An optimized active pre-chamber geometry was obtained by combining computational fluid dynamics (CFD) and machine learning (ML). A heavy-duty engine operating with methane under lean conditions was considered. The combustion process was modeled with a multi-zone well-stirred reactor (MZ-WSR) with a skeletal methane oxidation mechanism. The simulations were run for a complete cycle. For the optimization study, the pre-chamber was parametrized; six independent and three dependent variables were considered, while the volume was kept constant. Three hundred pre-chamber designs were generated, and a one-shot design of experiments (DoE) optimization was first considered. A merit function was adopted to rank the designs, and an optimum design was found from the DoE results, which yielded considerable improvements in merit ranking, considering fuel consumption, engine-out emissions, noise, and safety; secondly, machine learning algorithms were trained by utilizing the DoE results aiming at finding a globally optimum geometry for the considered operating condition. Five sequential iterations were performed, and the ML algorithms were capable of proposing a new design with superior performance compared to the best DoE.
AttardWPFraserNParsonsPToulsonE.A turbulent jet ignition pre-chamber combustion system for large fuel economy improvements in a modern vehicle powertrain. SAE Int J Engines2010; 3: 20–37.
2.
ShahA.Improving the efficiency of gas engines using pre-chamber ignition. Doctoral dissertation, Lund University, Lund, Sweden. 2015.
3.
McTaggart-CowanGPReynoldsCCBusheWK.Natural gas fuelling for heavy-duty on-road use: current trends and future direction. Int J Environ Stud2006; 63: 421–440.
4.
AlvarezCECCoutoGERosoVRThirietABValleRM.A review of prechamber ignition systems as lean combustion technology for SI engines. Appl Therm Eng2018; 128: 107–120.
5.
AttardWPParsonsP.A normally aspirated spark initiated combustion system capable of high load, high efficiency and near zero NOx emissions in a modern vehicle powertrain. SAE Int J Engines2010; 3: 269–287.
6.
BenajesJNovellaRGomez-SorianoJMartinez-HernandizPJLibertCDabiriM.Evaluation of the passive pre-chamber ignition concept for future high compression ratio turbocharged spark-ignition engines. Appl Energy2019; 248: 576–588.
7.
GussakLTurkishMSieglaD.High chemical activity of incomplete combustion products and a method of prechamber torch ignition for avalanche activation of combustion in internal combustion engines. SAE technical paper 750890, 1975.
8.
HlaingPSilvaMMarquezME, et al. Estimates of the air-fuel ratio at the time of ignition in a pre-chamber using a narrow throat geometry. Int J Engine Res. Epub ahead of print 15 December 2021. DOI:10.1177/14680874211059148.
9.
HlaingPEcheverri MarquezMCenkerEImHGJohanssonBTurnerJWG. Effects of volume and nozzle area in narrow-throat spark-ignited pre-chamber combustion engines. Fuel2022; 313: 123029.
10.
SilvaMSanalSHlaingPCenkerEJohanssonBImHG.A computational investigation of fuel enrichment in the pre-chamber on the ignition of the main chamber charge. SAE technical paper 2021-01-0523, 2021.
11.
JuDHuangZLiXZhangTCaiW.Comparison of open chamber and pre-chamber ignition of methane/air mixtures in a large bore constant volume chamber: effect of excess air ratio and pre-mixed pressure. Appl Energy2020; 260: 114319.
12.
LawC.Combustion physics. 1st ed. Cambridge: Cambridge University Press, 2006.
13.
ToulsonESchockHAttardW. A review of pre-chamber initiated jet ignition combustion systems. SAE technical paper 2010-01-2263, 2010.
14.
GentzGGholamisheeriMToulsonE.A study of a turbulent jet ignition system fueled with iso-octane: pressure trace analysis and combustion visualization. Appl Energy2017; 189: 385–394.
15.
LiuJDumitrescuCE.3D CFD simulation of a CI engine converted to SI natural gas operation using the G-equation. Fuel2018; 232: 833–844.
16.
YousefiABiroukM.Investigation of natural gas energy fraction and injection timing on the performance and emissions of a dual-fuel engine with pre-combustion chamber under low engine load. Appl Energy2017; 189: 492–505.
17.
