Artificial Neural Network Models for Octane Number and Octane Sensitivity: A Quantitative Structure Property Relationship Approach to Fuel Design

SubLaban, Amina; Kessler, Travis J.; Van Dam, Noah; Mack, J. Hunter

doi:10.1115/1.4062189

Artificial Neural Network Models for Octane Number and Octane Sensitivity: A Quantitative Structure Property Relationship Approach to Fuel Design

Journal Article · Mon Apr 17 00:00:00 EDT 2023 · Journal of Energy Resources Technology

DOI:https://doi.org/10.1115/1.4062189· OSTI ID:2283717

SubLaban, Amina ^[1]; Kessler, Travis J. ^[1]; Van Dam, Noah ^[1]; Mack, J. Hunter ^[1]

Univ. of Massachusetts, Lowell, MA (United States)

Octane sensitivity (OS), defined as the research octane number (RON) minus the motor octane number (MON) of a fuel, has gained interest among researchers due to its effect on knocking conditions in internal combustion engines. Compounds with a high OS enable higher efficiencies, especially within advanced compression ignition engines. RON/MON must be experimentally tested to determine OS, requiring time, funding, and specialized equipment. Thus, predictive models trained with existing experimental data and molecular descriptors (via quantitative structure-property relationships (QSPRs)) would allow for the preemptive screening of compounds prior to performing these experiments. Here, the present work proposes two methods for predicting the OS of a given compound: using artificial neural networks (ANNs) trained with QSPR descriptors to predict RON and MON individually to compute OS (derived octane sensitivity (dOS)), and using ANNs trained with QSPR descriptors to directly predict OS. Twenty-five ANNs were trained for both RON and MON and their test sets achieved an overall 6.4% and 5.2% error, respectively. Twenty-five additional ANNs were trained for both dOS and OS; dOS calculations were found to have 15.3% error while predicting OS directly resulted in 9.9% error. A chemical analysis of the top QSPR descriptors for RON/MON and OS is conducted, highlighting desirable structural features for high-performing molecules and offering insight into the inner mathematical workings of ANNs; such chemical interpretations study the interconnections between structural features, descriptors, and fuel performance showing that connectivity, structural diversity, and atomic hybridization consistently drive fuel performance.

View Accepted Manuscript (DOE)

Research Organization:: Univ. of Massachusetts, Lowell, MA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Office of Sustainable Transportation. Bioenergy Technologies Office (BETO)

Grant/Contract Number:: EE0008479

OSTI ID:: 2283717

Journal Information:: Journal of Energy Resources Technology, Vol. 145, Issue 10; ISSN 0195-0738

Publisher:: ASMECopyright Statement

Country of Publication:: United States

Language:: English

References (44)

