User Manual, 2011, Release 14.0.
[2] Back, T., Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms (1996), Oxford University Press · Zbl 0877.68060
[3] Berggren, M., Numerical solution of a flow-control problem: vorticity reduction by dynamic boundary action, SIAM J. Sci. Comput., 19, 3, 829-860 (May 1998) · Zbl 0946.76016
[4] (Bijl, H.; Lucor, D.; Mishra, S.; Schwab, C., Uncertainty Quantification in Computational Fluid Dynamics (2013), Springer International Publishing) · Zbl 1276.76005
[5] Bobke, A.; Vinuesa, R.; Örlü, R.; Schlatter, P., History effects and near equilibrium in adverse-pressure-gradient turbulent boundary layers, J. Fluid Mech., 820, 667-692 (May 2017) · Zbl 1383.76220
[6] Boppana, V. B.L.; Gajjar, J. S.B., Global flow instability in a lid-driven cavity, Int. J. Numer. Methods Fluids, 62, 8, 827-853 (2010) · Zbl 1423.76135
[7] Box, G.; Draper, N., Empirical Model-Building and Response Surfaces, Wiley Series in Probability and Statistics (1987), Wiley · Zbl 0614.62104
[8] Bragg, M.; Broeren, A.; Blumenthal, L., Iced-airfoil aerodynamics, Prog. Aerosp. Sci., 41, 5, 323-362 (July 2005)
[9] Bull, A. D., Convergence rates of efficient global optimization algorithms, J. Mach. Learn. Res., 12, null, 2879-2904 (Nov. 2011) · Zbl 1280.90094
[10] Cabral, B.; Leedom, L. C., Imaging vector fields using line integral convolution, (Proceedings of the 20th Annual Conference on Computer Graphics and Interactive Techniques. Proceedings of the 20th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’93, New York, NY, USA (1993), Association for Computing Machinery), 263-270
[11] Chung, H.-S.; Alonso, J., Using gradients to construct cokriging approximation models for high-dimensional design optimization problems (2002)
[12] Clauser, F. H., Turbulent boundary layers in adverse pressure gradients, J. Aeronaut. Sci., 21, 2, 91-108 (Feb. 1954)
[13] Clauser, F. H., The turbulent boundary layer, (Advances in Applied Mechanics (1956), Elsevier), 1-51
[14] Deck, S.; Gand, F.; Brunet, V.; Khelil, S. B., High-fidelity simulations of unsteady civil aircraft aerodynamics: stakes and perspectives. Application of zonal detached eddy simulation, Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci., 372, 2022, Article 20130325 pp. (Aug. 2014)
[15] DeGennaro, A. M.; Rowley, C. W.; Martinelli, L., Uncertainty quantification for airfoil icing using polynomial chaos expansions, J. Aircr., 52, 5, 1404-1411 (2015)
[16] Deville, M. O.; Fischer, P. F.; Mund, E. H., High-Order Methods for Incompressible Fluid Flow, Cambridge Monographs on Applied and Computational Mathematics (2002), Cambridge University Press · Zbl 1007.76001
[17] Dilgen, C. B.; Dilgen, S. B.; Fuhrman, D. R.; Sigmund, O.; Lazarov, B. S., Topology optimization of turbulent flows, Comput. Methods Appl. Mech. Eng., 331, 363-393 (2018) · Zbl 1439.74265
[18] Fan, Y.; Li, W.; Atzori, M.; Pozuelo, R.; Schlatter, P.; Vinuesa, R., Decomposition of the mean friction drag in adverse-pressure-gradient turbulent boundary layers, Phys. Rev. Fluids, 5, Article 114608 pp. (Nov 2020)
[19] Fischer, P. F.; Lottes, J. W.; Kerkemeier, S. G., NEK5000: open source spectral element CFD solver (2008), Available at
[20] Forrester, A. I.J.; Sóbester, A.; Keane, A. J., Engineering Design via Surrogate Modelling (July 2008), Wiley
[21] Frazier, P., A tutorial on Bayesian optimization (2018), ArXiv
[22] Gantasala, S.; Tabatabaei, N.; Cervantes, M.; Aidanpää, J.-O., Numerical investigation of the aeroelastic behavior of a wind turbine with iced blades, Energies, 12, 12, 2422 (Jun 2019)
[23] Geuzaine, C.; Remacle, J.-F., Gmsh: a 3-d finite element mesh generator with built-in pre- and post-processing facilities, Int. J. Numer. Methods Eng., 79, 11, 1309-1331 (2009) · Zbl 1176.74181
