This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Artificial Neural Networks for In-Cycle Prediction of Knock Events
Technical Paper
2022-01-0478
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Downsized turbocharged engines have been increasingly popular in modern light-duty vehicles due to their fuel efficiency benefits. However, high power density in such engines is achieved thanks to high in-cylinder pressure and temperature conditions that increase knock propensity. Next-cycle control has been studied as a method to reduce the damaging effects of knock by operating the engine in a low knock probability condition. This exploratory study looks at the feasibility of in-cycle knock prediction as a tool for advanced knock control algorithms. A methodology is proposed to 1) choose in-cycle features of the pressure trace that highly correlate with knock events and 2) train artificial neural networks to predict in-cycle knock events before knock onset. The methodology was validated at different operating conditions and different levels of generalization. Precision and recall were used as metrics to evaluate the binary classifier. However, the Fowlkes-Mallows (FM) index was used to compare the result of the clustering algorithm at different operating conditions. The results showed a maximum FM index of 0.7 when the prediction was done at knock onset and a minimum FM index of 0.45 when the prediction was done at spark timing.
Recommended Content
Technical Paper | Shape Optimization of a Single Cylinder Engine Crankshaft |
Technical Paper | Turbocharging the DI Gasoline Engine |
Technical Paper | Advances in Waste Heat Recovery Systems for Gas Engines |
Authors
Citation
Maldonado, B., Kaul, B., and Szybist, J., "Artificial Neural Networks for In-Cycle Prediction of Knock Events," SAE Technical Paper 2022-01-0478, 2022, https://doi.org/10.4271/2022-01-0478.Also In
References
- Heywood , J.B. Internal Combuation Engine Fundamentals New York McGraw-Hill Education 2018
- Zhen , X. , Wang , Y. , Xu , S. , Zhu , Y. et al. The Engine Knock Analysis - An Overview Applied Energy 92 2012 628 636 10.1016/j.apenergy.2011.11.079
- D'Adamo , A. , Breda , S. , Fontanesi , S. , and Cantore , G. A RANS-Based CFD Model to Predict the Statistical Occurrence of Knock in Spark-Ignition Engines SAE International Journal of Engines 9 1 2016 618 630 10.4271/2016-01-0581
- Yue , Z. , Xu , C. , Som , S. , Sluder , C.S. et al. A Transported Livengood-Wu Integral Model for Knock Prediction in Computational Fluid Dynamics Simulation Journal of Engineering for Gas Turbines and Power 143 9 2021 10.1115/1.4050583
- Zembi , J. , Battistoni , M. , Ranuzzi , F. , Cavina , N. et al. CFD Analysis of Port Water Injection in a GDI Engine under Incipient Knock Conditions Energies (Basel) 12 18 2019 3409 10.3390/en12183409
- Kosmadakis , G. , Rakopoulos , D. , Arroyo , J. , Moreno , F. et al. CFD-based Method with an Improved Ignition Model for Estimating Cyclic Variability in a Spark-ignition Engine Fueled with Methane Energy Conversion and Management 174 2018 769 778 10.1016/j.enconman.2018.08.093
- Dulbecco , A. , Richard , S. , and Angelberger , C. Investigation on the Potential of Quantitatively Predicting CCV in DI-SI Engines by Using a One-Dimensional CFD Physical Modeling Approach SAE International Journal of Engines 8 5 2015 2012 2028 10.4271/2015-24-2401
- Kassa , M. , Hall , C. , Pamminger , M. , and Wallner , T. Knock Intensity Distribution and a Stochastic Control Framework for Knock Control Journal of Dynamic Systems, Measurement, and Control 141 11 2019 10.1115/1.4044437