Octane Rating of Gasoline and Octane Booster Additives Demirbas, A.; Balubaid, M. A.; Basahel, A. M. Petroleum Science and Technology, Vol. 33, Issue 11 https://doi.org/10.1080/10916466.2015.1050506	journal	June 2015
Numerical Investigation of a Central Fuel Property Hypothesis Under Boosted Spark-Ignition Conditions Pal, Pinaki; Kalvakala, Krishna; Wu, Yunchao Journal of Energy Resources Technology, Vol. 143, Issue 3 https://doi.org/10.1115/1.4048995	journal	December 2020
Determination of octane numbers in gasoline by distillation curves and partial least squares regression Mendes, Gisele; Aleme, Helga G.; Barbeira, Paulo J. S. Fuel, Vol. 97, p. 131-136 https://doi.org/10.1016/j.fuel.2012.01.058	journal	July 2012
Detailed Chemistry Promotes Understanding of Octane Numbers and Gasoline Sensitivity Mehl, Marco; Faravelli, Tiziano; Giavazzi, Fulvio Energy & Fuels, Vol. 20, Issue 6 https://doi.org/10.1021/ef060339s	journal	November 2006
Pressure and temperature effects on fuels with varying octane sensitivity at high load in SI engines Szybist, James P.; Splitter, Derek A. Combustion and Flame, Vol. 177 https://doi.org/10.1016/j.combustflame.2016.12.002	journal	March 2017
Ignition timing sensitivities of oxygenated biofuels compared to gasoline in a direct-injection SI engine Daniel, Ritchie; Tian, Guohong; Xu, Hongming Fuel, Vol. 99 https://doi.org/10.1016/j.fuel.2012.01.053	journal	September 2012
Bio-butanol as a new generation of clean alternative fuel for SI (spark ignition) and CI (compression ignition) engines Zhen, Xudong; Wang, Yang; Liu, Daming Renewable Energy, Vol. 147 https://doi.org/10.1016/j.renene.2019.10.119	journal	March 2020
Identifying and designing chemicals with minimal acute aquatic toxicity Kostal, Jakub; Voutchkova-Kostal, Adelina; Anastas, Paul T. Proceedings of the National Academy of Sciences, Vol. 112, Issue 20 https://doi.org/10.1073/pnas.1314991111	journal	March 2014
The Electrotopological State: An Atom Index for QSAR Hall, Lowell H.; Mohney, Brian; Kier, Lemont B. Quantitative Structure-Activity Relationships, Vol. 10, Issue 1 https://doi.org/10.1002/qsar.19910100108	journal	January 1991
Randić index and information Gutman, Ivan; Furtula, Boris; Katanić, Vladimir AKCE International Journal of Graphs and Combinatorics, Vol. 15, Issue 3 https://doi.org/10.1016/j.akcej.2017.09.006	journal	December 2018
A Mathematical Theory of Communication Shannon, C. E. Bell System Technical Journal, Vol. 27, Issue 3 https://doi.org/10.1002/j.1538-7305.1948.tb01338.x	journal	July 1948
Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods Saldana, Diego Alonso; Starck, Laurie; Mougin, Pascal Energy & Fuels, Vol. 25, Issue 9 https://doi.org/10.1021/ef200795j	journal	September 2011
Cetane numbers of hydrocarbons: calculations using optimal topological indices Smolenskii, E. A.; Bavykin, V. M.; Ryzhov, A. N. Russian Chemical Bulletin, Vol. 57, Issue 3 https://doi.org/10.1007/s11172-008-0073-0	journal	March 2008
Impact of Aromatic Structures and Content in Formulated Fuel for Jet Engine Applications on Particulate Matter Emissions Zheng, Lukai; Singh, Paramvir; Cronly, James Journal of Energy Resources Technology, Vol. 143, Issue 12 https://doi.org/10.1115/1.4049905	journal	February 2021
Machine learning in chemoinformatics and drug discovery Lo, Yu-Chen; Rensi, Stefano E.; Torng, Wen Drug Discovery Today, Vol. 23, Issue 8 https://doi.org/10.1016/j.drudis.2018.05.010	journal	August 2018
A Computational Investigation of Fuel Chemical and Physical Properties Effects on Gasoline Compression Ignition in a Heavy-Duty Diesel Engine Zhang, Yu; Voice, Alexander; Pei, Yuanjiang Journal of Energy Resources Technology, Vol. 140, Issue 10 https://doi.org/10.1115/1.4040010	journal	May 2018
Numerical Analysis of Fuel Effects on Advanced Compression Ignition Using a Cooperative Fuel Research Engine Computational Fluid Dynamics Model Kalvakala, Krishna; Pal, Pinaki; Wu, Yunchao Journal of Energy Resources Technology, Vol. 143, Issue 10 https://doi.org/10.1115/1.4050490	journal	March 2021
Numerical Investigation of Fuel Property Effects on Mixed-Mode Combustion in a Spark-Ignition Engine Xu, Chao; Pal, Pinaki; Ren, Xiao Journal of Energy Resources Technology, Vol. 143, Issue 4 https://doi.org/10.1115/1.4048242	journal	September 2020
Multidimensional Numerical Simulations of Knocking Combustion in a Cooperative Fuel Research Engine Pal, Pinaki; Wu, Yunchao; Lu, Tianfeng Journal of Energy Resources Technology, Vol. 140, Issue 10 https://doi.org/10.1115/1.4040063	journal	May 2018
Machine learning regression based group contribution method for cetane and octane numbers prediction of pure fuel compounds and mixtures Li, Runzhao; Herreros, Jose Martin; Tsolakis, Athanasios Fuel, Vol. 280 https://doi.org/10.1016/j.fuel.2020.118589	journal	November 2020
A comparison of computational models for predicting yield sooting index Kessler, Travis; St. John, Peter C.; Zhu, Junqing Proceedings of the Combustion Institute, Vol. 38, Issue 1 https://doi.org/10.1016/j.proci.2020.07.009	journal	January 2021