[24] Goldberg, P. W.; Williams, C. K.I.; Bishop, C. M., Regression with input-dependent noise: a Gaussian process treatment, (Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems 10. Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems 10, NIPS ’97, Cambridge, MA, USA (1998), MIT Press), 493-499
[25] GPy, GPy: a gaussian process framework in Python (since 2012)
[26] Gramacy, R.; Lee, H., Optimization Under Unknown Constraints (2011), Oxford University Press, chapter 8
[27] Gramacy, R. B., Surrogates: Gaussian Process Modeling, Design and Optimization for the Applied Sciences (2020), Chapman Hall/CRC: Chapman Hall/CRC Boca Raton, Florida
[28] Gunzburger, M., Adjoint equation-based methods for control problems in incompressible, viscous flows, Flow Turbul. Combust., 65, 3/4, 249-272 (2000) · Zbl 0996.76024
[29] Hinze, M.; Walther, A.; Sternberg, J., An optimal memory-reduced procedure for calculating adjoints of the instationary Navier-Stokes equations, Optim. Control Appl. Methods, 27, 1, 19-40 (2006)
[30] Jalali, H.; Van Nieuwenhuyse, I.; Picheny, V., Comparison of Kriging-based algorithms for simulation optimization with heterogeneous noise, Eur. J. Oper. Res., 261, 1, 279-301 (2017) · Zbl 1403.90553
[31] Jones, D. R.; Schonlau, M.; Welch, W. J., Efficient global optimization of expensive black-box functions, J. Glob. Optim., 13, 4, 455-492 (1998) · Zbl 0917.90270
[32] Kerswell, R. R.; Pringle, C. C.T.; Willis, A. P., An optimization approach for analysing nonlinear stability with transition to turbulence in fluids as an exemplar, Rep. Prog. Phys., 77, 8, Article 085901 pp. (Aug 2014)
[33] Larson, J.; Menickelly, M.; Wild, S. M., Derivative-free optimization methods, Acta Numer., 28, 287-404 (2019) · Zbl 1461.65169
[34] Laurenceau, J.; Meaux, M.; Montagnac, M.; Sagaut, P., Comparison of gradient-based and gradient-enhanced response-surface-based optimizers, AIAA J., 48, 5, 981-994 (2010)
[35] Laurent, L.; Riche, R. L.; Soulier, B.; Boucard, P.-A., An overview of gradient-enhanced metamodels with applications, Arch. Comput. Methods Eng., 26, 1, 61-106 (July 2017)
[36] Letham, B.; Karrer, B.; Ottoni, G.; Bakshy, E., Constrained Bayesian optimization with noisy experiments, Bayesian Anal., 14, 2, 495-519 (2019) · Zbl 1416.62156
[37] Lindgren, B.; Johansson, A. V., Evaluation of the flow quality in the MTL wind-tunnel (2002), Dept. of Mechanics, KTH: Dept. of Mechanics, KTH Sweden, Report TRITA-MEK 2002:13
[38] Mahfoze, O. A.; Moody, A.; Wynn, A.; Whalley, R. D.; Laizet, S., Reducing the skin-friction drag of a turbulent boundary-layer flow with low-amplitude wall-normal blowing within a Bayesian optimization framework, Phys. Rev. Fluids, 4, Article 094601 pp. (Sep 2019)
[39] Menter, F.; Kuntz, M.; Langtry, R., Ten years of industrial experience with the SST turbulence model, Heat Mass Transf., 4, Article 01 pp. (2003)
[40] Močkus, J., On Bayesian methods for seeking the extremum, (Marchuk, G. I., Optimization Techniques IFIP Technical Conference. Optimization Techniques IFIP Technical Conference, Novosibirsk, July 1-7, 1974 (1975), Springer: Springer Berlin, Heidelberg), 400-404 · Zbl 0311.90042
[41] Mohammadi, B.; Pironneau, O., Shape optimization in fluid mechanics, Annu. Rev. Fluid Mech., 36, 1, 255-279 (2004) · Zbl 1076.76020
[42] Moriconi, R.; Deisenroth, M. P.; Kumar, K. S.S., High-dimensional Bayesian optimization using low-dimensional feature spaces, Mach. Learn., 109, 9-10, 1925-1943 (Sept. 2020) · Zbl 1525.68121
[43] Morita, Y., Robust optimisation of the pressure-gradient distribution in turbulent boundary layers (2020), KTH Royal Institute of Technology: KTH Royal Institute of Technology Sweden, Master’s thesis
[44] Nabae, Y.; Kawai, K.; Fukagata, K., Bayesian optimization of traveling wave-like wall deformation for turbulent drag reduction, (The Ninth JSME-KSME Thermal and Fluids Engineering Conference. The Ninth JSME-KSME Thermal and Fluids Engineering Conference, TFEC9 (Oct. 2017)), Paper TFEC9-1045
