Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Chemical Science and Engineering

ISSN 2095-0179

ISSN 2095-0187(Online)

CN 11-5981/TQ

Postal Subscription Code 80-969

2018 Impact Factor: 2.809

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Chem. Sci. Eng.    2024, Vol. 18 Issue (11) : 136    https://doi.org/10.1007/s11705-024-2487-0
Optimization of kinetic mechanism for hydrogen combustion based on machine learning
Shuangshuang Cao1, Houjun Zhang1, Haoyang Liu3, Zhiyuan Lyu3, Xiangyuan Li2, Bin Zhang3(), You Han1()
1. School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
2. School of Chemical Engineering, Sichuan University, Chengdu 610065, China
3. School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai 200240, China
 Download: PDF(1564 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

The reduced mechanism based on the minimized reaction network method can effectively solve the rigidity problem in the numerical calculation of turbulent internal combustion engine. The optimization of dynamic parameters of the reduced mechanism is the key to reproduce the experimental data. In this work, the experimental data of ignition delay times and laminar flame speeds were taken as the optimization objectives based on the machine-learning model constructed by radial basis function interpolation method, and pre-exponential factors and activation energies of H2 combustion mechanism were optimized. Compared with the origin mechanism, the performance of the optimized mechanism was significantly improved. The error of ignition delay times and laminar flame speeds was reduced by 24.3% and 26.8%, respectively, with 25% decrease in total mean error. The optimized mechanism was used to predict the ignition delay times, laminar flame speeds and species concentrations of jet stirred reactor, and the predicted results were in good agreement with experimental results. In addition, the differences of the key reactions of the combustion mechanism under specific working conditions were studied by sensitivity analysis. Therefore, the machine-learning model is a tool with broad application prospects to optimize various combustion mechanisms in a wide range of operating conditions.
Keywords hydrogen combustion      machine learning      chemical kinetics      mechanism optimization     
Corresponding Author(s): Bin Zhang,You Han   
Just Accepted Date: 13 June 2024   Issue Date: 15 August 2024
 Cite this article:   
Shuangshuang Cao,Houjun Zhang,Haoyang Liu, et al. Optimization of kinetic mechanism for hydrogen combustion based on machine learning[J]. Front. Chem. Sci. Eng., 2024, 18(11): 136.
 URL:  
https://academic.hep.com.cn/fcse/EN/10.1007/s11705-024-2487-0
https://academic.hep.com.cn/fcse/EN/Y2024/V18/I11/136
Fig.1  Experimental data distribution of (a) IDTs [27?29] and (b) LFSs [27,30?33].
No.ReactionA/(cm3·mol–1·s–1)Aopti/(cm3·mol–1·s–1)Ea/(cal·mol–1)Ea-opti/(cal·mol–1)
1H2O2(+M) = OH + OH(+M)2.21E + 152.71E + 155023050432
Low pressure limit4.17E + 164.19E + 164496045476
H2O/7.65/N2/1.50/O2/1.20/H2O2/7.70/H2/3.70/He/0.65
2H2 + HO2 = H2O2 + H3.01E + 134.46E + 13260802.4438
3H2 + OH = H + H2O4.38E + 133.29E + 1369907547
4H2 + O2 = HO2 + H1.76E + 141.79E + 14578205.7361
5H2 + O = H + OH6.83E + 139.80E + 131038010985
6H2 + M = H + H + M3.33E + 144.56E + 14102070101267
H2/2.50/H2O/12.00/He/0.83
7HO2 + H = OH + OH7.08E + 135.18E + 1315001111
8H + O2(+M) = HO2(+M)1.14E + 141.30E + 1400
Low pressure limit2.28E + 153.48E + 1500
H2/1.30/H2O/10.00/He/0.64/Ar/0.50
9O2 + H = O + OH1.04E + 141.54E + 141560015793
Tab.1  The initial H2 mechanism and optimized H2 mechanism
Fig.2  Implementation process of mechanism optimization using the machine-learning model.
