Physics informed machine learning for chemistry tabulation

Salunkhe, Amol; Deighan, Dwyer; DesJardin, Paul E.; Chandola, Varun

doi:10.1016/j.jocs.2023.102001

Physics informed machine learning for chemistry tabulation

Journal Article · Fri Mar 17 00:00:00 EDT 2023 · Journal of Computational Science

DOI:https://doi.org/10.1016/j.jocs.2023.102001· OSTI ID:2417942

^[1]; Deighan, Dwyer ^[2]; DesJardin, Paul E. ^[2]; Chandola, Varun ^[2]

Univ. at Buffalo, NY (United States); OSTI
Univ. at Buffalo, NY (United States)

Modeling of turbulent combustion system requires modeling the underlying chemistry and the turbulent transport. Solving both systems simultaneously is computationally prohibitive. Instead, given the difference in scales at which the two sub-systems evolve, the two sub-systems are typically (re)solved separately. Popular approaches such as the Flamelet Generated Manifolds (FGM) use a two-step strategy where the governing reaction kinetics are pre-computed and mapped to a low-dimensional manifold, characterized by a few reaction progress variables (model reduction) and the manifold is then “looked-up” during the run-time to estimate the high-dimensional system state by the turbulent transport system. While existing works have focused on these two steps independently, in this work we show that joint learning of the progress variables and the look-up model, can yield more accurate results. Here, we build on the base formulation and implementation to include the dynamically generated Thermochemical State Variables (Lower Dimensional Dynamic Source Terms). We discuss the challenges in the implementation of this deep neural network architecture and experimentally demonstrate its superior performance.

View Accepted Manuscript (DOE)

Research Organization:: State Univ. of New York (SUNY), Albany, NY (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0003961

OSTI ID:: 2417942

Alternate ID(s):: OSTI ID: 1968509

Journal Information:: Journal of Computational Science, Journal Name: Journal of Computational Science Journal Issue: C Vol. 69; ISSN 1877-7503

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (22)