HlaingPEcheverri MarquezMBhavani ShankarVCenkerEBen HouidiMJohanssonB. A study of lean burn pre-chamber concept in a heavy duty engine, SAE technical paper 2019-24-0107, 2019.
18.
MullerMFreemanCZhaoP, et al. Numerical simulation of ignition mechanism in the main chamber of turbulent jet ignition system. In: Proceedings of the ASME 2018 internal combustion engine division fall technical conference. volume 2: emissions control systems; instrumentation, controls, and hybrids; numerical simulation; engine design and mechanical development, San Diego, California, USA. November 4–7, 2018. V002T06A010. New York, NY: ASME. DOI: 10.1115/ICEF2018-9587.
19.
HuaJSongYZhouLLiuFWeiH.Operation strategy optimization of lean combustion using turbulent jet ignition at different engine loads. Appl Energy2021; 302: 117586.
20.
GorbatenkoINicolleASilvaMImHGSarathySM.The impact of gasoline formulation on turbulent jet ignition. Fuel2022; 324: 124373.
21.
SilvaMSanalSHlaingPCenkerEJohanssonBImHG. Effects of geometry on passive pre-chamber combustion characteristics. SAE technical paper 2020-01-0821, 2020.
22.
SilvaMM.A numerical investigation of pre-chamber combustion engines, KAUST Research Repository, 2020.
23.
RosoVRSantosNDSAValleRMAlvarezCECMonsalve-SerranoJGarcíaA.Evaluation of a stratified prechamber ignition concept for vehicular applications in real world and standardized driving cycles. Appl Energy2019; 254: 113691.
24.
BiswasSQiaoL.Ignition of ultra-lean premixed hydrogen/air by an impinging hot jet. Appl Energy2018; 228: 954–964.
25.
ShahATunestalPJohanssonB.Effect of pre-chamber volume and nozzle diameter on pre-chamber ignition in heavy duty natural gas engines. SAE technical paper 2015-01-0867, 2015.
26.
HeyneSMillotGFavratD. Numerical simulations of a prechamber autoignition engine operating on natural gas. Int J Thermodyn2011; 14(2): 43–50. DOI: 10.5541/ijot.166
27.
SyrovatkaZVitekOVavraJTakatsM.Scavenged pre-chamber volume effect on gas engine performance and emissions. SAE technical paper 2019-01-0258, 2019.
28.
ThelenBCToulsonE.A computational study on the effect of the orifice size on the performance of a turbulent jet ignition system. Proc IMechE, Part D: J Automobile Engineering2017; 231: 536–554.
29.
KorbBKuppaKNguyenHDDinkelackerFWachtmeisterG.Experimental and numerical investigations of charge motion and combustion in lean-burn natural gas engines. Combust Flame2020; 212: 309–322.
30.
SanalSSilvaMHlaingPCenkerEJohanssonBImHG.A numerical study on the ignition of lean CH4/air mixture by a pre-chamber-initiated turbulent jet. SAE technical paper 2020-01-0820, 2020.
31.
d’AdamoAIacovanoCFontanesiS. Large-eddy simulation of lean and ultra-lean combustion using advanced ignition modelling in a transparent combustion chamber engine. Appl Energy2020; 280: 115949.
32.
GenMChengR.Genetic algorithms and engineering optimization. Hoboken, NJ: John Wiley & Sons, 2000.
33.
BadraJAKhaledFTangM, et al. Engine combustion system optimization using computational fluid dynamics and machine learning: a methodological approach. J Energy Resour Technol2021; 143: 022306.
34.
MoizAAPalPProbstD, et al. A machine learning-genetic algorithm (ML-GA) approach for rapid optimization using high-performance computing. SAE Int J Commer Veh2018; 11: 291–306.
35.
ProbstDMSenecalPKChienPZXuMXLeydeBP.Optimization and uncertainty analysis of a diesel engine operating point using computational fluid dynamics. J Eng Gas Turb Power2018; 140: 102806.
GeHBakirAHYadavSKangYParameswaranSZhaoP.CFD optimization of the pre-chamber geometry for a gasoline spark ignition engine. Front Mech Eng2021; 6: 599752.
38.
