This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A Comparative Study of Physics Based Grey Box and Neural Network Trained Black Box Dynamic Models in an RCCI Engine Control Parameter Prediction
Technical Paper
2021-01-0178
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Event:
SAE WCX Digital Summit
Language:
English
Abstract
Reactivity controlled compression ignition (RCCI) engines are considered as a potent solution to realize near zero nitrogen oxides (NOx) and soot emission with higher thermal efficiency. However, operational control in RCCI engines is challenging, as events such as ignition and combustion phasing etc. are mostly decoupled from hardware induced start of injection. In modern control architecture, these real time data are internally computed using signals from cylinder pressure sensor (CPS). Lately, physics based control models or grey box models in RCCI engines were considered as a cost competitive and smart alternative to hardware signal source. In this work, an attempt was made to develop and compare physics based grey box model with data based neural networks, trained through supervised learning (or the black box models) to accurately predict dynamic combustion control parameters across five engine loads and incremental premix energy share not exceeding 60%. Chosen control parameters for the study were the start of combustion (Ɵsoc), 50% mass fraction burnt crank angle (Ɵ50) and combustion peak pressure (PP). The model predictions were compared with real time experimentally measured data and comparative model quality study was carried out. Results indicated that the grey box model regression (R2) values for Ɵsoc, PP and Ɵ50 were 0.7054, 0.9535 and 0.7658 respectively that increased to 0.7637, 0.9654 and 0.8854 respectively for black box models. The overall tracking error for Ɵsoc was 2.442 and 2.0780CA for grey and black box models, respectively. For Ɵ50, the error was 4.262 and 2.9040CA in the same order. Finally, for PP, the error was 6.420 and 5.475 bar respectively for grey and black box models. Grey box models exhibited higher skewness and lower kurtosis values in error distribution compared to black box models.
Authors
Citation
Mishra, C. and Subbarao, P., "A Comparative Study of Physics Based Grey Box and Neural Network Trained Black Box Dynamic Models in an RCCI Engine Control Parameter Prediction," SAE Technical Paper 2021-01-0178, 2021, https://doi.org/10.4271/2021-01-0178.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 | ||
Unnamed Dataset 3 | ||
Unnamed Dataset 4 | ||
Unnamed Dataset 5 | ||
Unnamed Dataset 6 |
Also In
References
- Kokjohn , S.L. , Hanson , R.M. , Splitter , D.A. , and Reitz , R.D. Fuel Reactivity Controlled Compression Ignition (RCCI): A Pathway to Controlled High-Efficiency Clean Combustion Int J Engine Res 12 209 226 2011 https://doi.org/10.1177/1468087411401548
- Splitter , D.A. , and Reitz , R.D. Fuel Reactivity Effects on the Efficiency and Operational Window of Dual-Fuel Compression Ignition Engines Fuel 118 163 175 2014 https://doi.org/10.1016/j.fuel.2013.10.045
- Klos , D. , and Kokjohn , S.L. Investigation of the Sources of Combustion Instability in Low-Temperature Combustion Engines Using Response Surface Models Int J Engine Res 16 419 440 2015 https://doi.org/10.1177/1468087414556135
- Hanson , R. , Kokjohn , S. , Splitter , D. , and Reitz , R. Fuel Effects on Reactivity Controlled Compression Ignition (RCCI) Combustion at Low Load SAE Int J Engines 2011 https://doi.org/10.4271/2011-01-0361
- Splitter , D. , Reitz , R.D. , and R. , H. High Efficiency, Low Emissions RCCI Combustion by Use of a Fuel Additive SAE Int J Fuels Lubr 3 742 756 2010 https://doi.org/10.4271/2010-01-2167
- Benajes , J. , García , A. , Monsalve-Serrano , J. , and Sari , R. Potential of RCCI Series Hybrid Vehicle Architecture to Meet the Future CO2 Targets with Low Engine-Out Emissions Appl Sci 2018 https://doi.org/10.3390/app8091472