[45] Nakazawa, T., Increasing the critical Reynolds number by maximizing energy dissipation problem, (Segalini, A., Proceedings of the 5th International Conference on Jets, Wakes and Separated Flows. Proceedings of the 5th International Conference on Jets, Wakes and Separated Flows, ICJWSF2015 (2016), Springer International Publishing: Springer International Publishing Cham), 613-620
[46] Nocedal, J.; Wright, S., Numerical Optimization (2006), Springer: Springer New York · Zbl 1104.65059
[47] Offermans, N.; Peplinski, A.; Marin, O.; Schlatter, P., Adaptive mesh refinement for steady flows in Nek5000, Comput. Fluids, 197, Article 104352 pp. (2020) · Zbl 1519.76234
[48] Oliver, T. A.; Malaya, N.; Ulerich, R.; Moser, R. D., Estimating uncertainties in statistics computed from direct numerical simulation, Phys. Fluids, 26, 3, Article 035101 pp. (2014)
[49] Pang, G.; Perdikaris, P.; Cai, W.; Karniadakis, G. E., Discovering variable fractional orders of advection-dispersion equations from field data using multi-fidelity bayesian optimization, J. Comput. Phys., 348, 694-714 (2017) · Zbl 1419.62499
[50] Papadakis, M.; Laflin, B. G., Aerodynamic performance of a tail section with simulated ice shapes and roughness (2001), AIAA, chapter 539
[51] Papadakis, M.; Alansatan, S.; Seltmann, M., Experimental study of simulated ice shapes on a NACA 0011 airfoil, 1-29 (1999), AIAA
[52] Papadakis, M.; Alansatan, S.; Wong, S.-C., Aerodynamic characteristics of a symmetric NACA section with simulated ice shapes, 1-36 (2000), AIAA
[53] Papadakis, M.; Laflin, B. G.; Youssef, G.; Ratvasky, T., Aerodynamic scaling experiments with simulated ice accretions, 1-42 (2001), AIAA
[54] Papadakis, M.; Yeong, H.; Chandrasekharan, R.; Hinson, M.; Ratvasky, T.; Giriunas, J., Experimental investigation of simulated ice accretions on a full-scale T-tail (2001), AIAA, chapter 90
[55] Patankar, S. V., Numerical Heat Transfer and Fluid Flow, Series on Computational Methods in Mechanics and Thermal Science (1980), Hemisphere Publishing Corporation (CRC Press, Taylor & Francis Group) · Zbl 0521.76003
[56] Peherstorfer, B.; Willcox, K.; Gunzburger, M., Survey of multifidelity methods in uncertainty propagation, inference, and optimization, SIAM Rev., 60, 3, 550-591 (2018) · Zbl 1458.65003
[57] Rasmussen, C. E.; Williams, C. K.I., Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) (2005), The MIT Press
[58] Rezaeiravesh, S.; Liefvendahl, M., Effect of grid resolution on large eddy simulation of wall-bounded turbulence, Phys. Fluids, 30, 5, Article 055106 pp. (May 2018)
[59] Rezaeiravesh, S.; Vinuesa, R.; Schlatter, P., An uncertainty-quantification framework for assessing accuracy, sensitivity, and robustness in computational fluid dynamics (2020)
[60] Rezaeiravesh, S.; Vinuesa, R.; Schlatter, P., Towards multifidelity models with calibration for turbulent flows, (14th WCCM-ECCOMAS Congress (2021), CIMNE)
[61] Rezaeiravesh, S.; Vinuesa, R.; Schlatter, P., On numerical uncertainties in scale-resolving simulations of canonical wall turbulence, Comput. Fluids, 227, Article 105024 pp. (2021) · Zbl 1521.76248
[62] Roman, I.; Santana, R.; Mendiburu, A.; Lozano, J. A., An experimental study in adaptive kernel selection for bayesian optimization, IEEE Access, 7, 184294-184302 (2019)
[63] Sagaut, P.; Deck, S.; Terracol, M., Multiscale and Multiresolution Approaches in Turbulence: LES, DES and Hybrid RANS/LES Methods: Applications and Guidelines (2013), Imperial College Press · Zbl 1275.76004
[64] Sanmiguel Vila, C.; Vinuesa, R.; Discetti, S.; Ianiro, A.; Schlatter, P.; Örlü, R., Experimental realisation of near-equilibrium adverse-pressure-gradient turbulent boundary layers, Exp. Therm. Fluid Sci., 112, Article 109975 pp. (Apr. 2020)
[65] Schlatter, P.; Örlü, R., Assessment of direct numerical simulation data of turbulent boundary layers, J. Fluid Mech., 659, 116-126 (July 2010) · Zbl 1205.76139