- Thomasson , A. , Shi , H. , Lindell , T. , Eriksson , L. et al. Experimental Validation of a Likelihood-Based Stochastic Knock Controller IEEE Transactions on Control Systems Technology 24 4 2016 1407 1418 10.1109/TCST.2015.2483566
- Selmanaj , D. , Panzani , G. , Dooren , S.V. , Rosgren , J. et al. Adaptive and Unconventional Strategies for Engine Knock Control IEEE Transactions on Control Systems Technology 27 4 2019 1838 1845 10.1109/TCST.2018.2827898
- Pla , B. , Bares , P. , Jimenez , I. , Guardiola , C. et al. A Fuzzy Logic Map-based Knock Control for Spark Ignition Engines Applied Energy 280 2020 10.1016/j.apenergy.2020.116036
- Shayestehmanesh , S. and Jones , J.P. Stochastic Modeling and Prediction of IMEP for Closed Loop Knock Control Performance Assessment Control Engineering Practice 92 2019 104130 10.1016/j.conengprac.2019.104130
- Peyton Jones , J.C. , Spelina , J.M. , and Frey , J. Likelihood-Based Control of Engine Knock IEEE Transactions on Control Systems Technology 21 6 2013 2169 2180 10.1109/TCST.2012.2229280
- Peyton Jones , J.C. , Shayestehmanesh , S. , and Frey , J. A Bayesian Knock Event Controller IEEE Transactions on Control Systems Technology 28 5 2020 1627 1637 10.1109/TCST.2019.2916735
- Zhao , K. , Wu , Y. , and Shen , T. Beta-Distribution-Based Knock Probability Estimation, Control Scheme, and Experimental Validation for SI Engines IEEE Transactions on Control Systems Technology 29 2 2021 918 925 10.1109/TCST.2020.2980799
- Aliramezani , M. , Koch , C.R. , and Shahbakhti , M. Modeling, Diagnostics, Optimization, and Control of Internal Combustion Engines via Modern Machine Learning Techniques: A Review and Future Directions Progress in Energy and Combustion Science 88 2022 100967 10.1016/j.pecs.2021.100967
- Maldonado , B.P. , Kaul , B.C. , Schuman , C.D. , Young , S.R. et al. Dilute Combustion Control Using Spiking Neural Networks SAE Technical Paper 2021-01-0534 2021 https://doi.org/10.4271/2021-01-0534
- Gharehghani , A. , Abbasi , H.R. , and Alizadeh , P. Application of Machine Learning Tools for Constrained Multi-objective Optimization of an HCCI Engine Energy (Oxford) 233 2021 121106 10.1016/j.energy.2021.121106
- Hu , S. , d’Ambrosio , Finesso , R. , Manelli , A. et al. Comparison of Physics-Based, Semi-empirical and Neural Network-based Models for Model-based Combustion Control in a 3.0 L Diesel Engine Energies (Basel) 12 18 2019 3423 10.3390/en12183423
- Lee , S. , Lee , Y. , Lee , Y. , Shin , S. et al. Proposal of a Methodology for Designing Engine Operating Variables Using Predicted NOx Emissions Based on Deep Neural Networks Journal of Mechanical Science and Technology 35 4 2021 1747 1756 10.1007/s12206-021-0337-2
- Ortmann , S. , Rychetsky , M. , Glesner , M. , Groppo , R. et al. Engine Knock Estimation Using Neural Networks Based on a Real-World Database SAE Technical Paper 980513 1998 https://doi.org/10.4271/980513
- Rychetsky , M. , Ortmann , S. , and Glesne , M. Support Vector Approaches for Engine Knock Detection International Joint Conference on Neural Networks 1999 10.1109/IJCNN.1999.831085
- Kefalas , A. , Ofner , A.B. , Pirker , G. , Posch , S. et al. Detection of Knocking Combustion Using the Continuous Wavelet Transformation and a Convolutional Neural Network Energies 14 2 2021 439 10.3390/en14020439
- Maldonado , B. , Stefanopoulou , A. , and Kaul , B. Chapter 8 - Artificial-Intelligence-Based Prediction and Control of Combustion Instabilities in Spark-Ignition Engines Artificial Intelligence and Data Driven Optimization of Internal Combustion Engines Elsevier 2022 185 212 10.1016/B978-0-323-88457-0.00006-0