- Saxena , M.R. , and Maurya , R.K. Experimental Investigation of Combustion Stability and Particle Emission from CNG/Diesel RCCI Engine SAE Tech Pap. 2020 https://doi.org/10.4271/2020-01-0810
- Willems , F.I. Cylinder Pressure-Based Control Required to Meet Future HD Legislation? IFAC-PapersOnLine 51 111 118 2018 https://doi.org/10.1016/j.ifacol.2018.10.021
- Maurya , R.K. 2017
- Isermann , R. Engine Modeling and Control 2014 https://doi.org/10.1007/978-3-642-39934-3
- Kakoee , A. , Bakhshan , Y. , Barbier , A. , Bares , P. , and Guardiola , C. Modeling Combustion Timing in an RCCI Engine by Means of a Control Oriented Model Control Eng Pract 97 104321 2020 https://doi.org/10.1016/j.conengprac.2020.104321
- Khodadadi Sadabadi , K. , Shahbakhti , M. , Bharath , A.N. , and Reitz , R.D. Modeling of Combustion Phasing of a Reactivity-Controlled Compression Ignition Engine for Control Applications Int J Engine Res 17 421 435 2016 https://doi.org/10.1177/1468087415583773
- Bekdemir , C. , Baert , R. , Willems , F. , and Somers , B. Towards Control-Oriented Modeling of Natural Gas-Diesel RCCI Combustion SAE Tech Pap. 2015 https://doi.org/10.4271/2015-01-1745
- Guardiola , C. , Pla , B. , Bares , P. , and Barbier , A. A Combustion Phasing Control-Oriented Model Applied to an RCCI Engine IFAC-PapersOnLine 51 119 124 2018 https://doi.org/10.1016/j.ifacol.2018.10.022
- Raut , A. , Irdmousa , B.K. , and Shahbakhti , M. Dynamic Modeling and Model Predictive Control of an RCCI Engine Control Eng Pract 81 129 144 2018 https://doi.org/10.1016/j.conengprac.2018.09.004
- Indrajuana , A. , Bekdemir , C. , Feru , E. , and Willems , F. Towards Model-Based Control of RCCI-CDF Mode-Switching in Dual Fuel Engines SAE Tech Pap. 2018 https://doi.org/10.4271/2018-01-0263
- Kondipati , N.N.T. , Arora , J.K. , Bidarvatan , M. , Shahbakhti , M. Modeling, Design and Implementation of a Closed-Loop Combustion Controller for an RCCI Engine Proc. Am. Control Conf 2017 https://doi.org/10.23919/ACC.2017.7963689
- Arora , J.K. , and Shahbakhti , M. Real-Time Closed-Loop Control of a Light-Duty RCCI Engine during Transient Operations SAE Tech Pap. 2017 https://doi.org/10.4271/2017-01-0767
- Fathi , M. , Jahanian , O. , and Shahbakhti , M. Modeling and Controller Design Architecture for Cycle-By-Cycle Combustion Control of Homogeneous Charge Compression Ignition (HCCI) Engines - A Comprehensive Review Energy Convers Manag 139 1 19 2017 https://doi.org/10.1016/j.enconman.2017.02.038
- Janakiraman , V.M. , Nguyen , X.L. , and Assanis , D. An ELM Based Predictive Control Method for HCCI Engines Eng Appl Artif Intell 48 106 118 2016 https://doi.org/10.1016/j.engappai.2015.10.007
- Bahri , B. , Shahbakhti , M. , and Aziz , A.A. Real-Time Modeling of Ringing in HCCI Engines Using Artificial Neural Networks Energy 125 509 518 2017 https://doi.org/10.1016/j.energy.2017.02.137
- Choi , Y. , and Chen , J.Y. Fast Prediction of Start-of-Combustion in HCCI with Combined Artificial Neural Networks and Ignition Delay Model Proc Combust Inst 30 II 2711 2718 2005 https://doi.org/10.1016/j.proci.2004.08.143
- Mirhassani , M. , Chen , X. , Tahmasebi , A. , and Ahmadi , M. On Control of HCCI Combustion-Neural Network Approach Proc. IEEE Int. Conf Control Appl. 2006 https://doi.org/10.1109/CACSD-CCA-ISIC.2006.4776892
- Janakiraman , V.M. , Nguyen , X.L. , Sterniak , J. , and Assanis , D. A System Identification Framework for Modeling Complex Combustion Dynamics Using Support Vector Machines Lect. Notes Electr. Eng. 2014 https://doi.org/10.1007/978-3-319-03500-0_19
- Wong , P.K. , Wong , K.I. , Vong , C.M. , and Cheung , C.S. Modeling and Optimization of Biodiesel Engine Performance Using Kernel-Based Extreme Learning Machine and Cuckoo Search Renew Energy 2015 https://doi.org/10.1016/j.renene.2014.08.075