No. Reaction f(T) R
1 H2O2(+M) = OH + OH(+M) 0.2 between 700 and 1500 K 58.38%
Low pressure limit 37.88%
H2O/7.65/N2/1.50/O2/1.20/ H2O2/7.70/H2/3.70/He/0.65
2 H2 + HO2 = H2O2 + H 0.5 between 280 and 1000 K –12.85%
3 H2 + OH = H + H2O 0.1 at 250 K, increasing to 0.3 at 2500 K –22.02%
4 H2 + O2 = HO2 + H 0.3 between 250 and 1000 K –19.27%
5 H2 + O = H + OH 0.2 between 298 and 3300 K 121.64%
6 H2 + M = H + H + M 0.3 between 2500 and 8000 K 7.15%
H2/2.50/H2O/12.00/He/0.83
7 HO2 + H = OH + OH 0.15 between 250 and 1000 K –127.7%
8 H + O2(+M) = HO2(+M) 0.1 at 298 K, increasing to 0.3 at 2000 K 39.46%
Low pressure limit 74.76%
H2/1.30/H2O/10.00/He/0.64/Ar/0.50
9 O2 + H = O + OH 0.29 at 800 K, decreasing to 0.21 at 1300 K, then increasing to 0.33 at 2700 K 79.23%
Tab.2  The uncertainty factor and the integrated reaction rate adjustment of each reaction in H2 mechanism
Fig.3  Box plot of the prediction relative error using the origin, optimized, Kéromnès, and NUIG mechanisms for IDTs and LFSs.
Fig.4  IDTs simulations using the origin, optimized, Kéromnès, NUIG mechanisms for experimental data for (a) P = 1.6208 × 105 Pa, (b) P = 1.3169 × 106 Pa, (c) P = 3.3429 × 106 Pa.
Fig.5  IDTs simulations using the origin, optimized, Kéromnès, NUIG mechanisms for experimental data for N2 and Ar diluents. (a) P = 1.013 × 105 Pa with N2 diluent, (b) P = 4.052 × 105 Pa with N2 diluent, (c) P = 1.2156 × 105 Pa with Ar diluent, and (d) P = 4.052 × 105 Pa with Ar diluent.
Fig.6  IDTs simulations using the origin, optimized, Kéromnès, NUIG mechanisms for experimental data for different equivalent ratios. (a) φ = 0.1, (b) φ = 1, and (c) φ = 1.5.
Fig.7  LFSs simulations using the origin, optimized, Kéromnès, NUIG mechanisms for experimental data for (a) N2, (b) He, and (c) Ar diluents.
Fig.8  LFSs simulations using the origin, optimized, Kéromnès, and NUIG mechanisms for experimental data for (a) P = 1.013 × 105 Pa, (b) P = 2.026 × 105 Pa, (c) P = 3.039 × 105 Pa, and (d) P = 4.052 × 105 Pa.
Fig.9  LFSs simulations using the origin, optimized, Kéromnès and NUIG mechnisms for experimental data for (a) T = 298 K, (b) T = 300 K, (c) T = 303 K, and (d) T = 365 K.
Case V/cm3 P/Pa tau/s φ Initial_H2 Initial_O2 Initial_N2 Initial_H2O
1 30 1.013 × 105 0.12 0.2 0.0108 0.025 0.9642 0
2 30 1.013 × 105 0.12 0.5 0.0107 0.01 0.9793 0
3 30 1.013 × 105 0.12 2 0.011 0.0025 0.9865 0
4 30 1.013 × 105 0.12 0.2 0.0115 0.025 0.8635 0.1
5 30 1.013 × 105 0.12 0.5 0.00928 0.011 0.87972 0.1
6 30 1.013 × 105 0.12 1 0.0113 0.005 0.8837 0.1
Tab.3  Simulation conditions for the PSR
Fig.10  Sensitivity analysis using the origin and optimized mechanisms at the ignition point (φ = 1, T = 1172 K, and P = 1.013 × 105 Pa).
