Abstract
Four methods for direct classification (decision tree classifier, K-nearest neighbors, support vector machine and artificial neural networks) have been optimized and compared to classify biodiesel samples according to their compliance to viscosity, density, oxidative stability and iodine value, having as input the composition of fatty acid methyl esters. The eight databases for the classification of each property according to the standards EN 14214, RANP 45/2014 and ASTM D6751 were increased by synthetic minority over-sampling technique to deal with imbalanced data (different numbers of compliant and non-compliant samples). Taking as criteria the best performance and lowest complexity, decision tree classifier and K-nearest neighbors methods presented the best results, ensuring maximum accuracy, sensitivity and specificity (1.0000) for samples of external validation, for almost all properties and standards. A comparison between these methods of direct classification and empirical equations (indirect classification) distinguished positively the direct classification methods in the problem addressed.
Similar content being viewed by others
References
Hoekman SK, Broch A, Robbins C, Ceniceros E, Natarajan M (2012) Review of biodiesel composition, properties, and specifications. Renew Sust Energy Rev 16:143–169
Sarin A (2012) Biodiesel: production and properties. Royal Society of Chemistry, Cambridge
Alptekin E, Canakci M (2008) Determination of the density and the viscosities of biodiesel–diesel fuel blends. Renew Energy 33:2623–2630
Barradas Filho AO, Barros AKD, Labidi S, Viegas IMA, Marques DB, Romariz ARS, De Sousa RM, Marques ALB, Marques EP (2015) Application of artificial neural networks to predict viscosity, iodine value and induction period of biodiesel focused on the study of oxidative stability. Fuel 145:127–135
Knothe G (2005) Dependence of biodiesel fuel properties on the structure of fatty acid alkyl esters. Fuel Process Technol 86:1059–1070
Ramírez-Verduzco LF, Rodríguez-Rodríguez JE, Jaramillo-Jacob AR (2012) Predicting cetane number, kinematic viscosity, density and higher heating value of biodiesel from its fatty acid methyl ester composition. Fuel 91:102–111
Balabin RM, Lomakina EI, Safieva RZ (2011) Neural network (ANN) approach to biodiesel analysis: analysis of biodiesel density, kinematic viscosity, methanol and water contents using near infrared (NIR) spectroscopy. Fuel 90:2007–2015
Balabin RM, Safieva RZ (2011) Biodiesel classification by base stock type (vegetable oil) using near infrared spectroscopy data. Anal Chim Acta 689:190–197
Veras G, Gomes AA, Da Silva AC, De Brito ALB, Almeida PBA, Medeiros EP (2010) Classification of biodiesel using NIR spectrometry and multivariate techniques. Talanta 83:565–568
Pontes MJC, Pereira CF, Pimentel MF, Vasconcelos FVC, Silva AGB (2011) Screening analysis to detect adulteration in diesel/biodiesel blends using near infrared spectrometry and multivariate classification. Talanta 85:2159–2165
Khanmohammadi M, Garmarudi AB, Ghasemi K, De La Guardia M (2013) Quality based classification of gasoline samples by ATR-FTIR spectrometry using spectral feature selection with quadratic discriminant analysis. Fuel 111:96–102
Moser BR (2011) Influence of extended storage on fuel properties of methyl esters prepared from canola, palm, soybean and sunflower oils. Renew Energy 36:1221–1226
Park JY, Kim DK, Lee JP, Park SC, Kim YJ, Lee JS (2008) Blending effects of biodiesels on oxidation stability and low temperature flow properties. Bioresour Technol 99:1196–1203
Balat M (2011) Potential alternatives to edible oils for biodiesel production—a review of current work. Energy Convers Manag 52:1479–1492
Candeia RA (2008) Biodiesel de soja: síntese, degradação e misturas binárias. Thesis, Federal University of Paraíba
