Estimation of cetane numbers of biodiesel and diesel oils using regression and PSO-ANFIS models

Abstract One of the essential characteristics of diesel oils is their cetane number (CN) which indicates the ignition delay of the fuel in the process. In this study, using PSO-ANFIS technique, CNs of biodiesel and conventional diesel (called petrodiesel) oils were modeled and estimated based on the fatty acid methyl ester compositions of biodiesel oils and carbon type structure of the diesel fuels. For the first time, novel correlations were developed for the estimation of CNs of biodiesel and conventional diesel oils. For the models development, as the raw data, 232 biodiesel and 134 conventional diesel oils samples were derived from the literature. Based on the obtained results, the coefficient determinations (R2) of 0.91 and 0.93 and %AARD of 6.4 and 9.6 were obtained by PSO-ANFIS and MNR models for the estimation of biodiesel oil CN, respectively. The R2 of 0.98 and 0.96 and %AARD of 2 and 2.9 were resulted using PSO-ANFIS and MNR models for the prognostication of diesel oil CN, respectively. Based on the gained results, PSO-ANFIS and MNR algorithms are capable of estimating the biodiesel and diesel oils CNs. The novelty of this study is the development of novel correlations and smart models with high accuracies.

[1]  Sebastian Verhelst,et al.  Prediction of the cetane number of biodiesel using artificial neural networks and multiple linear regression , 2013 .

[2]  Ömer L. Gülder,et al.  Ignition Quality Rating Methods for Diesel Fuels-A Critical Appraisal , 1985 .

[3]  Pezhman Kazemi,et al.  Fatty Acid Methyl Ester (FAME) composition used for estimation of biodiesel cetane number employing random forest and artificial neural networks: A new approach , 2016 .

[4]  Mostafa Mostafaei,et al.  ANFIS models for prediction of biodiesel fuels cetane number using desirability function , 2018 .

[5]  Amir H. Mohammadi,et al.  Improved estimation of Cetane number of fatty acid methyl esters (FAMEs) based biodiesels using TLBO-NN and PSO-NN models , 2018, Fuel.

[6]  Nicos Ladommatos,et al.  Equations for predicting the cetane number of diesel fuels from their physical properties , 1995 .

[7]  Amin Talebian-Kiakalaieh,et al.  Transesterification of waste cooking oil by heteropoly acid (HPA) catalyst: Optimization and kinetic model , 2013 .

[8]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[9]  A. Mohammadi,et al.  On modeling of bitumen/n‐tetradecane mixture viscosity: Application in solvent‐assisted recovery method , 2018 .

[10]  G. Nagarajan,et al.  Effect of unsaturated fatty acid esters of biodiesel fuels on combustion, performance and emission characteristics of a DI diesel engine , 2010 .

[11]  A. I. Bamgboye,et al.  PREDICTION OF CETANE NUMBER OF BIODIESEL FUEL FROM THE FATTY ACID METHYL ESTER (FAME) COMPOSITION , 2008 .

[12]  Veena Singh,et al.  Microalgal biodiesel: A possible solution for India’s energy security , 2017 .

[13]  K. Krisnangkura.  A simple method for estimation of cetane index of vegetable oil methyl esters , 1986 .

[14]  Gerhard Knothe,et al.  A comprehensive evaluation of the cetane numbers of fatty acid methyl esters , 2014 .

[15]  S. Chou,et al.  Clean, efficient and affordable energy for a sustainable future , 2017 .

[16]  Ali Eslamimanesh,et al.  QSPR molecular approach for representation/prediction of very large vapor pressure dataset , 2012 .

[17]  Mu-Yen Chen,et al.  A hybrid ANFIS model for business failure prediction utilizing particle swarm optimization and subtractive clustering , 2013, Inf. Sci..

[18]  M. Lapuerta,et al.  Correlation for the estimation of the cetane number of biodiesel fuels and implications on the iodine number , 2009 .

[19]  S. O. Adekomaya,et al.  Prediction of selected biodiesel fuel properties using artificial neural network , 2015 .

[20]  Ömer L. Gülder,et al.  Cetane Number Estimation of Diesel Fuels from Carbon Type Structural Composition , 1984 .

[21]  G. Knothe.  Dependence of biodiesel fuel properties on the structure of fatty acid alkyl esters , 2005 .

[22]  Changwei Hu,et al.  Cetane Number Prediction of Biodiesel from the Composition of the Fatty Acid Methyl Esters , 2011 .

[23]  Jürgen Krahl,et al.  The Biodiesel Handbook , 2005 .

[24]  A. Mohammadi,et al.  Rigorous prognostication and modeling of gas adsorption on activated carbon and Zeolite-5A. , 2018, Journal of environmental management.

[25]  Ebru Akkaya,et al.  ANFIS based prediction model for biomass heating value using proximate analysis components , 2016 .

[26]  A. Dashti,et al.  H-2-selective mixed matrix membranes modeling using ANFIS, PSO-ANFIS, GA-ANFIS , 2017 .

[27]  S. Hoekman,et al.  Review of biodiesel composition, properties, and specifications , 2012 .

[28]  G Nagarajan,et al.  Relating the cetane number of biodiesel fuels to their fatty acid composition: A critical study , 2009 .

[29]  S. Jayaraj,et al.  Artificial neural networks used for the prediction of the cetane number of biodiesel , 2006 .

[30]  Octavio Armas,et al.  Correlation for the estimation of the density of fatty acid esters fuels and its implications. A proposed Biodiesel Cetane Index. , 2010, Chemistry and physics of lipids.

[31]  Havva Balat,et al.  Progress in biodiesel processing , 2010 .

[32]  Prasenjeet Ghosh,et al.  Development of a Detailed Gasoline Composition-Based Octane Model , 2006 .

[33]  Navab Kazemi,et al.  Intention of agricultural professionals toward biofuels in Iran: Implications for energy security, society, and policy , 2017 .

[34]  Zbigniew Ring,et al.  Neural network prediction of cetane number and density of diesel fuel from its chemical composition determined by LC and GC–MS , 2002 .

[35]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[36]  M. H. Doranehgard,et al.  Modeling of cetane number of biodiesel from fatty acid methyl ester (FAME) information using GA-, PSO-, and HGAPSO- LSSVM models , 2020 .

[37]  L. Durlofsky,et al.  Application of a particle swarm optimization algorithm for determining optimum well location and type , 2010 .

[38]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[39]  Stephen B. Jaffe,et al.  Detailed Composition-Based Model for Predicting the Cetane Number of Diesel Fuels , 2006 .

[40]  Farhad Gharagheizi,et al.  Evaluation of experimental data for wax and diamondoids solubility in gaseous systems , 2012 .

[41]  Nor Azimah Mohd Zain,et al.  Immobilized lipase-catalyzed transesterification of Jatropha curcas oil: Optimization and modeling , 2014 .