Measuring and predicting sooting tendencies of oxygenates, alkanes, alkenes, cycloalkanes, and aromatics on a unified scale Das, Dhrubajyoti D.; St. John, Peter C.; McEnally, Charles S. Combustion and Flame, Vol. 190 https://doi.org/10.1016/j.combustflame.2017.12.005	journal	April 2018
Artificial neural network based predictions of cetane number for furanic biofuel additives Kessler, Travis; Sacia, Eric R.; Bell, Alexis T. Fuel, Vol. 206 https://doi.org/10.1016/j.fuel.2017.06.015	journal	October 2017
Octane number prediction based on gas chromatographic analysis with non-linear regression techniques van Leeuwen, J. A.; Jonker, R. J.; Gill, R. Chemometrics and Intelligent Laboratory Systems, Vol. 25, Issue 2 https://doi.org/10.1016/0169-7439(94)85051-8	journal	November 1994
Octane number prediction for gasoline blends Pasadakis, Nikos; Gaganis, Vassilis; Foteinopoulos, Charalambos Fuel Processing Technology, Vol. 87, Issue 6 https://doi.org/10.1016/j.fuproc.2005.11.006	journal	June 2006
Predicting fuel research octane number using Fourier-transform infrared absorption spectra of neat hydrocarbons Daly, Shane R.; Niemeyer, Kyle E.; Cannella, William J. Fuel, Vol. 183 https://doi.org/10.1016/j.fuel.2016.06.097	journal	November 2016
Predicting Viscosities of Heavy Oils and Solvent–Heavy Oil Mixtures Using Artificial Neural Networks Chen, Zehua; Yang, Daoyong Journal of Energy Resources Technology, Vol. 143, Issue 11 https://doi.org/10.1115/1.4049603	journal	February 2021
Development of a Detailed Gasoline Composition-Based Octane Model Ghosh, Prasenjeet; Hickey, Karlton J.; Jaffe, Stephen B. Industrial & Engineering Chemistry Research, Vol. 45, Issue 1 https://doi.org/10.1021/ie050811h	journal	January 2006
Renewable Oxygenate Blending Effects on Gasoline Properties Christensen, Earl; Yanowitz, Janet; Ratcliff, Matthew Energy & Fuels, Vol. 25, Issue 10 https://doi.org/10.1021/ef2010089	journal	October 2011
Octane-Enhancing, Zeolitic FCC Catalysts: Scientific and Technical Aspects Scherzer, Julius Catalysis Reviews, Vol. 31, Issue 3 https://doi.org/10.1080/01614948909349934	journal	August 1989
Selection Criteria and Screening of Potential Biomass-Derived Streams as Fuel Blendstocks for Advanced Spark-Ignition Engines McCormick, Robert L.; Fioroni, Gina; Fouts, Lisa SAE International Journal of Fuels and Lubricants, Vol. 10, Issue 2 https://doi.org/10.4271/2017-01-0868	journal	March 2017
A property database of fuel compounds with emphasis on spark-ignition engine applications vom Lehn, Florian; Cai, Liming; Tripathi, Rupali Applications in Energy and Combustion Science, Vol. 5 https://doi.org/10.1016/j.jaecs.2020.100018	journal	March 2021
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
ECNet: Large scale machine learning projects for fuel property prediction Kessler, Travis; Hunter Mack, John The Journal of Open Source Software, Vol. 2, Issue 17 https://doi.org/10.21105/joss.00401	journal	September 2017
Using machine learning with target-specific feature sets for structure-property relationship modeling of octane numbers and octane sensitivity vom Lehn, Florian; Brosius, Benedict; Broda, Rafal Fuel, Vol. 281 https://doi.org/10.1016/j.fuel.2020.118772	journal	December 2020
Phase discrimination of compound gratings: generalized autocorrelation analysis Klein, Stanley A.; Tyler, Christopher W. Journal of the Optical Society of America A, Vol. 3, Issue 6 https://doi.org/10.1364/JOSAA.3.000868	journal	June 1986
The spatial autocorrelation matrix Chessel, D. Vegetation dynamics in grasslans, healthlands and mediterranean ligneous formations https://doi.org/10.1007/978-94-009-7991-8_17	book	January 1981
A comparison of methods for measuring relative radical stabilities of carbon-centred radicals Coote, Michelle L.; Lin, Ching Yeh; Beckwith, Athelstan L. J. Physical Chemistry Chemical Physics, Vol. 12, Issue 33 https://doi.org/10.1039/c003880f	journal	January 2010
Uniqueness in the low temperature oxidation of cycloalkanes Yang, Yi; Boehman, André L.; Simmie, John M. Combustion and Flame, Vol. 157, Issue 12 https://doi.org/10.1016/j.combustflame.2010.06.005	journal	December 2010
Characterization of molecular branching Randic, Milan Journal of the American Chemical Society, Vol. 97, Issue 23 https://doi.org/10.1021/ja00856a001	journal	November 1975
Bond order weighted graphs in molecules as structure-property indices Estrada, Ernesto; Montero, Luis Alberto Molecular Engineering, Vol. 2, Issue 4 https://doi.org/10.1007/BF00999824	journal	January 1993
Chemical kinetics of octane sensitivity in a spark-ignition engine Westbrook, Charles K.; Mehl, Marco; Pitz, William J. Combustion and Flame, Vol. 175 https://doi.org/10.1016/j.combustflame.2016.05.022	journal	January 2017
Experimental and Kinetic Modeling Study of 2-Methyl-2-Butene: Allylic Hydrocarbon Kinetics Westbrook, Charles K.; Pitz, William J.; Mehl, Marco The Journal of Physical Chemistry A, Vol. 119, Issue 28 https://doi.org/10.1021/acs.jpca.5b00687	journal	February 2015
Theoretical Study of Radical–Molecule Reactions with Negative Activation Energies in Combustion: Hydroxyl Radical Addition to Alkenes Xiao, FengXia; Sun, XiaoHui; Li, ZeRong ACS Omega, Vol. 5, Issue 22 https://doi.org/10.1021/acsomega.0c00400	journal	May 2020

