Predictive Data-Driven Model Based on Generative Adversarial Network for Premixed Turbulence-Combustion Regimes

References

• Abadi, M., A. Agarwal, P. Barham, E. Brevdo, Z. Chen, and C. Citro, others. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467.
   Google Scholar
• Aspden, A., M. Day, and J. Bell. 2011. Turbulence–flame interactions in lean premixed hydrogen: Transition to the distributed burning regime. J Fluid Mech 680:287–320. doi:10.1017/jfm.2011.164.
   Web of Science ®Google Scholar
• Batchelor, G. K. 1952. The effect of homogeneous turbulence on material lines and surfaces. Proc R Soc Lond A Math Phys Sci 213 (1114):349–66.
   Google Scholar
• Bilger, R. 2004. Some aspects of scalar dissipation. Flow, Turbulence and Combustion 72 (2):93–114. doi:10.1023/B:APPL.0000044404.24369.f1.
   Web of Science ®Google Scholar
• Bobbitt, B., S. Lapointe, and G. Blanquart. 2016. Vorticity transformation in high karlovitz number premixed flames. Physics of Fluids 28 (1):15101. doi:10.1063/1.4937947.
   Web of Science ®Google Scholar
• Bode, M., M. Gauding, Z. Lian, D. Denker, M. Davidovic, K. Kleinheinz, H. Pitsch, and H. Pitsch. 2021. Using physics-informed enhanced super-resolution generative adversarial networks for subfilter modeling in turbulent reactive flows. Proceedings of the Combustion Institute 38 (2):2617–25. doi:10.1016/j.proci.2020.06.022.
   Web of Science ®Google Scholar
• Bray, K., P. A. Libby, G. Masuya, and J. Moss. 1981. Turbulence production in premixed turbulent flames. Combustion Science and Technology 25 (3–4):127–40. doi:10.1080/00102208108547512.
   Web of Science ®Google Scholar
• Bray, K., P. A. Libby, and J. Moss. 1985. Unified modeling approach for premixed turbulent combustion—part i: General formulation. Combustion and Flame 61 (1):87–102. doi:10.1016/0010-2180(85)90075-6.
   Web of Science ®Google Scholar
• Brenner, M., J. Eldredge, and J. Freund. 2019. Perspective on machine learning for advancing fluid mechanics. Physical Review Fluids 4 (10):100501. doi:10.1103/PhysRevFluids.4.100501.
   Web of Science ®Google Scholar
• Cao, Z.-M., K. Nishino, S. Mizuno, and K. Torii. 2000. Piv measurement of internal structure of diesel fuel spray. Exp. Fluids 29 (1):S211–S219. doi:10.1007/s003480070023.
   Web of Science ®Google Scholar
• Davis, S. G., A. V. Joshi, H. Wang, and F. Egolfopoulos. 2005. An optimized kinetic model of h2/co combustion. Proceedings of the Combustion Institute 30 (1):1283–92. doi:10.1016/j.proci.2004.08.252.
   Web of Science ®Google Scholar
• Deng, Z., C. He, Y. Liu, and K. C. Kim. 2019. Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework. Physics of Fluids 31 (12):125111.
   Web of Science ®Google Scholar
• Desjardins, O., G. Blanquart, G. Balarac, and H. Pitsch. 2008. High order conservative finite difference scheme for variable density low mach number turbulent flows. J. Comput. Phys. 227 (15):7125–59. doi:10.1016/j.jcp.2008.03.027.
   Web of Science ®Google Scholar
• Driscoll, J. F., and A. Gulati. 1988. Measurement of various terms in the turbulent kinetic energy balance within a flame and comparison with theory. Combustion and Flame 72 (2):131–52. doi:10.1016/0010-2180(88)90114-9.
   Web of Science ®Google Scholar
• European Union. 2021. A European green deal. Accessed November 01, 2021. from https://ec.europa.eu/info/strategy/priorities-2019-2024/european-green-deal
   Google Scholar
• Flemming, F., A. Sadiki, and J. Janicka. 2005. Les using artificial neural networks for chemistry representation. Progress in Computational Fluid Dynamics, an International Journal 5 (7):375–85. doi:10.1504/PCFD.2005.007424.
   Google Scholar
• Fukami, K., K. Fukagata, and K. Taira. 2019. Super-resolution reconstruction of turbulent flows with machine learning. J Fluid Mech 870:106–20. doi:10.1017/jfm.2019.238.