1 O I Awad , B Zhou , K Harrath , K Kadirgama . Characteristics of NH3/H2 blend as carbon-free fuels: a review. International Journal of Hydrogen Energy, 2023, 48(96): 38077–38100
https://doi.org/10.1016/j.ijhydene.2022.09.096
2 X LiX YaoJ ShentuX SunJ LiM LiuS Xu. Combustion reaction mechanism construction by two-parameter rate constant method. Chemical Journal of Chinese Universities, 2020, 41(3): 512–520 (in Chinese)
3 X LiJ ShentuY LiJ LiJ Wang. Combustion mechanism construction based on minimized reaction network: hydrogen-oxygen combustion. Chemical Journal of Chinese Universities, 2020, 41(4): 772–779 (in Chinese)
4 H Wang , D A Sheen . Combustion kinetic model uncertainty quantification, propagation and minimization. Progress in Energy and Combustion Science, 2015, 47: 1–31
https://doi.org/10.1016/j.pecs.2014.10.002
5 H Wang , M Yao , R D Reitz . Development of a reduced primary reference fuel mechanism for internal combustion engine combustion simulations. Energy & Fuels, 2013, 27(12): 7843–7853
https://doi.org/10.1021/ef401992e
6 Y Ra , R D Reitz . A reduced chemical kinetic model for IC engine combustion simulations with primary reference fuels. Combustion and Flame, 2008, 155(4): 713–738
https://doi.org/10.1016/j.combustflame.2008.05.002
7 D Lv , Y Chen , Y Chen , X Guo , H Chen , H Huang . Development of a reduced diesel/PODEn mechanism for diesel engine application. Energy Conversion and Management, 2019, 199: 112070
https://doi.org/10.1016/j.enconman.2019.112070
8 S Lin , W Sun , L Guo , P Cheng , Y Sun , H Zhang . Development of a reduced mechanism of a three components surrogate fuel for the coal-to-liquid and diesel combustion simulation. Fuel, 2021, 294: 120370
https://doi.org/10.1016/j.fuel.2021.120370
9 A Lapene , G Debenest , M Quintard , L M Castanier , M G Gerritsen , A R Kovscek . Kinetics oxidation of heavy oil. 2. Application of genetic algorithm for evaluation of kinetic parameters. Energy & Fuels, 2015, 29(2): 1119–1129
https://doi.org/10.1021/ef501392k
10 B Niu , M Jia , G Xu , Y Chang , M Xie . Efficient approach for the optimization of skeletal chemical mechanisms with multiobjective genetic algorithm. Energy & Fuels, 2018, 32(6): 7086–7102
https://doi.org/10.1021/acs.energyfuels.8b00356
11 J Si , G Wang , P Li , J Mi . Optimization of the global reaction mechanism for MILD combustion of methane using artificial neural network. Energy & Fuels, 2020, 34(3): 3805–3815
https://doi.org/10.1021/acs.energyfuels.9b04413
12 Q Lin , J Zheng , C Zou , J Cheng , J Li , W Xia , H Shi . An improved 3-pentanone high temperature kinetic model using Bayesian optimization algorithm based on ignition delay times, flame speeds and species profiles. Fuel, 2020, 279: 118540
https://doi.org/10.1016/j.fuel.2020.118540
13 Q Lin , C Zou , S Liu , Y Wang , L Lu , C Peng . An improved 2-pentanone low to high-temperature kinetic model using Bayesian optimization algorithm. Combustion and Flame, 2021, 231: 111453
https://doi.org/10.1016/j.combustflame.2021.111453
14 W Li , C Zou , H Yao , Q Lin , R Fu , J Luo . An optimized kinetic model for H2/CO combustion in CO2 diluent at elevated pressures. Combustion and Flame, 2022, 241: 112093
https://doi.org/10.1016/j.combustflame.2022.112093
15 X Liu , Y Wang , Y Bai , W Yang . Development of reduced and optimized mechanism for ammonia/hydrogen mixture based on genetic algorithm. Energy, 2023, 270: 126927
https://doi.org/10.1016/j.energy.2023.126927
16 Q Lin , C Zou , J Luo , W Xia , W Li , C Peng . A shock tube experiment and an improved high-temperature diisopropyl ketone model by Bayesian optimization. Combustion and Flame, 2022, 245: 112305