Similar Records

Prediction of Research/Motor Octane Number and Octane Sensitivity Using Artificial Neural Networks

Conference · Mon Mar 09 00:00:00 EDT 2020 · OSTI ID:2283729

Kessler, Travis J.; Hudson, Corey; Whitmore, Leanne; +1 more

Development of a Supercharged Octane Number and a Supercharged Octane Index

Journal Article · Tue Apr 11 00:00:00 EDT 2023 · SAE Technical Paper Series · OSTI ID:1969816

Hoth, Alexander; Kolodziej, Christopher P.; Waqas, Muhammad; +2 more

Determination of octane numbers and Reid vapor pressure of commercial petroleum fuels using FT-Raman spectroscopy and partial least-squares regression analysis

Journal Article · Wed Nov 15 00:00:00 EST 1995 · Analytical Chemistry (Washington) · OSTI ID:159681

Cooper, J B; Wise, K L; Groves, J; +1 more

Related Subjects

09 BIOMASS FUELS
octane
octane sensitivity
artificial neural network
research octane number
motor octane number
quantitative structure-property relationship
fuel performance
fuel combustion
renewable energy

Artificial Neural Network Models for Octane Number and Octane Sensitivity: A Quantitative Structure Property Relationship Approach to Fuel Design

Citation Formats

References (44)

Similar Records

Related Subjects