This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Predicting Distillation Properties of Gasoline Fuel Blends using Machine Learning
Technical Paper
2022-01-1086
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Distillation properties of gasoline are regulated to ensure the safe and efficient operation of SI-engines. Blending various gasoline components affects the distillation values in a non-linear fashion, making the prediction of these properties challenging. Furthermore, the rise of renewable components necessitates the development of new property prediction methods. In this work, a variety of Machine Learning models were created to predict the distillation points of gasoline blends based on the blending recipe. As input data, real industrial data from a refinery was used together with data from blends created for R&D purposes. The predicted properties were the evaporated volume at the 70 and 100 °C distillation points (E70 and E100). Altogether four different machine learning models were trained, cross-validated and tested using seven different pre-processing methods. It was found that Support Vector Regression (SVR) was the most effective at predicting the distillation points. It achieved a mean absolute error (MAE) of 1.5 and 1.1 respectively for E70 and E100, compared to a widely used linear model which had MAEs of 12.2 and 3.27. These findings underline that the SVR model was substantially more effective. In addition, the SVR model maintained its performance when used on oxygenated blends for which the linear model was highly inaccurate. It was also found that higher distillation points behave more linearly and therefore there’s less need for complex non-linear models near the higher end of the distillation curve. The methodology presented in this work can be further used to predict other distillation points or fuel properties.
Authors
Citation
Lamberg, A., Toldy, A., Keskiväli, J., Karvo, A. et al., "Predicting Distillation Properties of Gasoline Fuel Blends using Machine Learning," SAE Technical Paper 2022-01-1086, 2022, https://doi.org/10.4271/2022-01-1086.Also In
References
- Christensen , E. , Yanowitz , J. , Ratcliff , M. , and McCormick , R.L. Renewable Oxygenate Blending Effects on Gasoline Properties Energy & Fuels 25 10 Sep. 2011 4723 4733 10.1021/ef2010089
- Babazadeh Shayan , S. , Seyedpour , S.M. , and Ommi , F. Effect of Oxygenates Blending with Gasoline to Improve Fuel Properties Chinese Journal of Mechanical Engineering 25 4 2012 792 797 10.3901/CJME.2012.04.792
- Bruno , T.J. , Wolk , A. , and Naydich , A. Composition-Explicit Distillation Curves for Mixtures of Gasoline with Four-Carbon Alcohols (Butanols) Energy & Fuels 23 4 2009 2295 2306
- https://www.concawe.eu/wp-content/uploads/2017/01/rpt_04-3-2004-01204-01-e.pdf
- Ahmed , A.A. , El-Masry , A.M. , and Barakat , Y. Azeotrope Formation in Gasoline-Ethanol Blends. Part 1 - Impact of Nonionic on E10 Distillation Curve Egyptian Journal of Petroleum 27 4 Dec. 2018 1167 1175 10.1016/J.EJPE.2018.04.006
- Schweidtmann , A.M. , Rittig , J.G. , König , A. , Grohe , M. et al. Graph Neural Networks for Prediction of Fuel Ignition Quality Energy and Fuels 34 9 2020 11395 11407 10.1021/acs.energyfuels.0c01533
- Kubic , W.L. , Jenkins , R.W. , Moore , C.M. , Semelsberger , T.A. et al. Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds Industrial & Engineering Chemistry Research 56 42 Oct. 2017 12236 12245 10.1021/acs.iecr.7b02753
- Li , R. , Herreros , J.M. , Tsolakis , A. , and Yang , W. Machine Learning Regression based Group Contribution Method for Cetane and Octane Numbers Prediction of Pure Fuel Compounds and Mixtures Fuel 280 Nov. 2020 118589 10.1016/J.FUEL.2020.118589
- vom Lehn , F. , Cai , L. , Tripathi , R. , Broda , R. et al. A Property Database of Fuel Compounds with Emphasis on Spark-Ignition Engine Applications Applications in Energy and Combustion Science 5 100018 Mar. 2021 10.1016/J.JAECS.2020.100018
- Jameel , A.G.A. , van Oudenhoven , V. , Emwas , A.-H. , and Sarathy , S.M. Predicting Octane Number Using Nuclear Magnetic Resonance Spectroscopy and Artificial Neural Networks Energy & Fuels 32 5 6309 6329 Apr. 2018 10.1021/acs.energyfuels.8b00556
- Alves , J.C. , Henriques , C. , and Poppi , R. Determination of Diesel Quality Parameters using Support Vector Regression and Near Infrared Spectroscopy for an In-Line Blending Optimizer System Fuel 97 2012 710 717 10.1016/j.fuel.2012.03.016
- Filgueiras , P. , Terra , L. , Castro , E. , Oliveira , L. et al. Prediction of the Distillation Temperatures of Crude Oils using 1H NMR and Support Vector Regression with Estimated Confidence Intervals Talanta 142 2015 10.1016/j.talanta.2015.04.046
- Pasadakis , N. , Sourligas , S. , and Foteinopoulos , C. Prediction of the Distillation Profile and Cold Properties of Diesel Fuels using Mid-IR Spectroscopy and Neural Networks Fuel 85 7-8 May 2006 1131 1137 10.1016/J.FUEL.2005.09.016
- de Godoy , L.A.F. , Pedroso , M.P. , Ferreira , E.C. , Augusto , F. et al. Prediction of the Physicochemical Properties of Gasoline by Comprehensive Two-Dimensional Gas Chromatography and Multivariate Data Processing Journal of Chromatography A 1218 12 1663 1667 Mar. 2011 10.1016/J.CHROMA.2011.01.056
- Pasadakis , N. , Gaganis , V. , and Foteinopoulos , C. Octane Number Prediction for Gasoline Blends Fuel Processing Technology 87 6 Jun. 2006 505 509 10.1016/J.FUPROC.2005.11.006
- Murty , B.S.N. and Rao , R.N. Global Optimization for Prediction of Blend Composition of Gasolines of Desired Octane Number and Properties Fuel Processing Technology 85 14 Sep. 2004 1595 1602 10.1016/J.FUPROC.2003.08.004
- Correa Gonzalez , S. et al. Prediction of Gasoline Blend Ignition Characteristics Using Machine Learning Models Energy and Fuels 35 11 2021 10.1021/acs.energyfuels.1c00749
- Alboqami , F. et al. A Methodology for Designing Octane Number of Fuels using Genetic Algorithms and Artificial Neural Networks Energy & Fuels 36 7 Mar. 2022 3867 3880 10.1021/acs.energyfuels.1c04052
- Zahed AH , M.D. , Mullah , S.A. , and Bashir Predict Octane Number for Gasoline Blends Hydrocarbon Processing 72 1993 5
- Pedregosa , F. et al. Scikit-Learn: Machine Learning in Python the Journal of machine Learning research 12 2011 2825 2830
- https://scikit-learn.org/stable/modules/generated/sklearn.impute.IterativeImputer.html
- Krstajic , D. , Buturovic , L.J. , Leahy , D.E. , and Thomas , S. Cross-Validation Pitfalls when Selecting and Assessing Regression and Classification Models Journal of Cheminformatics 6 1 2014 10 10.1186/1758-2946-6-10
- Fernández-Feal , M.M.d.C. 2017 10.5772/67140