PeiYPalPZhangY, et al. CFD-guided combustion system optimization of a gasoline range fuel in a heavy-duty compression ignition engine using automatic piston geometry generation and a supercomputer. SAE Int J Adv Curr Pract Mobil2019; 1: 166–179.
39.
WickmanDSenecalPReitzR.Diesel engine combustion chamber geometry optimization using genetic algorithms and multi-dimensional spray and combustion modeling. SAE technical paper 2001-01-0547, 2001.
40.
BadraJKhaledFSimJ, et al. Combustion system optimization of a light-duty GCI engine using CFD and machine learning. SAE technical paper 2020-01-1313, 2020.
41.
SimJChangJBadraJ.CFD-guided optimization of the injector and injection parameters for light-duty GCI engine. Fuel2022; 316: 123389.
42.
SimJMohanBBadraJ.Co-optimization of piston bowl and injector for light-duty GCI engine using CFD and ML. Fuel2022; 329: 125455.
43.
MohanBAlRamadanASAl-QahtaniYViolletYBadraJ.Development cycle time reduction using design of experiments and machine learning-based optimization framework. Fuel2022; 324: 124671.
SilvaMLiuXHlaingP, et al. Computational assessment of effects of throat diameter on combustion and turbulence characteristics in a pre-chamber engine. Appl Therm Eng2022; 212: 118595.
46.
SilvaMLiuXHlaingPCenkerETurnerJImHG. A computational assessment of combustion submodels for predictive simulations of pre-chamber combustion. In: Proceedings of the ASME 2022 internal combustion engine division fall technical conference, Indianapolis, Indiana, 2022.
47.
KimJScarcelliRSomSShahABirudugantiMSLongmanDE.Assessment of turbulent combustion models for simulating prechamber ignition in a natural gas engine. ASME J Eng Gas Turb Power2021; 143: 091004.
48.
LuTLawCK. A criterion based on computational singular perturbation for the identification of quasi steady state species: a reduced mechanism for methane oxidation with NO chemistry. Combust Flame2008; 154: 761–774.
49.
HanZReitzRD.Turbulence modeling of internal combustion engines using RNG κ-ε models. Combust Sci Technol1995; 106(4–6): 267–295.
50.
IssaRIGosmanADWatkinsAP.The computation of compressible and incompressible recirculating flows by a non-iterative implicit scheme. J Comput Phys1986; 62: 66–82.
51.
AmsdenAAButlerTDO’RourkePJ. The KIVA-II: computer program for transient multidimensional chemically reactive flows with sprays. SAE Technical Paper 872072, 1987.
52.
SilvaMBen HouidiMHlaingP, et al. The effects of piston shape in a narrow-throat pre-chamber engine. SAE technical paper 2022-01-1059, 2022.
53.
SanalSEcheverri MarquezMSilvaMCenkerEImHG.A numerical study on the effect of a pre-chamber initiated turbulent jet on main chamber combustion. SAE technical paper 2022-01-0469, 2022.
54.
DreyfusSE.Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure. J Guid Control Dyn1990; 13: 926–928.
ProkhorenkovaLGusevGVorobevADorogushAVGulinA. CatBoost: unbiased boosting with categorical features. In: Proceedings of the 32nd international conference on neural information processing systems (NIPS’18), Curran Associates Inc., Red Hook, NY, USA, 2018, pp. 6639–6649. New York, NY: ACM Digital Library. DOI: 10.5555/3327757.3327770.
58.
DorogushAVErshovVGulinA.CatBoost: gradient boosting with categorical features support. 2018.
59.
KeGMengQFinleyT, et al. LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st international conference on neural information processing systems (NIPS’17), Curran Associates Inc., Red Hook, NY, USA, 2017, pp.3149–3157. New York, NY: ACM Digital Library. DOI: 10.5555/3294996.3295074.
60.
ZouHHastieT.Regularization and variable selection via the elastic net. J R Stat Soc Ser B2005; 67: 301–320.
61.
HofmannTSchölkopfBSmolaAJ.Kernel methods in machine learning. Ann Stat2008; 36: 1171–1220.
62.
SaundersCGammermanAVovkV. Ridge regression learning algorithm in dual variables. Proceedings of the fifteenth international conference on machine learning (ICML’98), Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1998, pp. 515–521. New York, NY: ACM Digital Library. DOI: 10.5555/645527.657464.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