https://doi.org/10.1016/j.combustflame.2022.112305
17 N I Vollmer , R Al , K V Gernaey , G Sin . Synergistic optimization framework for the process synthesis and design of biorefineries. Frontiers of Chemical Science and Engineering, 2022, 16(2): 251–273
https://doi.org/10.1007/s11705-021-2071-9
18 X Wang , J Li , Y Zheng , J Lin . Smart systems engineering contributing to an intelligent carbon-neutral future: opportunities, challenges, and prospects. Frontiers of Chemical Science and Engineering, 2022, 16(6): 1023–1029
https://doi.org/10.1007/s11705-022-2142-6
19 H Fang , J Zhou , Z Wang , Z Qiu , Y Sun , Y Lin , K Chen , X Zhou , M Pan . Hybrid method integrating machine learning and particle swarm optimization for smart chemical process operations. Frontiers of Chemical Science and Engineering, 2022, 16(2): 274–287
https://doi.org/10.1007/s11705-021-2043-0
20 E Chee , W C Wong , X Wang . An integrated approach for machine-learning-based system identification of dynamical systems under control: application towards the model predictive control of a highly nonlinear reactor system. Frontiers of Chemical Science and Engineering, 2022, 16(2): 237–250
https://doi.org/10.1007/s11705-021-2058-6
21 P O Ludl , R Heese , J Höller , N Asprion , M Bortz . Using machine learning models to explore the solution space of large nonlinear systems underlying flowsheet simulations with constraints. Frontiers of Chemical Science and Engineering, 2022, 16(2): 183–197
https://doi.org/10.1007/s11705-021-2073-7
22 A Kéromnès , W K Metcalfe , K A Heufer , N Donohoe , A K Das , C J Sung , J Herzler , C Naumann , P Griebel , O Mathieu . et al.. An experimental and detailed chemical kinetic modeling study of hydrogen and syngas mixture oxidation at elevated pressures. Combustion and Flame, 2013, 160(6): 995–1011
https://doi.org/10.1016/j.combustflame.2013.01.001
23 D Healy , D M Kalitan , C J Aul , E L Petersen , G Bourque , H J Curran . Oxidation of C1–C5 alkane quinternary natural gas mixtures at high pressures. Energy & Fuels, 2010, 24(3): 1521–1528
https://doi.org/10.1021/ef9011005
24 C Olm , I G Zsély , T Varga , H J Curran , T Turányi . Comparison of the performance of several recent syngas combustion mechanisms. Combustion and Flame, 2015, 162(5): 1793–1812
https://doi.org/10.1016/j.combustflame.2014.12.001
25 Cantera: an object-oriented software toolkit for chemical kinetics, thermodynamics, and transport processes. Version 2.6.0. Pasadena: California Institute of Technology, 2022
26 W Sun , J Wang , C Huang , N Hansen , B Yang . Providing effective constraints for developing ketene combustion mechanisms: a detailed kinetic investigation of diacetyl flames. Combustion and Flame, 2019, 205: 11–21
https://doi.org/10.1016/j.combustflame.2019.03.037
27 C Olm , I G Zsély , R Pálvölgyi , T Varga , T Nagy , H J Curran , T Turányi . Comparison of the performance of several recent hydrogen combustion mechanisms. Combustion and Flame, 2014, 161(9): 2219–2234
https://doi.org/10.1016/j.combustflame.2014.03.006
28 L Pan , E Hu , F Deng , Z Zhang , Z Huang . Effect of pressure and equivalence ratio on the ignition characteristics of dimethyl ether-hydrogen mixtures. International Journal of Hydrogen Energy, 2014, 39(33): 19212–19223
https://doi.org/10.1016/j.ijhydene.2014.09.098
29 A Drakon , A Eremin , N Matveeva , E Mikheyeva . The opposite influences of flame suppressants on the ignition of combustible mixtures behind shock waves. Combustion and Flame, 2017, 176: 592–598
