Abstract
Latent heat of vaporization (LHvap) is a crucial property in internal combustion engines (ICEs). It affects the cylinder temperature (T), ignition delay, NOx emission and other phenomenon in ICEs. With the increase in global warming, use of alternative fuels in ICEs such as gasoline–ethanol blends, gasoline–methanol blends have become evident. Another important use of LHvap values is encountered while performing the spray combustion analysis of blended fuels using Computational Fluid Dynamics (CFD). This paper investigates the use of various Machine Learning (ML) techniques to predict the latent heat of vaporization (LHvap) for blended fuels. The algorithms used were Linear Regression (LR), Polynomial Regression (PR), Support Vector Machine (SVM), K Nearest Neighbors (KNN), Decision Tree (DT), and Random Forest (RF). The features used were Temperature, Blend Ratio, Molecular weight, Carbon (wt%), Hydrogen (wt%), and Oxygen (wt%). For training the algorithms, data was collected from several published research papers with LHvap values of gasoline-alcohol fuel blends and various diesel blends. The model was initially trained with data pertaining to gasoline-alcohol blends only, which showed that LR performed better than other algorithms in predicting both LHvap, with a coefficient of determination (R2 score) of 90% and Mean Absolute Percentage Error (MAPE) of 6.2%. This behavior was attributed to the linearity in the data, as most of the data points were of gasoline-alcohol blends with different blend ratios and temperatures. However, when more datapoints were included such as various oxygenated blends of diesel, it was found that RF performed much better than other algorithms, with an R2 score of 95.7% and MAPE of 6.8%. Furthermore, additional features were considered such as vol% of paraffins, aromatics, olefins, iso-paraffins, cyclo-paraffins, napthenes along with original features. The results showed that predictions improved with adding these features as the R2 score improved for all algorithms. It could be summarized that with availability of more data, the performance of RF algorithm could further improve. Thermodynamic relations have been attempted to correlate predictions of latent heat of vaporization with vapor pressure data of the blends.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Our world in data. https://ourworldindata.org/co2-and-greenhouse-gas-emissions. Access on 24 March 2023
T.M. Foong, K.J. Morganti, M.J. Brear, G. da Silva, Y. Yang, F.L. Dryer, The effect of charge cooling on the RON of ethanol/gasoline blends. SAE Int. J. Fuels Lubr. 6, 34–43 (2013)
R. Da Silva, R. Cataluna, E.W. de Menezes, D. Samios, C.M.S. Piatnicki, Effect of additives on the antiknock properties and Reid vapor pressure of gasoline. Fuel 84, 951–959 (2005)
S.A. Shirazi, B. Abdollahipoor, J. Martinson, B. Windom, T.D. Foust, K.F. Reardon, Effects of dual-alcohol gasoline blends on physiochemical properties and volatility behavior. Fuel 252, 542–552 (2019)
S. Feng, H. Zhou, H. Dong, Using deep neural network with small dataset to predict material defects. Mater. Des. 162, 300–310 (2019)
A. Alibakhshi, B. Hartke, Evaluation of the temperature dependence of vaporization enthalpy and its correlation with surface tension by machine learning and predictive correlations. ChemRxiv (2021)
R. Li, J.M. Herreros, A. Tsolakis, W. Yang, Machine learning-quantitative structure property relationship (ML-QSPR) method for fuel physicochemical properties prediction of multiple fuel types. Fuel 304, 121437 (2021)
Y. Zheng, M.S. Shadloo, H. Nasiri, A. Maleki, A. Karimipour, I. Tlili, Prediction of viscosity of biodiesel blends using various artificial model and comparison with empirical correlations. Renew. Energy 153, 1296–1306 (2020)
K.R. Bukkarapu, A. Krishnasamy, A critical review on available models to predict engine fuel properties of biodiesel. Renew. Sustain. Energy Rev. 155, 111925 (2022)