Turbulent Combustion Modelling and Experiments: Recent Trends and Developments Giusti, A.; Mastorakos, E. Flow, Turbulence and Combustion, Vol. 103, Issue 4 https://doi.org/10.1007/s10494-019-00072-6	journal	November 2019
Laminar diffusion flamelet models in non-premixed turbulent combustion Peters, N. Progress in Energy and Combustion Science, Vol. 10, Issue 3 https://doi.org/10.1016/0360-1285(84)90114-X	journal	January 1984
Modeling of complex premixed burner systems by using flamelet-generated manifolds van Oijen, J. A.; Lammers, F. A.; de Goey, L. P. H. Combustion and Flame, Vol. 127, Issue 3 https://doi.org/10.1016/S0010-2180(01)00316-9	journal	November 2001
An a-posteriori evaluation of principal component analysis-based models for turbulent combustion simulations Biglari, Amir; Sutherland, James C. Combustion and Flame, Vol. 162, Issue 10 https://doi.org/10.1016/j.combustflame.2015.07.042	journal	October 2015
Formulation and assessment of flamelet-generated manifolds for reacting interfaces Bojko, Brian T.; DesJardin, Paul E. Combustion and Flame, Vol. 173 https://doi.org/10.1016/j.combustflame.2016.08.004	journal	November 2016
Principal component analysis coupled with nonlinear regression for chemistry reduction Malik, Mohammad Rafi; Isaac, Benjamin J.; Coussement, Axel Combustion and Flame, Vol. 187 https://doi.org/10.1016/j.combustflame.2017.08.012	journal	January 2018
Large eddy simulation of spray combustion using flamelet generated manifolds combined with artificial neural networks Zhang, Yan; Xu, Shijie; Zhong, Shenghui Energy and AI, Vol. 2 https://doi.org/10.1016/j.egyai.2020.100021	journal	November 2020
Regularization of reaction progress variable for application to flamelet-based combustion models Ihme, Matthias; Shunn, Lee; Zhang, Jian Journal of Computational Physics, Vol. 231, Issue 23 https://doi.org/10.1016/j.jcp.2012.06.029	journal	October 2012
Hidden physics models: Machine learning of nonlinear partial differential equations Raissi, Maziar; Karniadakis, George Em Journal of Computational Physics, Vol. 357 https://doi.org/10.1016/j.jcp.2017.11.039	journal	March 2018
Modeling and simulation of turbulent nuclear flames in Type Ia supernovae Nouri, Arash G.; Givi, Peyman; Livescu, Daniel Progress in Aerospace Sciences, Vol. 108 https://doi.org/10.1016/j.paerosci.2019.04.004	journal	July 2019
Toward accommodating realistic fuel chemistry in large-scale computations Lu, Tianfeng; Law, Chung K. Progress in Energy and Combustion Science, Vol. 35, Issue 2 https://doi.org/10.1016/j.pecs.2008.10.002	journal	April 2009
Prediction of local extinction and re-ignition effects in non-premixed turbulent combustion using a flamelet/progress variable approach Ihme, Matthias; Cha, Chong M.; Pitsch, Heinz Proceedings of the Combustion Institute, Vol. 30, Issue 1 https://doi.org/10.1016/j.proci.2004.08.260	journal	January 2005
Optimal artificial neural networks and tabulation methods for chemistry representation in LES of a bluff-body swirl-stabilized flame Ihme, Matthias; Schmitt, Christoph; Pitsch, Heinz Proceedings of the Combustion Institute, Vol. 32, Issue 1 https://doi.org/10.1016/j.proci.2008.06.100	journal	January 2009
Combustion modeling using principal component analysis Sutherland, James C.; Parente, Alessandro Proceedings of the Combustion Institute, Vol. 32, Issue 1 https://doi.org/10.1016/j.proci.2008.06.147	journal	January 2009
Petascale direct numerical simulation of turbulent combustion—fundamental insights towards predictive models Chen, Jacqueline H. Proceedings of the Combustion Institute, Vol. 33, Issue 1 https://doi.org/10.1016/j.proci.2010.09.012	journal	January 2011
Progress-variable approach for large-eddy simulation of non-premixed turbulent combustion Pierce, Charles D.; Moin, Parviz Journal of Fluid Mechanics, Vol. 504 https://doi.org/10.1017/S0022112004008213	journal	January 1999
Spatial reduction algorithm for atmospheric chemical transport models Rastigejev, Y.; Brenner, M. P.; Jacob, D. J. Proceedings of the National Academy of Sciences, Vol. 104, Issue 35 https://doi.org/10.1073/pnas.0705649104	journal	August 2007
Modelling of Premixed Laminar Flames using Flamelet-Generated Manifolds Oijen, J. A. Van; Goey, L. P. H. De Combustion Science and Technology, Vol. 161, Issue 1 https://doi.org/10.1080/00102200008935814	journal	December 2000
Validation of the fpi Chemistry Reduction Method for Diluted Nonadiabatic Premixed Flames Fiorina, B.; Gicquel, O.; Carpentier, S. Combustion Science and Technology, Vol. 176, Issue 5-6 https://doi.org/10.1080/00102200490428404	journal	May 2004
Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data Karpatne, Anuj; Atluri, Gowtham; Faghmous, James H. IEEE Transactions on Knowledge and Data Engineering, Vol. 29, Issue 10 https://doi.org/10.1109/TKDE.2017.2720168	journal	October 2017
In situ temperature measurements in sooting methane/air flames using synchrotron x-ray fluorescence of seeded krypton atoms Montgomery, Matthew J.; Kwon, Hyunguk; Kastengren, Alan L. Science Advances, Vol. 8, Issue 17 https://doi.org/10.1126/sciadv.abm7947	journal	April 2022
Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations Raissi, Maziar; Yazdani, Alireza; Karniadakis, George Em Science, Vol. 367, Issue 6481 https://doi.org/10.1126/science.aaw4741	journal	January 2020

Similar Records

Co-optimized machine-learned manifold models for large eddy simulation of turbulent combustion

Journal Article · Fri Jul 15 20:00:00 EDT 2022 · Combustion and Flame · OSTI ID:1877598

A two-equation soot-in-flamelet modeling approach applied under Spray A conditions

Journal Article · Tue Aug 31 20:00:00 EDT 2021 · Combustion and Flame · OSTI ID:1788418

Using the tabulated diffusion flamelet model ADF-PCM to simulate a lifted methane-air jet flame

Journal Article · Wed Jul 15 00:00:00 EDT 2009 · Combustion and Flame · OSTI ID:21195819

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
97 MATHEMATICS AND COMPUTING
Chemistry tabulation
Combustion
Computer Science
Deep neural networks
Fluid dynamics
Physics informed machine learning

Physics informed machine learning for chemistry tabulation

Citation Formats

References (22)

Similar Records

Related Subjects