https://doi.org/10.1016/j.combustflame.2016.11.001
30 X LVE HuC PengX MengZ Huang. Measurements on laminar burning velocities of hydrogen/oxygen/diluents at elevated pressure and temperature. Journal of Aerospace Power, 2017, 32(7): 1599–1607 (in Chinese)
31 E Hu , Z Huang , J He , C Jin , J Zheng . Experimental and numerical study on laminar burning characteristics of premixed methane-hydrogen-air flames. International Journal of Hydrogen Energy, 2009, 34(11): 4876–4888
https://doi.org/10.1016/j.ijhydene.2009.03.058
32 X Qin , H Kobayashi , T Niioka . Laminar burning velocity of hydrogen-air premixed flames at elevated pressure. Experimental Thermal and Fluid Science, 2000, 21(1): 58–63
https://doi.org/10.1016/S0894-1777(99)00054-0
33 Z Huang , Y Zhang , K Zeng , B Liu , Q Wang , D Jiang . Measurements of laminar burning velocities for natural gas-hydrogen-air mixtures. Combustion and Flame, 2006, 146(1): 302–311
https://doi.org/10.1016/j.combustflame.2006.03.003
34 G A Pang , D F Davidson , R K Hanson . Experimental study and modeling of shock tube ignition delay times for hydrogen-oxygen-argon mixtures at low temperatures. Proceedings of the Combustion Institute, 2009, 32(1): 181–188
https://doi.org/10.1016/j.proci.2008.06.014
35 C W Zhou , Y Li , U Burke , C Banyon , K P Somers , S Ding , S Khan , J W Hargis , T Sikes , O Mathieu . et al.. An experimental and chemical kinetic modeling study of 1,3-butadiene combustion: ignition delay time and laminar flame speed measurements. Combustion and Flame, 2018, 197: 423–438
https://doi.org/10.1016/j.combustflame.2018.08.006
36 H WangX YouA V JoshiS G DavisA LaskinF EgolfopoulosC Law. USC Mech Version II. High-Temperature Combustion Reaction Model of H2/CO/C1/C4 Compounds, 2007
37 H Behrooz , Y M Hayeri . Machine learning applications in surface transportation systems: a literature review. Applied Sciences (Basel, Switzerland), 2022, 12(18): 9156
https://doi.org/10.3390/app12189156
38 A K Shakya , G Pillai , S Chakrabarty . Reinforcement learning algorithms: a brief survey. Expert Systems with Applications, 2023, 231: 120495
https://doi.org/10.1016/j.eswa.2023.120495
39 P Priore , B Ponte , J Puente , A Gómez . Learning-based scheduling of flexible manufacturing systems using ensemble methods. Computers & Industrial Engineering, 2018, 126: 282–291
https://doi.org/10.1016/j.cie.2018.09.034
40 J I Ryu , K Kim , K Min , R Scarcelli , S Som , K S Kim , J E Temme , C B M Kweon , T Lee . Data-driven chemical kinetic reaction mechanism for F-24 jet fuel ignition. Fuel, 2021, 290: 119508
https://doi.org/10.1016/j.fuel.2020.119508
41 J A Nelder , R Mead . A simplex method for function minimization. Computer Journal, 1964, 7(4): 308–313
https://doi.org/10.1093/comjnl/7.4.308
42 J W Sutherland , J V Michael , A N Pirraglia , F L Nesbitt , R B Klemm . Rate constant for the reaction of O(3P) with H2 by the flash photolysis-shock tube and flash photolysis-resonance fluorescence techniques; 504 K ≤ T ≤ 2495 K. Symposium (International) on Combustion, 1988, 21(1): 929–941
43 S O Ryu , S M Hwang , M J Rabinowitz . Rate coefficient of the O + H2 = OH + H reaction determined via shock tube-laser absorption spectroscopy. Chemical Physics Letters, 1995, 242(3): 279–284
https://doi.org/10.1016/0009-2614(95)00733-K
44 S H Mousavipour , V Saheb . Theoretical study on the kinetic and mechanism of H + HO2 reaction. Bulletin of the Chemical Society of Japan, 2007, 80(10): 1901–1913
https://doi.org/10.1246/bcsj.80.1901
45 H Yang , W C Gardiner , K S Shin , N Fujii . Shock tube study of the rate coefficient of H + O2 → OH + O. Chemical Physics Letters, 1994, 231(4): 449–453
