Accurate Compression of Tabulated Chemistry Models with Partition of Unity Networks

References

• Abadi, M., A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, et al., 2016. TensorFlow: Large-scale machine learning on heterogeneous systems. https://arxiv.org/abs/1603.04467v2
   Google Scholar
• Adcock, B., and N. Dexter. 2021. The gap between theory and practice in function approximation with deep neural networks. SIAM J. Math. Data Sci 3 (2):624–55. doi:10.1137/20M131309X.
   Google Scholar
• Armstrong, E., J. C. Hewson, and J. C. Sutherland. 2022. Characterizing tradeoffs in memory, accuracy, and speed for chemistry tabulation techniques. Combust. Sci. Technol 1–20. doi:10.1080/00102202.2022.2028780.
   Web of Science ®Google Scholar
• Blasco, J. A., N. Fueyo, J. C. Larroya, C. Dopazo, and Y. J. Chen. 1999. A single-step time-integrator of a methane-air chemical system using artificial neural networks. Comput. Chem. Eng 23 (9):1127–33. doi:10.1016/S0098-1354(99)00278-1.
   Web of Science ®Google Scholar
• Blasco, J., N. Fueyo, C. Dopazo, and J.-Y. Chen. 2000. A self-organizing-map approach to chemistry representation in combustion applications. Combust. Theory Model 4 (1):61–76. doi:10.1088/1364-7830/4/1/304.
   Web of Science ®Google Scholar
• Bode, M., N. Collier, F. Bisetti, and H. Pitsch. 2019. Adaptive chemistry lookup tables for combustion simulations using optimal B-spline interpolants. Combust. Theory Model 23 (4):674–99. doi:10.1080/13647830.2019.1583379.
   Web of Science ®Google Scholar
• Chatzopoulos, A., and S. Rigopoulos. 2013. A chemistry tabulation approach via rate-controlled constrained equilibrium (RCCE) and artificial neural networks (ANNs), with application to turbulent non-premixed CH4/H2/N2 flames. Proc. Combust. Inst 34 (1):1465–73. doi:10.1016/j.proci.2012.06.057.
   Web of Science ®Google Scholar
• Christo, F., A. Masri, and E. Nebot. 1996. Artificial neural network implementation of chemistry with pdf simulation of H2/CO2 flames. Combust. Flame 106 (4):406–27. doi:10.1016/0010-2180(95)00250-2.
   Web of Science ®Google Scholar
• Cyr, E. C., M. A. Gulian, R. G. Patel, M. Perego, and N. A. Trask. 2020. Robust training and initialization of deep neural networks: An adaptive basis viewpoint. Proc. Mach. Learn. Res 107:512–36.
   Google Scholar
• Domino, S. P., J. Hewson, R. Knaus, and M. Hansen. 2021. Predicting large-scale pool fire dynamics using an unsteady flamelet- and large-eddy simulation-based model suite. Phys. Fluids 33 (8):085109. doi:10.1063/5.0060267.
   Web of Science ®Google Scholar
• Emami, M., and A. Eshghinejad Fard. 2012. Laminar flamelet modeling of a turbulent CH4/H2/N2 jet diffusion flame using artificial neural networks. Appl. Math. Model 36 (5):2082–93. doi:10.1016/j.apm.2011.08.012.
   Web of Science ®Google Scholar
• Fokina, D., and I. Oseledets, 2020. Growing axons: Greedy learning of neural networks with application to function approximation. https://arxiv.org/abs/1910.12686v2
   Google Scholar
• Franke, L. L. C., A. K. Chatzopoulos, and S. Rigopoulos. 2017. Tabulation of combustion chemistry via artificial neural networks (ANNs): Methodology and application to LES-PDF simulation of Sydney flame L. Combust. Flame 185:245–60. doi:10.1016/j.combustflame.2017.07.014.
   Web of Science ®Google Scholar
• Haghshenas, M., P. Mitra, N. D. Santo, and D. P. Schmidt. 2021. Acceleration of chemical kinetics computation with the learned intelligent tabulation (LIT) method. Energies 14 (23):7851. doi:10.3390/en14237851.
   Web of Science ®Google Scholar
• Hansen, M. A., E. Armstrong, J. Sutherland, J. McConnell, J. Hewson, and R. Knaus, 2020. Spitfire. Accessed 27 May 2021. https://github.com/sandialabs/Spitfire
   Google Scholar
• Honzawa, T., R. Kai, K. Hori, M. Seino, T. Nishiie, and R. Kurose. 2021. Experimental and numerical study of water sprayed turbulent combustion: Proposal of a neural network modeling for five-dimensional flamelet approach. Energy AI 5:100076. doi:10.1016/j.egyai.2021.100076.
   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. Proc. Combust. Inst 32 (1):1527–35. doi:10.1016/j.proci.2008.06.100.
   Web of Science ®Google Scholar
• Kempf, A., F. Flemming, and J. Janicka. 2005. Investigation of lengthscales, scalar dissipation, and flame orientation in a piloted diffusion flame by LES. Proc. Combust. Inst 30 (1):557–65. doi:10.1016/j.proci.2004.08.182.
   Web of Science ®Google Scholar
• Lee, K., N. A. Trask, R. G. Patel, M. A. Gulian, and E. C. Cyr, 2021. Partition of unity networks: Deep hp-approximation. https://arxiv.org/abs/2101.11256v1
   Google Scholar
• Luo, Z., C. Yoo, E. Richardson, J. Chen, C. Law, and T. Lu. 2012. Chemical explosive mode analysis for a turbulent lifted ethylene jet flame in highly-heated coflow. Combust. Flame 159 (1):265–74. doi:10.1016/j.combustflame.2011.05.023.
   Web of Science ®Google Scholar
• Opschoor, J. A., P. C. Petersen, and C. Schwab. 2020. Deep relu networks and high-order finite element methods. Anal. Appl 18 (5):715–70. doi:10.1142/S0219530519410136.
   Web of Science ®Google Scholar
• Owoyele, O., P. Kundu, M. M. Ameen, T. Echekki, and S. Som. 2020. Application of deep artificial neural networks to multi-dimensional flamelet libraries and spray flames. Int. J. Engine Res 21 (1):151–68. doi:10.1177/1468087419837770.
   Web of Science ®Google Scholar
• Owoyele, O., P. Kundu, and P. Pal. 2021. Efficient bifurcation and tabulation of multi-dimensional combustion manifolds using deep mixture of experts: An a priori study. Proc. Combust. Inst 38 (4):5889–96. doi:10.1016/j.proci.2020.09.006.
   Web of Science ®Google Scholar
• Peters, N. 2000. Turbulent Combustion. Cambridge, U.K: Cambridge University Press.
   Google Scholar
• Pope, S. B. 2013. Small scales, many species and the manifold challenges of turbulent combustion. Proc. Combust. Inst 34 (1):1–31. doi:10.1016/j.proci.2012.09.009.
   Web of Science ®Google Scholar