- Szybist , J. Knock Mitigation Effectiveness of EGR across the Pressure-Temperature Domain SAE Int. J. Adv. & Curr. Prac. in Mobility 3 1 2020 262 275 https://doi.org/10.4271/2020-01-2053
- Caton , J. A Comparison of Lean Operation and Exhaust Gas Recirculation: Thermodynamic Reasons for the Increases of Efficiency SAE Technical Paper 2013-01-0266 2013 https://doi.org/10.4271/2013-01-0266
- Duchaussoy , Y. , Lefebvre , A. , and Bonetto , R. Dilution Interest on Turbocharged SI Engine Combustion SAE Technical Paper 2003-01-0629 2003 https://doi.org/10.4271/2003-01-0629
- Grandin , B. and Angstrom , H. Replacing Fuel Enrichment in a Turbo Charged SI Engine: Lean Burn or Cooled EGR SAE Technical Paper 1999-01-3505 1999 https://doi.org/10.4271/1999-01-3505
- Szybist , J. , Wagnon , S. , Splitter , D. , Pitz , W. et al. The Reduced Effectiveness of EGR to Mitigate Knock at High Loads in Boosted SI Engines SAE Int. J. Engines 10 5 2017 2305 2318 https://doi.org/10.4271/2017-24-0061
- Alger , T. , Mangold , B. , Roberts , C. , and Gingrich , J. The Interaction of Fuel Anti-Knock Index and Cooled EGR on Engine Performance and Efficiency SAE Int J Engines 5 3 2012 1229 1241 https://doi.org/10.4271/2012-01-1149
- Diana , S. , Giglio , V. , Iorio , B. , and Police , G. Evaluation of the Effect of EGR on Engine Knock SAE Technical Paper 982479 1998 https://doi.org/10.4271/982479
- Grandin , B. , Angstrom , H. , Stalhammar , P. , and Olofsson , E. Knock Suppression in a Turbocharged SI Engine by Using Cooled EGR SAE Technical Paper 982476 1998 https://doi.org/10.4271/982476
- Maldonado , B. , Stefanopoulou , A. , Scarcelli , R. , and Som , S. Characteristics of Cycle-to-Cycle Combustion Variability at Partial-Burn Limited and Misfire Limited Spark Timing Under Highly Diluted Conditions ASME 2019 Internal Combustion Engine Division Fall Technical Conference Chicago, Illinois, USA 2019 10.1115/ICEF2019-7256
- Maldonado , B.P. , Zaseck , K. , Kitagawa , E. , and Stefanopoulou , A.G. Closed-Loop Control of Combustion Initiation and Combustion Duration IEEE Transactions on Control Systems Technology 28 3 2020 936 950 10.1109/TCST.2019.2898849
- Maldonado , B.P. and Stefanopoulou , A.G. Non-Equiprobable Statistical Analysis of Misfires and Partial Burns for Cycle-to-Cycle Control of Combustion Variability ASME 2018 Internal Combustion Engine Division Fall Technical Conference San Diego, California, USA 2018 10.1115/ICEF2018-9540
- Prikhodko , V.Y. , Parks , J.E. , Pihl , J.A. , and Toops , T.J. Ammonia Generation Over TWC for Passive SCR NOx Control for Lean Gasoline Engines SAE Technical Paper 2014-01-1505 2014 https://doi.org/10.4271/2014-01-1505
- Yun , H. and Mirsky , W. Schlieren-Streak Measurements of Instantaneous Exhaust Gas Velocities from a Spark-Ignition Engine SAE Technical Paper 741015 1974 https://doi.org/10.4271/741015
- Maldonado , B.P. and Stefanopoulou , A.G. Linear Stochastic Modeling and Control of Diluted Combustion for SI Engines IFAC-PapersOnLine 51 31 2018 99 104 10.1016/j.ifacol.2018.10.019
- Naber , J.D. , Blough , J.R. , Frankowski , D. , Goble , M. et al. Analysis of Combustion Knock Metrics in Spark-Ignition Engines SAE Transactions 115 2006 223 243 https://doi.org/10.4271/2006-01-0400
- McKenzie , J. and Cheng , W.K. The Anatomy of Knock SAE Technical Paper 2016-01-0704 2016 https://doi.org/10.4271/2016-01-0704