R.S. Freitas, Á.P. Lima, C. Chen, F.A. Rochinha, D. Mira, X. Jiang, Towards predicting liquid fuel physicochemical properties using molecular dynamics guided machine learning models. Fuel 329, 125415 (2022)
M. Amine, Y. Barakat, Properties of gasoline-ethanol-methanol ternary fuel blend compared with ethanol-gasoline and methanol-gasoline fuel blends. Egypt. J. Pet. 28, 371–376 (2019)
V.F. Andersen, J.E. Anderson, T.J. Wallington, S.A. Mueller, O.J. Nielsen, Vapor pressures of alcohol–gasoline blends. Energy Fuels 24, 3647–3654 (2010)
G.M. Chupka, E. Christensen, L. Fouts, T.L. Alleman, M.A. Ratcliff, R.L. McCormick, Heat of vaporization measurements for ethanol blends up to 50 volume percent in several hydrocarbon blendstocks and implications for knock in SI engines. SAE Int. J. Fuels Lubr. 8, 251–263 (2015)
G.M. Fioroni, E. Christensen, L. Fouts, R. McCormick, Heat of vaporization and species evolution during gasoline evaporation measured by DSC/TGA/MS for blends of C1 to C4 alcohols in commercial gasoline blendstocks. SAE Technical Paper (No. 2019-01-0014) (2019)
W. Tutak, A. Jamrozik, K. Grab-Rogaliński, The effect of RME-1-butanol blends on combustion, performance and emission of a direct injection diesel engine. Energies 14, 2941 (2021)
L.R. Waterland, S. Venkatesh, S. Unnasch, , Safety and performance assessment of ethanol/diesel blends (E-diesel) (No. NREL/SR-540-34817). National Renewable Energy Lab., Golden, CO. (US) (2003)
Q. Xia, Z. Han, W. Tian, Comparative analysis of effect of diesel and n-butanol blend properties on combustion process and hydrocarbon emission at various oxygen-intake concentrations. J. Energy Eng. 146, 04020010 (2020)
Z.A.M. Yusof, I. Ahmed, M.S. Khan, S.A. Hussain, A. Hussain, I.B.A. Mutalib, K.S. Balkhair, M.H. Albeirutty, Thermal evaluation of diesel/hydrogen peroxide fuel blend. Chem. Eng. Technol. 38, 2170–2180 (2015)
P. Zhang, X. Su, H. Chen, L. Geng, X. Zhao, Assessing fuel properties effects of 2,5-dimethylfuran on microscopic and macroscopic characteristics of oxygenated fuel/diesel blends spray. Sci. Rep. 10, 1427 (2020)
K. Kar, T. Last, C. Haywood, R. Raine, Measurement of vapor pressures and enthalpies of vaporization of gasoline and ethanol blends and their effects on mixture preparation in an SI engine. SAE Int. J. Fuels Lubr. 1, 132–144 (2009)
N. Papaioannou, X. Fang, F. Leach, A. Lewis, S. Akehurst, J. Turner, Using neural network and random forest algorithmic approaches to predicting particulate emissions from a highly boosted GDI engine. SAE Technical Papers (No. 2021-24-0076) (2021)
Gasoline (IARC). https://inchem.org/documents/iarc/vol45/45-03.html. Access on 24 March 2023
S. Negro, F. Brusiani, G.M. Bianchi, A numerical model for flash boiling of gasoline-ethanol blends in fuel injector nozzles. SAE Int. J. Fuels Lubr. 4, 237–256 (2011)
Wind Turbines—Renewable Energy Fact Sheet | US EPA. https://www.epa.gov/sustainable-water-infrastructure/wind-turbines-renewable-energy-fact-sheet. Access on 21 March 2023
Acknowledgements
The authors would like to acknowledge Dr. Souvick Chatterjee (Mathworks India) India for providing helpful insights on different machine learning algorithms.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bansal, M., Kashyap, R., Saha, K. (2024). The Estimation of Latent Heat and Vapor Pressure of Ethanol–Gasoline Blends Using Machine Learning and Thermodynamic Relations. In: Zhao, J., Kadam, S., Yu, Z., Li, X. (eds) IGEC Transactions, Volume 1: Energy Conversion and Management. IAGE 2023. Springer Proceedings in Energy. Springer, Cham. https://doi.org/10.1007/978-3-031-48902-0_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-48902-0_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48901-3
Online ISBN: 978-3-031-48902-0
eBook Packages: EnergyEnergy (R0)