   Web of Science ®Google Scholar
• Fureby, C. 2005. A fractal flame-wrinkling large eddy simulation model for premixed turbu- lent combustion. Proceedings of the Combustion Institute 30 (1):593–601. doi:10.1016/j.proci.2004.08.068.
   Web of Science ®Google Scholar
• Germano, M., U. Piomelli, P. Moin, and W. H. Cabot. 1991. A dynamic subgrid-scale eddy viscosity model. Physics of Fluids A: Fluid Dynamics 3 (7):1760–65. doi:10.1063/1.857955.
   Web of Science ®Google Scholar
• Géron, A. 2019. Hands-on machine learning with scikit-learn, keras, and tensorflow: Concepts, tools, and techniques to build intelligent systems. Sebastopol, CA, USA: O’Reilly Media.
   Google Scholar
• Grenga, T., J. F. MacArt, and M. E. Mueller. 2018. Dynamic mode decomposition of a direct numerical simulation of a turbulent premixed planar jet flame: Convergence of the modes. Combust. Theory Modelling 22 (4):795–811. doi:10.1080/13647830.2018.1457799.
   Web of Science ®Google Scholar
• Grenga, T., and M. Mueller. 2020. Dynamic mode decomposition: A Tool to Extract Structures Hidden in Massive Datasets. In Pitsch, H., and Attili, A., (eds) Data Analysis for Direct Numerical Simulations of Turbulent Combustion. Springer, Cham. https://doi.org/10.1007/978-3-030-44718-2_8
   Google Scholar
• Hamlington, P. E., A. Y. Poludnenko, and E. S. Oran. 2011. Interactions between turbulence and flames in premixed reacting flows. Physics of Fluids 23 (12):125111. doi:10.1063/1.3671736.
   Web of Science ®Google Scholar
• He, K., X. Zhang, S. Ren, and J. Sun (2016). Deep residual learning for image recognition. In Proceedings of the ieee conference on computer vision and pattern recognition Las Vegas, NV, USA 26/06-01/07/2016 (pp. 770–78).
   Google Scholar
• Ihme, M. 2010 01 Topological optimization of artificial neural networks using a pattern search method. In E, Chabot., and H. D, Arras. (eds) Neural Computation and Particle Accelerators: Research, Technology and Applications. 323–44. Nova science.
   Google Scholar
• Ihme, M., A. L. Marsden, and H. Pitsch. 2008. Generation of optimal artificial neural networks using a pattern search algorithm: Application to approximation of chemical systems. Neural Comput 20 (2):573–601. doi:10.1162/neco.2007.08-06-316.
   PubMed Web of Science ®Google Scholar
• Ihme, M., H. Pitsch, and D. Bodony. 2009. Radiation of noise in turbulent non-premixed flames. Proceedings of the Combustion Institute 32 (1):1545–53. doi:10.1016/j.proci.2008.06.137.
   Google Scholar
• Ihme, M., C. Schmitt, and H. Pitsch. 2009. Optimal artificial neural networks and tabulation methods for chemistry representation in les of a bluff-body swirl-stabilized flame. Proceedings of the Combustion Institute 32 (1):1527–35. doi:10.1016/j.proci.2008.06.100.
   Google Scholar
• Jolicoeur-Martineau, A. 2018. The relativistic discriminator: A key element missing from standard gan. arXiv preprint arXiv:1807.00734.
   Google Scholar
• Kim, H., J. Kim, S. Won, and C. Lee. 2021. Unsupervised deep learning for super-resolution reconstruction of turbulence. J Fluid Mech 910. doi: 10.1017/jfm.2020.1028.
   Web of Science ®Google Scholar
• Kolla, H., E. Hawkes, A. Kerstein, N. Swaminathan, and J. Chen. 2014. On velocity and reactive scalar spectra in turbulent premixed flames. J Fluid Mech 754:456–87. doi:10.1017/jfm.2014.392.
   Web of Science ®Google Scholar
• Kong, C., J.-T. Chang, Y.-F. Li, and R.-Y. Chen. 2020. Deep learning methods for super- resolution reconstruction of temperature fields in a supersonic combustor. AIP Adv. 10 (11):115021. doi:10.1063/5.0030040.
   Web of Science ®Google Scholar
• Lapeyre, C. J., A. Misdariis, N. Cazard, D. Veynante, and T. Poinsot. 2019. Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates. Combustion and Flame 203:255–64. doi:10.1016/j.combustflame.2019.02.019.