- Azad , A.K. , Rasul , M.G. , Khan , M.M.K. , Sharma , S.C. , and Bhuiya , M.M.K. Recent Development of Biodiesel Combustion Strategies and Modelling for Compression Ignition Engines Renew Sustain Energy Rev 56 1068 1086 2016 https://doi.org/10.1016/j.rser.2015.12.024
- Wong , P.K. , Zhong , J. , Yang , Z. , and Vong , C.M. Sparse Bayesian Extreme Learning Committee Machine for Engine Simultaneous Fault Diagnosis Neurocomputing 2016 https://doi.org/10.1016/j.neucom.2015.02.097
- Livengood , J.C. , and Wu , P.C. Correlation of Autoignition Phenomena in Internal Combustion Engines and Rapid Compression Machines Symp Combust 5 347 356 1955 https://doi.org/10.1016/S0082-0784(55)80047-1
- Valecha , P. , Mishra , C. , Subbarao , P. , and Das , P. Development of Improved Thermodynamic Model Using Cylinder Blow by and Double-Wiebe Functions for High Speed Diesel Engine SAE Tech. Pap. Ser. 2018 https://doi.org/10.4271/2018-01-0244
- Mishra , C. , Subbarao , P.M.V. Experimental Investigation and Thermodynamic Modelling of an RCCI Engine with Gasoline and Ethanol as Pilot Fuels ASME 2019 Intern. Combust. Engine Div. Fall Tech. Conf. ICEF 2019 2020 https://doi.org/10.1115/ICEF2019-7274
- Zhou , A. , Dong , T. , and Akih-Kumgeh , B. Simplifying Ignition Delay Prediction for Homogeneous Charge Compression Ignition Engine Design and Control Int J Engine Res 17 957 968 2016 https://doi.org/10.1177/1468087416630882
- Livengood , J.C. , and Wu , P.C. Correlation of Autoignition Phenomena in Internal Combustion Proc 5th Intarnational Symp Combusit 5 347 356 1953
- Namar , M.M. , and Jahanian , O. A Simple Algebraic Model for Predicting HCCI Auto-Ignition Timing According to Control Oriented Models Requirements Energy Convers Manag 154 38 45 2017 https://doi.org/10.1016/j.enconman.2017.10.056
- Pan , J. , Zhao , P. , Law , C.K. , and Wei , H. A Predictive Livengood-Wu Correlation for Two-Stage Ignition Int J Engine Res 17 825 835 2016 https://doi.org/10.1177/1468087415619516
- Javed , T. , Lee , C. , AlAbbad , M. , Djebbi , K. et al. Ignition Studies of n-Heptane/Iso-Octane/Toluene Blends Combust Flame 171 223 233 2016 https://doi.org/10.1016/j.combustflame.2016.06.008
- Bengtsson , J. , Strandh , P. , Johansson , R. , Tunestål , P. , and Johansson , B. Hybrid Modelling of Homogeneous Charge Compression Ignition (HCCI) Engine Dynamics - A Survey Int J Control 2007 https://doi.org/10.1080/00207170701484869
- Yildiz , M. , and Albayrak Çeper , B. Zero-Dimensional Single Zone Engine Modeling of an SI Engine Fuelled with Methane and Methane-Hydrogen Blend Using Single and Double Wiebe Function: A Comparative Study Int J Hydrogen Energy 1 10 2017 https://doi.org/10.1016/j.ijhydene.2017.07.016
- Miyoshi , A. Kinetics of Autoignition: A Simple Intuitive Interpretation and Its Relation to the Livengood-Wu Integral Phys Chem Chem Phys 20 10762 10769 2018 https://doi.org/10.1039/c7cp07736j
- Larimore , J. , Hellström , E. , Jade , S. , Stefanopoulou , A.G. , and Jiang , L. Real-Time Internal Residual Mass Estimation for Combustion with High Cyclic Variability Int J Engine Res 16 474 484 2015 https://doi.org/10.1177/1468087414552616
- Fitzgerald , R.P. , Steeper , R. , Snyder , J. , Hanson , R. , and Hessel , R. Determination of Cycle Temperatures and Residual Gas Fraction for HCCI Negative Valve Overlap Operation SAE Tech Pap. 2010 https://doi.org/10.4271/2010-01-0343
- Hellström , E. , Stefanopoulou , A. , Vavra , J. , Babajimopoulos , A. et al. Understanding the Dynamic Evolution of Cyclic Variability at the Operating Limits of HCCI Engines with Negative Valve Overlap SAE Int J Engines 2012 https://doi.org/10.4271/2012-01-1106
- Belman-Flores , J.M. , Ledesma , S.E. , Garcia , M.G. , Ruiz , J. , and Rodríguez-Muñoz , J.L. Analysis of a Variable Speed Vapor Compression System Using Artificial Neural Networks Expert Syst Appl 2013 https://doi.org/10.1016/j.eswa.2013.01.015
- Hecht-Nielsen , R. Kolmogorov’s Mapping Neural Network Existence Theorem 1987