[66] Scotto Di Perrotolo, A., A theoretical framework for Bayesian optimization convergence (2018), KTH, Optimization and Systems Theory, Master’s thesis
[67] Shahriari, B.; Swersky, K.; Wang, Z.; Adams, R. P.; de Freitas, N., Taking the human out of the loop: a review of Bayesian optimization, Proc. IEEE, 104, 1, 148-175 (Jan 2016)
[68] Slotnick, J. P.; Khodadoust, A.; Alonso, J. J.; Darmofal, D. L.; Gropp, W. D.; Lurie, E. A.; Mavriplis, D. J., CFD vision 2030 study: A path to revolutionary computational aerosciences (2014)
[69] Smith, R. C., Uncertainty Quantification: Theory, Implementation, and Applications (2013), Society for Industrial and Applied Mathematics: Society for Industrial and Applied Mathematics Philadelphia, PA, USA, 9781611973211
[70] Tabatabaei, N.; Cervantes, M.; Trivedi, C.; Aidanpää, J.-O., Numerical study of aerodynamic characteristics of a symmetric NACA section with simulated ice shapes, J. Phys. Conf. Ser., 753, Article 022055 pp. (Sep 2016)
[71] Tabatabaei, N.; Cervantes, M.; Trivedi, C., Time-dependent effects of glaze ice on the aerodynamic characteristics of an airfoil, Int. J. Rotating Mach., 2018 (2018)
[72] Tabatabaei, N.; Raisee, M.; Cervantes, M. J., Uncertainty quantification of aerodynamic icing losses in wind turbine with polynomial chaos expansion, J. Energy Resour. Technol., 141, 5, Article 051210 pp. (04 2019)
[73] Talnikar, C.; Blonigan, P.; Bodart, J.; Wang, Q., Parallel optimization for large eddy simulations, (Proceedings of the CTR Summer Program (2014)), 315
[74] Tanarro, Á.; Vinuesa, R.; Schlatter, P., Effect of adverse pressure gradients on turbulent wing boundary layers, J. Fluid Mech., 883, A8 (2020) · Zbl 1430.76282
[75] (2016), The GPyOpt authors. GPyOpt: a Bayesian Optimization framework in Python
[76] (Thévenin, D.; Janiga, G., Optimization and Computational Fluid Dynamics (2008), Springer: Springer Berlin, Heidelberg) · Zbl 1134.76003
[77] Vazquez, E.; Villemonteix, J.; Sidorkiewicz, M.; Walter, É., Global optimization based on noisy evaluations: an empirical study of two statistical approaches, J. Phys. Conf. Ser., 135, Article 012100 pp. (Nov 2008)
[78] Viana, F. A.C.; Simpson, T. W.; Balabanov, V.; Toropov, V., Special section on multidisciplinary design optimization: metamodeling in multidisciplinary design optimization: how far have we really come?, AIAA J., 52, 4, 670-690 (Apr. 2014)
[79] Vinuesa, R.; Rozier, P. H.; Schlatter, P.; Nagib, H. M., Experiments and computations of localized pressure gradients with different history effects, AIAA J., 52, 2, 368-384 (Feb. 2014)
[80] Vinuesa, R.; Bobke, A.; Örlü, R.; Schlatter, P., On determining characteristic length scales in pressure-gradient turbulent boundary layers, Phys. Fluids, 28, 5, Article 055101 pp. (May 2016)
[81] Vinuesa, R.; Örlü, R.; Vila, C. S.; Ianiro, A.; Discetti, S.; Schlatter, P., Revisiting history effects in adverse-pressure-gradient turbulent boundary layers, Flow Turbul. Combust., 99, 3-4, 565-587 (Aug. 2017)
[82] Weatheritt, J.; Sandberg, R., A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationship, J. Comput. Phys., 325, 22-37 (2016) · Zbl 1375.76141
[83] Weller, H. G.; Tabor, G.; Jasak, H.; Fureby, C., A tensorial approach to computational continuum mechanics using object-oriented techniques, Comput. Phys., 12, 6, 620-631 (1998)
[84] Wu, J.; Poloczek, M.; Wilson, A. G.; Frazier, P., Bayesian optimization with gradients, (Guyon, I.; Luxburg, U. V.; Bengio, S.; Wallach, H.; Fergus, R.; Vishwanathan, S.; Garnett, R., Advances in Neural Information Processing Systems, vol. 30 (2017), Curran Associates, Inc.), 5267-5278
[85] Xiao, H.; Cinnella, P., Quantification of model uncertainty in RANS simulations: a review, Prog. Aerosp. Sci., 108, 1-31 (2019)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.