   Web of Science ®Google Scholar
• Ledig, C., L. Theis, F. Huszár, J. Caballero, A. Cunningham, and A. Acosta, … others (2017). Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the ieee conference on computer vision and pattern recognition Honolulu, HI, USA 21-26/07/2017 (pp. 4681–90).
   Google Scholar
• Leith, C. 1990. Stochastic backscatter in a subgrid-scale model: Plane shear mixing layer. Physics of Fluids A: Fluid Dynamics 2 (3):297–99. doi:10.1063/1.857779.
   Web of Science ®Google Scholar
• Li, Y., E. Perlman, M. Wan, Y. Yang, C. Meneveau, R. Burns, G. Eyink, A. Szalay, and G. Eyink. 2008. A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence. J. Turbulence 9 (9):N31. doi:10.1080/14685240802376389.
   Google Scholar
• Libby, P. A., and K. Bray. 1981. Countergradient diffusion in premixed turbulent flames. AIAA J. 19 (2):205–13. doi:10.2514/3.50941.
   Google Scholar
• Lilly, D. K. 1992. A proposed modification of the germano subgrid-scale closure method. Physics of Fluids A: Fluid Dynamics 4 (3):633–35. doi:10.1063/1.858280.
   Web of Science ®Google Scholar
• Lipatnikov, A., and J. Chomiak. 2010. Effects of premixed flames on turbulence and turbulent scalar transport. Progress in Energy and Combustion Science 36 (1):1–102. doi:10.1016/j.pecs.2009.07.001.
   Web of Science ®Google Scholar
• Liu, B., J. Tang, H. Huang, and X.-Y. Lu. 2020. Deep learning methods for super-resolution reconstruction of turbulent flows. Physics of Fluids 32 (2):25105. doi:10.1063/1.5140772.
   Web of Science ®Google Scholar
• Lumley, J. L., and G. R. Newman. 1977. The return to isotropy of homogeneous turbulence. J Fluid Mech 82 (1):161–78. doi:10.1017/S0022112077000585.
   Web of Science ®Google Scholar
• Maas, A. L., A. Y. Hannun, and A. Y. Ng (2013). Rectifier nonlinearities improve neural network acoustic models (Tech. Rep.). Computer Science Department, Stanford University, CA 94305 USA.
   Google Scholar
• MacArt, J. F., T. Grenga, and M. E. Mueller. 2018. Effects of combustion heat release on velocity and scalar statistics in turbulent premixed jet flames at low and high karlovitz numbers. Combustion and Flame 191:468–85. doi:10.1016/j.combustflame.2018.01.022.
   Web of Science ®Google Scholar
• MacArt, J. F., T. Grenga, and M. E. Mueller. 2019. Evolution of flame-conditioned velocity statistics in turbulent premixed jet flames at low and high karlovitz numbers. Proceedings of the Combustion Institute 37 (2):2503–10. doi:10.1016/j.proci.2018.08.030.
   Web of Science ®Google Scholar
• MacArt, J. F., and M. E. Mueller. 2016. Semi-implicit iterative methods for low mach number turbulent reacting flows: Operator splitting versus approximate factorization. J. Comput. Phys. 326:569–95. doi:10.1016/j.jcp.2016.09.016.
   Web of Science ®Google Scholar
• Mason, P. J., and D. J. Thomson. 1992. Stochastic backscatter in large-eddy simulations of boundary layers. J Fluid Mech 242:51–78. doi:10.1017/S0022112092002271.
   Web of Science ®Google Scholar
• Moin, P., K. Squires, W. Cabot, and S. Lee. 1991. A dynamic subgrid-scale model for compressible turbulence and scalar transport. Physics of Fluids A: Fluid Dynamics 3 (11):2746–57. doi:10.1063/1.858164.
   Web of Science ®Google Scholar
• Nations U. 2021. United nations sustainable development goals. Accessed November 01, 2021. https://www.un.org/sustainabledevelopment/sustainable-development-goals
   Google Scholar
• Nikolaou, Z. M., C. Chrysostomou, L. Vervisch, and S. Cant. 2018. Modelling turbulent premixed flames using convolutional neural networks: Application to sub-grid scale variance and filtered reaction rate. arXiv preprint arXiv:1810.07944.
   Google Scholar
• Nikolaou, Z., C. Chrysostomou, L. Vervisch, and S. Cant. 2019. Progress variable variance and filtered rate modelling using convolutional neural networks and flamelet methods. Flow, Turbulence and Combustion 103 (2):485–501. doi:10.1007/s10494-019-00028-w.