- Peyton Jones , J.C. , Shayestehmanesh , S. , and Frey , J. Parametric Modelling of Knock Intensity Data Using a Dual Log-Normal Model International Journal of Engine Research 21 6 2020 1026 1036 10.1177/1468087418796335
- Spelina , J.M. , Peyton Jones , J.C. , and Frey , J. Characterization of Knock Intensity Distributions: Part 1: Statistical Independence and Scalar Measures Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 228 2 2014 117 128 10.1177/0954407013496233
- Peyton Jones , J.C. and Shayestehmanesh , S. The Statistical Properties of Raw Knock Signal Time Histories Mechanical Systems and Signal Processing 156 2021 107660 10.1016/j.ymssp.2021.107660
- Finney , C.E. , Kaul , B.C. , Daw , S. , Wagner , R.M. et al. Invited Review: A Review of Deterministic Effects in Cyclic Variability of Internal Combustion Engines International Journal of Engine Research 16 3 2015 366 378 10.1177/1468087415572033
- Maldonado , B.P. and Kaul , B.C. Evaluation of Residual Gas Fraction Estimation Methods for Cycle-to-Cycle Combustion Variability Analysis and Modeling International Journal of Engine Research 2021 10.1177/1468087420983087
- Maldonado , B.P. and Kaul , B.C. Control-Oriented Modeling of Cycle-to-Cycle Combustion Variability at the Misfire Limit in SI Engines Proceedings of the ASME 2020 Dynamic Systems and Control Conference 2020 10.1115/DSCC2020-3255
- Ghandhi , J. and Kim , K.S. A statistical description of knock intensity and its prediction SAE Technical Paper 2017-01-0659 2017 https://doi.org/10.4271/2017-01-0659
- Fowlkes , E.B. and Mallows , C.L. A Method for Comparing Two Hierarchical Clusterings Journal of the American Statistical Association 78 383 1983 553 569 10.1080/01621459.1983.10478008
- Luo , Y. , Liu , S. , Adair , D. , Maldonado , B. et al. Portable In-Cylinder Pressure Measurement and Signal Processing System for Real-Time Combustion Analysis and Engine Control SAE Int. J. Adv. & Curr. Prac. in Mobility 2 6 2020 3432 3441 https://doi.org/10.4271/2020-01-1144
- Yang , F. , Wang , J. , Gao , G. , and Ouyang , M. In-Cycle Diesel Low Temperature Combustion Control Based on SOC Detection Applied Energy 136 C 2014 77 88 10.1016/j.apenergy.2014.09.014
- Jorques Moreno , C. , Stenlaas , O. , and Tunestal , P. Predictive In-Cycle Closed-Loop Combustion Control with Pilot-Main Injections IFAC-PapersOnLine 53 2 2020 14000 14007 10.1016/j.ifacol.2020.12.920
- Schuman , C.D. , Young , S.R. , Mitchell , J.P. , Johnston , J.T. , et al. Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency 2020 11th International Green and Sustainable Computing Workshops (IGSC) 2020 10.1109/IGSC51522.2020.9291228
- Schuman , C.D. , Young , S.R. , Maldonado , B.P. , and Kaul , B.C. Real-Time Evolution and Deployment of Neuromorphic Computing at The Edge 12th International Green and Sustainable Computing Conference (IGSC) 2021 10.1109/IGSC54211.2021.9651607
- Lian , H. , Martz , J.B. , Maldonado , B.P. , Stefanopoulou , A.G. et al. Prediction of Flame Burning Velocity at Early Flame Development Time With High Exhaust Gas Recirculation and Spark Advance J. Eng. Gas Turbines Power 139 8 2017 082801 10.1115/1.4035849
- Zhao , K. , Wu , Y. , and Shen , T. Stochastic Knock Control with Beta Distribution Learning for Gasoline Engines IFAC-PapersOnLine 51 31 2018 125 130 10.1016/j.ifacol.2018.10.023
- Turner , J. , Popplewell , A. , Patel , R. , Johnson , T. et al. Ultra Boost for Economy: Extending the Limits of Extreme Engine Downsizing SAE Int. J. Engines 7 1 2014 387 417 https://doi.org/10.4271/2014-01-1185