This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Prediction of Autoignition and Flame Properties for Multicomponent Fuels Using Machine Learning Techniques
Technical Paper
2019-01-1049
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
Machine learning methods, such as decision trees and deep neural networks, are becoming increasingly important and useful for data analysis in various scientific fields including dynamics and control, signal processing, pattern recognition, fluid mechanics, and chemical synthesis, etc. For future engine design and performance optimization, there is an urgent need for a robust predictive model which could capture the major combustion properties such as autoignition and flame propagation of multicomponent fuels under a wide range of engine operating conditions, without massive experimental measurement or computational efforts. It will be shown that these long-held limitations and challenges related to complex fuel combustion and engine research could be readily solved by implementing machine learning methods. In this paper, both random forest and deep neural network algorithms were implemented to predict ignition delay times, flame speeds, octane ratings, and CA50 values (crank angle corresponding to 50% of the heat release rate) in homogenous charge compression ignition (HCCI) engines for multicomponent gasoline surrogates. Various training models were first tested to optimize CPU efficiency while maximizing accuracy and reducing error, and then different machine learning models were tested on their ability to predict outputs based on conditions not included in the training set. Although differences in random forest and deep neural networks are noted in the training-prediction process, it is found that both random forests and deep neural networks exhibit good ability to predict results accurately with small training effort, by comparing with data extracted from simulations and previous models. For flame propagation, both methods predict flame speed values more accurately than a proposed empirical model in the literature. We have therefore demonstrated the usefulness and great potential of these machine learning methods to assist engine combustion prediction and control.
Recommended Content
Authors
Citation
Shah, N., Zhao, P., DelVescovo, D., and Ge, H., "Prediction of Autoignition and Flame Properties for Multicomponent Fuels Using Machine Learning Techniques," SAE Technical Paper 2019-01-1049, 2019, https://doi.org/10.4271/2019-01-1049.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 |
Also In
References
- Russell , S.J. and Norvig , P. Artificial Intelligence: A Modern Approach Third Upper Saddle River, NJ Prentice Hall 2010
- Lam , S.H. An Efficient Implementation of Computational Singular Perturbation Combustion Science and Technology 190 157 163 2018 10.1080/00102202.2017.1379512
- Law , C.K. Combustion Physics Cambridge University Press 2006 10.1017/CBO9780511754517
- Zhao , P. and Law , C.K. The Role of Global and Detailed Kinetics in the First-Stage Ignition Delay in NTC-Affected Phenomena Combustion and Flame 160 11 2352 2358 2013 10.1016/j.combustflame.2013.06.009
- Jalan , A. , Alecu , I.M. , Meana-Pañeda , R. , Aguilera-Iparraguirre , J. et al. New Pathways for Formation of Acids and Carbonyl Products in Low-Temperature Oxidation: The Korcek Decomposition of γ-Ketohydroperoxides Journal of American Chemistry Society 135 30 11100 11114 2013 10.1021/ja4034439
- Ahneman , D.T. , Estrada , J.G. , Lin , S.S. , Dreher , S.D. et al. Predicting Reaction Performance in C-N Cross-Coupling Using Machine Learning Science 360 6385 186 190 2018 10.1126/science.aar5169
- Xu , S.X. and Chen , L. A Novel Approach for Determining the Optimal Number of Hidden Layer Neurons for FNN’s and Its Application in Data Mining The 5th International Conference on Information Technology and Applications (ICITA 2008) 2008
- Ahmad , M.W. , Mourshed , M. , and Rezgui , Y. Trees Vs Neurons: Comparison between Random Forest and ANN for High-Resolution Prediction of Building Energy Consumption Energy and Buildings 147 77 89 2017 10.1016/j.enbuild.2017.04.038
- D'Adamo , A. , Del Pecchia , M. , Breda , S. , Berni , F. et al. Chemistry-Based Laminar Flame Speed Correlations for a Wide Range of Engine Conditions for Iso-Octane, N-Heptane, Toluene and Gasoline Surrogate Fuels SAE Technical Paper 2017-01-2190 2017 10.4271/2017-01-2190
- Westbrook , C.K. , Sjöberg , M. , and Cernansky , N. A New Chemical Kinetic Method of Determining RON and MON Values for Single Component and Multicomponent Engine Fuels Combustion and Flame 195 50 62 2018 10.1016/j.combustflame.2018.03.038
- 2013
- 2014
- Kalghatgi , G. , Babiker , H. , and Badra , J. A Simple Method to Predict Knock Using Toluene, N-Heptane and Iso-Octane Blends (TPRF) as Gasoline Surrogates SAE International Journal of Engines 8 2 505 519 2015 10.4271/2015-01-0757
- Badra , J. , Bokhumseen , N. , Mulla , N. , Sarathy , S. et al. A Methodology to Relate Octane Numbers of Binary and Ternary N-Heptane, Iso-Octane and Toluene Mixtures with Simulated Ignition Delay Times Fuel 160 458 469 2015 10.1016/j.fuel.2015.08.007
- Morgan , N. , Smallbone , A. , Bhave , A. , Kraft , M. et al. Mapping Surrogate Gasoline Compositions into RON/MON Space Combustion and Flame 157 6 1122 1131 2010 10.1016/j.combustflame.2010.02.003
- Kalghatgi , G. , Snowdon , P. , and McDonald , C. Studies of Knock in a Spark Ignition Engine with “CARS” Temperature Measurements and Using Different Fuels SAE Technical Paper 950690 1995 10.4271/950690
- Kalghatgi , G. and Head , R. The Available and Required Autoignition Quality of Gasoline-like Fuels in HCCI Engines at High Temperatures SAE Technical Paper 2004-01-1969 2004 10.4271/2004-01-1969
- Knop , V. , Loos , M. , Pera , C. , and Jeuland , N. A Linear-by-Mole Blending Rule for Octane Numbers of N-Heptane/Iso-Octane/Toluene Mixtures Fuel 115 666 673 2014 10.1016/j.fuel.2013.07.093
- Foong , T. , Morganti , K. , Brear , M. , Da Silva , G. et al. The Octane Numbers of Ethanol Blended with Gasoline and Its Surrogates Fuel 115 727 739 2014 10.1016/j.fuel.2013.07.105
- Yuan , H. , Yang , Y. , Brear , M. , Foong , T.M. et al. Optimal Octane Number Correlations for Mixtures of Toluene Reference Fuels (TRFs) and Ethanol Fuel 188 408 417 2017 10.1016/j.fuel.2016.10.042
- Andrae , J.C.G. Comprehensive Chemical Kinetic Modeling of Toluene Reference Fuels Oxidation Fuel 107 740 748 2013 10.1016/j.fuel.2013.01.070
- Tao , M.Y. , Wu , T. , Ge , H.W. , DelVescovo , D. et al. A Kinetic Modeling Study on Octane Rating and Fuel Sensitivity in Advanced Compression Ignition Engines Combustion and Flame 185 234 244 2017 10.1016/j.combustflame.2017.07.020
- Tao , M.Y. , Zhao , P. , DelVescovo , D. , and Ge , H.W. Manifestation of Octane Rating, Fuel Sensitivity and Composition Effects of Gasoline Surrogates under Advanced Compression Ignition Conditions Combustion and Flame 192 238 249 2018 10.1016/j.combustflame.2018.02.015