https://doi.org/10.1016/0009-2614(94)01288-1
46 H Du , J P Hessler . Rate coefficient for the reaction H + O2 → OH + O: results at high temperatures, 2000 to 5300 K. Journal of Chemical Physics, 1992, 96(2): 1077–1092
https://doi.org/10.1063/1.462194
47 K S Shin , J V Michael . Rate constants for the reactions H + O2 → OH + O and D + O2 → OD + O over the temperature range 1085–2278 K by the laser photolysis-shock tube technique. Journal of Chemical Physics, 1991, 95(1): 262–273
https://doi.org/10.1063/1.461483
48 A N Pirraglia , J V Michael , J W Sutherland , R B Klemm . A flash photolysis-shock tube kinetic study of the hydrogen atom reaction with oxygen: H + O2 → OH + O (962 K ≤ T ≤ ltoreq. 1705 K) and H + O2 + Ar → HO2 + Ar (746 K ≤ T ≤ 987 K). Journal of Physical Chemistry, 1989, 93(1): 282–291
https://doi.org/10.1021/j100338a058
49 T Le Cong , P Dagaut . Experimental and detailed modeling study of the effect of water vapor on the kinetics of combustion of hydrogen and natural gas, impact on NOx. Energy & Fuels, 2009, 23(2): 725–734
https://doi.org/10.1021/ef800832q
[1] FCE-24039-OF-CS_suppl_1 Download
[1] Lihe Zhang, Changwei Zhang, Xi Zhao, Changliu He, Xu Zhang. Improving lipid production by Rhodotorula glutinis for renewable fuel production based on machine learning[J]. Front. Chem. Sci. Eng., 2024, 18(5): 51-.
[2] Rohan Ali, Yifei Zhang. Machine learning meets enzyme engineering: examples in the design of polyethylene terephthalate hydrolases[J]. Front. Chem. Sci. Eng., 2024, 18(12): 149-.
[3] Yi Cheng, Qiong Pan, Jie Li, Nan Zhang, Yang Yang, Jiawei Wang, Ningbo Gao. Machine learning facilitated the modeling of plastics hydrothermal pretreatment toward constructing an on-ship marine litter-to-methanol plant[J]. Front. Chem. Sci. Eng., 2024, 18(10): 117-.
[4] Xiaonan Wang, Jie Li, Yingzhe Zheng, Jiali Li. Smart systems engineering contributing to an intelligent carbon-neutral future: opportunities, challenges, and prospects[J]. Front. Chem. Sci. Eng., 2022, 16(6): 1023-1029.
[5] Yiming Ma, Zhenguo Gao, Peng Shi, Mingyang Chen, Songgu Wu, Chao Yang, Jing-Kang Wang, Jingcai Cheng, Junbo Gong. Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients in industrial crystallization[J]. Front. Chem. Sci. Eng., 2022, 16(4): 523-535.
[6] Patrick Otto Ludl, Raoul Heese, Johannes Höller, Norbert Asprion, Michael Bortz. Using machine learning models to explore the solution space of large nonlinear systems underlying flowsheet simulations with constraints[J]. Front. Chem. Sci. Eng., 2022, 16(2): 183-197.
[7] Haoqin Fang, Jianzhao Zhou, Zhenyu Wang, Ziqi Qiu, Yihua Sun, Yue Lin, Ke Chen, Xiantai Zhou, Ming Pan. Hybrid method integrating machine learning and particle swarm optimization for smart chemical process operations[J]. Front. Chem. Sci. Eng., 2022, 16(2): 274-287.
[8] Quirin Göttl, Dominik G. Grimm, Jakob Burger. Automated synthesis of steady-state continuous processes using reinforcement learning[J]. Front. Chem. Sci. Eng., 2022, 16(2): 288-302.
[9] Ewan Chee, Wee Chin Wong, Xiaonan Wang. An integrated approach for machine-learning-based system identification of dynamical systems under control: application towards the model predictive control of a highly nonlinear reactor system[J]. Front. Chem. Sci. Eng., 2022, 16(2): 237-250.
[10] WANG Lijun, CHENG Youwei, WANG Qinbo, LI Xi. Progress in the research and development of p-xylene liquid phase oxidation process[J]. Front. Chem. Sci. Eng., 2007, 1(3): 317-326.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed