Machine learning assisted modeling of mixing timescale for LES/PDF of high-Karlovitz turbulent premixed combustion

Liu, Jinlong; Wang, Haifeng

doi:10.1016/j.combustflame.2021.111895

Machine learning assisted modeling of mixing timescale for LES/PDF of high-Karlovitz turbulent premixed combustion

Journal Article · Fri Dec 10 00:00:00 EST 2021 · Combustion and Flame

DOI:https://doi.org/10.1016/j.combustflame.2021.111895· OSTI ID:1841532

Liu, Jinlong ^[1]; ^[2]

Purdue Univ., West Lafayette, IN (United States); Zhejiang Univ., Hangzhou (China); Purdue University
Purdue Univ., West Lafayette, IN (United States)

Accurate modeling of mixing in the transported probability density function (PDF) method remains a great challenge, especially for turbulent premixed combustion under extreme conditions such as high Karlovitz number Ka. Recently, a power-law based mixing timescale model was developed for the large-eddy simulations (LES)/PDF modeling of high-Ka number turbulent premixed flames. It is found in this work that the power-law mixing timescale model is highly sensitive to the model parameters. It is thus critically needed to develop accurate calibration of these model parameters. The empirical specification of the model parameters developed in Zhang et. al. is found to be inadequate for accurate modeling of the mixing timescale. Here, machine learning is introduced as an attractive alternative in this work for the specification of the model parameters. A high-Ka number DNS jet flame is used as the training and validation of the machine learning models. The choices of the input parameters are discussed and compared for the machine learning models. The effect of differential molecular diffusion on mixing is examined by including the effect of the Lewis number in the training of the machine learning models. The performance of different machine learning algorithms is compared for the specification of the mixing model parameters. Overall, excellent performance of the machine learning models is observed for assisting the mixing modeling. The feasibility, interpretability, applicability, generality, and portability of using machine learning are discussed in general to provide a perspective on applying data-driven machine learning for turbulent combustion modeling studies.

View Accepted Manuscript (DOE)

Research Organization:: Purdue Univ., West Lafayette, IN (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office

Grant/Contract Number:: EE0008876

OSTI ID:: 1841532

Alternate ID(s):: OSTI ID: 1835471

Journal Information:: Combustion and Flame, Journal Name: Combustion and Flame Vol. 238; ISSN 0010-2180

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (30)

Top 10 algorithms in data mining Wu, Xindong; Kumar, Vipin; Ross Quinlan, J. Knowledge and Information Systems, Vol. 14, Issue 1 https://doi.org/10.1007/s10115-007-0114-2	journal	December 2007
LES/PDF Modeling of Turbulent Premixed Flames with Locally Enhanced Mixing by Reaction Wang, Haifeng; Pant, Tejas; Zhang, Pei Flow, Turbulence and Combustion, Vol. 100, Issue 1 https://doi.org/10.1007/s10494-017-9831-0	journal	July 2017
A survey of machine-learning and nature-inspired based credit card fraud detection techniques Adewumi, Aderemi O.; Akinyelu, Andronicus A. International Journal of System Assurance Engineering and Management, Vol. 8, Issue S2 https://doi.org/10.1007/s13198-016-0551-y	journal	December 2016
On reduced mechanisms for methaneair combustion in nonpremixed flames Bilger, R. W.; Stårner, S. H.; Kee, R. J. Combustion and Flame, Vol. 80, Issue 2 https://doi.org/10.1016/0010-2180(90)90122-8	journal	May 1990
An approach to the autoignition of a turbulent mixture Dopazo, César; O'Brien, Edward E. Acta Astronautica, Vol. 1, Issue 9-10 https://doi.org/10.1016/0094-5765(74)90050-2	journal	September 1974
PDF methods for turbulent reactive flows Pope, S. B. Progress in Energy and Combustion Science, Vol. 11, Issue 2 https://doi.org/10.1016/0360-1285(85)90002-4	journal	January 1985
PDF calculations of turbulent nonpremixed flames with local extinction Xu, Jun; Pope, Stephen B. Combustion and Flame, Vol. 123, Issue 3 https://doi.org/10.1016/S0010-2180(00)00155-3	journal	November 2000
The detailed flame structure of highly stretched turbulent premixed methane-air flames Chen, Yung-Cheng; Peters, Norbert; Schneemann, G. A. Combustion and Flame, Vol. 107, Issue 3 https://doi.org/10.1016/S0010-2180(96)00070-3	journal	November 1996
A mixing model for turbulent reactive flows based on Euclidean minimum spanning trees Subramaniam, S. Combustion and Flame, Vol. 115, Issue 4 https://doi.org/10.1016/S0010-2180(98)00023-6	journal	December 1998
Joint scalar probability density function modeling of pollutant formation in piloted turbulent jet diffusion flames with comprehensive chemistry Lindstedt, R. P.; Louloudi, S. A.; Váos, E. M. Proceedings of the Combustion Institute, Vol. 28, Issue 1 https://doi.org/10.1016/S0082-0784(00)80206-4	journal	January 2000
Computations of turbulent combustion: Progress and challenges Pope, S. B. Symposium (International) on Combustion, Vol. 23, Issue 1 https://doi.org/10.1016/S0082-0784(06)80307-3	journal	January 1991
Turbulent combustion modeling Veynante, Denis; Vervisch, Luc Progress in Energy and Combustion Science, Vol. 28, Issue 3 https://doi.org/10.1016/S0360-1285(01)00017-X	journal	March 2002
Turbulent lifted flames in a vitiated coflow investigated using joint PDF calculations Cao, Renfeng Richard; Pope, Stephen B.; Masri, Assaad R. Combustion and Flame, Vol. 142, Issue 4 https://doi.org/10.1016/j.combustflame.2005.04.005	journal	September 2005
A direct numerical simulation study of flame structure and stabilization of an experimental high Ka CH4/air premixed jet flame Wang, Haiou; Hawkes, Evatt R.; Chen, Jacqueline H. Combustion and Flame, Vol. 180 https://doi.org/10.1016/j.combustflame.2017.02.022	journal	June 2017
The effect of mixing models in PDF calculations of piloted jet flames Cao, Renfeng Richard; Wang, Haifeng; Pope, Stephen B. Proceedings of the Combustion Institute, Vol. 31, Issue 1 https://doi.org/10.1016/j.proci.2006.08.052	journal	January 2007
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
Scalar dissipation rate modelling for Large Eddy Simulation of turbulent premixed flames Dunstan, T. D.; Minamoto, Y.; Chakraborty, N. Proceedings of the Combustion Institute, Vol. 34, Issue 1 https://doi.org/10.1016/j.proci.2012.06.143	journal	January 2013
Effect of molecular transport on PDF modeling of turbulent non-premixed flames Wang, Haifeng; Kim, Kukjin Proceedings of the Combustion Institute, Vol. 35, Issue 2 https://doi.org/10.1016/j.proci.2014.06.017	journal	January 2015
Structure of a high Karlovitz n-C7H16 premixed turbulent flame Savard, Bruno; Bobbitt, Brock; Blanquart, Guillaume Proceedings of the Combustion Institute, Vol. 35, Issue 2 https://doi.org/10.1016/j.proci.2014.06.133	journal	January 2015
Flame structure analysis for categorization of lean premixed CH4/air and H2/air flames at high Karlovitz numbers: Direct numerical simulation studies Carlsson, Henning; Yu, Rixin; Bai, Xue-Song Proceedings of the Combustion Institute, Vol. 35, Issue 2 https://doi.org/10.1016/j.proci.2014.09.002	journal	January 2015
A priori analysis of a power-law mixing model for transported PDF model based on high Karlovitz turbulent premixed DNS flames Zhang, Pei; Xie, Tianfang; Kolla, Hemanth Proceedings of the Combustion Institute, Vol. 38, Issue 2 https://doi.org/10.1016/j.proci.2020.06.183	journal	January 2021
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Machine learning for 3D microscopy Waller, Laura; Tian, Lei Nature, Vol. 523, Issue 7561 https://doi.org/10.1038/523416a	journal	July 2015
Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation Zeng, Jinzhe; Cao, Liqun; Xu, Mingyuan Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-19497-z	journal	November 2020
Self-driving cars will take a while to get right Stilgoe, Jack Nature Machine Intelligence, Vol. 1, Issue 5 https://doi.org/10.1038/s42256-019-0046-z	journal	April 2019
Automating turbulence modelling by multi-agent reinforcement learning Novati, Guido; de Laroussilhe, Hugues Lascombes; Koumoutsakos, Petros Nature Machine Intelligence, Vol. 3, Issue 1 https://doi.org/10.1038/s42256-020-00272-0	journal	January 2021
Time-averaging strategies in the finite-volume/particle hybrid algorithm for the joint PDF equation of turbulent reactive flows Wang, Haifeng; Pope, Stephen B. Combustion Theory and Modelling, Vol. 12, Issue 3 https://doi.org/10.1080/13647830701847875	journal	May 2008
Lagrangian investigation of local extinction, re-ignition and auto-ignition in turbulent flames Wang, Haifeng; Pope, Stephen B. Combustion Theory and Modelling, Vol. 12, Issue 5 https://doi.org/10.1080/13647830802056137	journal	September 2008
Deep learning of turbulent scalar mixing Raissi, Maziar; Babaee, Hessam; Givi, Peyman Physical Review Fluids, Vol. 4, Issue 12 https://doi.org/10.1103/PhysRevFluids.4.124501	journal	December 2019
Closure of the Transport Equation for the Probability Density Funcfion of Turbulent Scalar Fields Janicka, J.; Kolbe, W.; Kollmann, W. Journal of Non-Equilibrium Thermodynamics, Vol. 4, Issue 1 https://doi.org/10.1515/jnet.1979.4.1.47	journal	January 1979

Similar Records

A priori analysis of a power-law sub-filter scale mixing model for transported PDF modeling of high Karlovitz turbulent premixed flames

Journal Article · Wed Jul 22 20:00:00 EDT 2020 · Proceedings of the Combustion Institute · OSTI ID:1642113

Multi-regime mixing modeling for local extinction and re-ignition in turbulent non-premixed flame by using LES/FDF method

Journal Article · Wed Mar 29 20:00:00 EDT 2023 · Flow, Turbulence and Combustion · OSTI ID:1971654

Large eddy simulation/dynamic thickened flame modeling of a high Karlovitz number turbulent premixed jet flame

Journal Article · Mon Jul 16 20:00:00 EDT 2018 · Proceedings of the Combustion Institute · OSTI ID:1497652

Related Subjects

42 ENGINEERING
Large-eddy simulations
Machine learning
Mixing process
Power-law mixing timescale model
Transported PDF method

Machine learning assisted modeling of mixing timescale for LES/PDF of high-Karlovitz turbulent premixed combustion

Citation Formats

References (30)

Similar Records

Related Subjects