   Web of Science ®Google Scholar
• Nista, L., C. Schumann, T. Grenga, A. N. Karimi, G. Scialabba, M. Bode, and H. Pitsch (2021). Turbulent mixing predictive model with physics-based generative adversarial network. In 10th european combustion meeting Naples, Italy 14-15/04/2021 (pp. 460–65).
   Google Scholar
• O’Brien, J., C. A. Towery, P. E. Hamlington, M. Ihme, A. Y. Poludnenko, and J. Urzay. 2017. The cross-scale physical-space transfer of kinetic energy in turbulent premixed flames. Proceedings of the Combustion Institute 36 (2):1967–75. doi:10.1016/j.proci.2016.05.005.
   Web of Science ®Google Scholar
• O’Brien, J., J. Urzay, M. Ihme, P. Moin, and A. Saghafian. 2014. Subgrid-scale backscatter in reacting and inert supersonic hydrogen–air turbulent mixing layers. J Fluid Mech 743:554–84. doi:10.1017/jfm.2014.62.
   Web of Science ®Google Scholar
• Pant, P., and A. B. Farimani. 2020. Deep learning for efficient reconstruction of high-resolution turbulent dns data. arXiv preprint arXiv:2010.11348.
   Google Scholar
• Perlman, E., R. Burns, Y. Li, and C. Meneveau (2007). Data exploration of turbulence simulations using a database cluster. In Proceedings of the 2007 acm/ieee conference on supercomputing Reno, NV (USA) 10-16/11/2007 (pp. 1–11).
   Google Scholar
• Pope, S. B. 2000. Turbulent flows. Cambridge UK: Cambridge university press.
   Google Scholar
• Richardson, L. F. 2007. Weather prediction by numerical process. Cambridge UK: Cambridge university press.
   Google Scholar
• Rogerson, J., N. Swaminathan, M. Tanahashi, and N. Shiwaku (2007). Analysis of progress variable variance equations using dns data. In Proceedings of the european combustion meeting Chania, Greece 11 - 13 April 2007.
   Google Scholar
• Rotunno, R., Y. Chen, W. Wang, C. Davis, J. Dudhia, and G. Holland. 2009. Large-eddy simulation of an idealized tropical cyclone. Bull. Am. Meteorol. Soc. 90 (12):1783–88. doi:10.1175/2009BAMS2884.1.
   Web of Science ®Google Scholar
• Schumann, U. 1995. Stochastic backscatter of turbulence energy and scalar variance by random subgrid-scale fluxes. Proc R Soc Lond A Math Phys Sci 451 (1941):293–318.
   Google Scholar
• Seltz, A., P. Domingo, L. Vervisch, and Z. M. Nikolaou. 2019. Direct mapping from les resolved scales to filtered-flame generated manifolds using convolutional neural networks. Combustion and Flame 210:71–82. doi:10.1016/j.combustflame.2019.08.014.
   Web of Science ®Google Scholar
• Sergeev, A., and M. Del Balso 2018. Horovod: Fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799.
   Google Scholar
• Steinberg, A. M., J. F. Driscoll, and N. Swaminathan. 2012. Statistics and dynamics of turbulence–flame alignment in premixed combustion. Combustion and Flame 159 (8):2576–88. doi:10.1016/j.combustflame.2011.12.001.
   Web of Science ®Google Scholar
• Subramaniam, A., M. L. Wong, R. D. Borker, S. Nimmagadda, and S. K. Lele. 2020. Turbulence enrichment using physics-informed generative adversarial networks. arXiv preprint arXiv:2003.1907.
   Google Scholar
• Veynante, D., A. Trouvé, K. Bray, and T. Mantel. 1997. Gradient and counter-gradient scalar transport in turbulent premixed flames. J Fluid Mech 332:263–93. doi:10.1017/S0022112096004065.
   Web of Science ®Google Scholar
• Wang, H., E. R. Hawkes, and J. H. Chen. 2016. Turbulence-flame interactions in dns of a laboratory high karlovitz premixed turbulent jet flame. Physics of Fluids 28 (9):95107. doi:10.1063/1.4962501.
   Web of Science ®Google Scholar
• Wang, X., K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, and C. Change Loy (2018). Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the european conference on computer vision (eccv) workshops Munich (Germany) 08-14/09/2018.
   Google Scholar
• Zhang, S., and C. J. Rutland. 1995. Premixed flame effects on turbulence and pressure-related terms. Combustion and Flame 102 (4):447–61. doi:10.1016/0010-2180(95)00036-6.
   Web of Science ®Google Scholar