Dantas MB (2010) Blendas de biodiesel: propriedades de fluxo, estabilidade térmica e oxidativa e monitoramento durante armazenamento. Thesis, Federal University of Paraíba
Kivevele TT, Makame MM (2011) Experimental investigations of oxidation stability of biodiesel produced from manketti seeds oil (Schinziophyton rautanenii). Energy Fuel 25:2341–2346
Martín C, Moure A, Martín G, Carrillo E, Domínguez H, Parajó JC (2010) Fractional characterisation of jatropha, neem, moringa, trisperma, castor and candlenut seeds as potential feedstocks for biodiesel production in Cuba. Biomass Bioenergy 34:533–538
Nogueira CA, Feitosa FX, Fernandes FAN, Santiago RS, De Sant’Ana HB (2010) Densities and viscosities of binary mixtures of babassu biodiesel + cotton seed or soybean biodiesel at different temperatures. J Chem Eng Data 55:5305–5310
Padhi SK (2010) Preparation and characterization of biodiesel from non-edible oils. Thesis, National Institute of Technology Rourkela
Santos JRJ (2008) Biodiesel de babaçu: avaliação térmica, oxidativa e misturas binárias. Thesis, Federal University of Paraíba
Sanford SD, White JM, Shah OS, Wee C, Valverde MA, Meier GR (2009) Feedstock and biodiesel characteristics report. Renew Energy Group. http://www.biodiesel.org/reports/20091117_gen-398.pdf. Acessed 03 Sep 2016
Sarin R, Sharma M, Sinharay S, Malhotra RK (2007) Jatropha–Palm biodiesel blends: an optimum mix for Asia. Fuel 86:1365–1371
Lima JRO, Da Silva RB, De Moura EM, De Moura CVR (2008) Biodiesel of tucum oil, synthesized by methanolic and ethanolic routes. Fuel 87:1718–1723
Nadai DV, Simões JB, Gatts CEN, Miranda PCML (2013) Inference of the biodiesel cetane number by multivariate techniques. Fuel 105:325–330
Bamgboye AI, Hansen AC (2008) Prediction of cetane number of biodiesel fuel from the fatty acid methyl ester (FAME) composition. Int Agrophys 22:21–29
Ramadhas AS, Jayaraj S, Muraleedharan C, Padmakumari K (2006) Artificial neural networks used for the prediction of the cetane number of biodiesel. Renew Energy 31:2524–2533
Ramos MJ, Fernández CM, Casas A, Rodríguez L, Pérez A (2009) Influence of fatty acid composition of raw materials on biodiesel properties. Bioresour Technol 100:261–268
Tong D, Hu C, Jiang K, Li Y (2011) Cetane number prediction of biodiesel from the composition of the fatty acid methyl esters. J Am Oil Chem Soc 88:415–423
Solberg AHS, Solberg R (1996) A large-scale evaluation of features for automatic detection of oil spills in ERS SAR images. IEEE international geoscience and remote sensing symposium, IGARSS '96, vol 3. IEEE, pp 1484–1486
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Brooks/Cole Publishing, Monterey
Cover TM, Hart PE (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21–27
Vapnik V (1995) The nature of statistical learning theory. Springer, New York
Balabin RM, Safieva RZ, Lomakina EI (2011) Near-infrared (NIR) spectroscopy for motor oil classification: from discriminant analysis to support vector machines. Microchem J 98:121–128
Alves JCL, Henriques CB, Poppi RJ (2012) Determination of diesel quality parameters using support vector regression and near infrared spectroscopy for an in-line blending optimizer system. Fuel 97:710–717
Shi F, Chen J, Xu Y, Karimi HR (2013) Optimization of biodiesel injection parameters based on support vector machine. Math Probl Eng 2013:1–8
Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27
Kumar J, Bansal A (2010) Application of artificial neural network to predict properties of diesel–biodiesel blends. Kathmandu Univ J Sci Eng Technol 6:98–103
Arumugam S, Sriram G, Shankara Subramanian PR (2012) Application of artificial intelligence to predict the performance and exhaust emissions of diesel engine using rapeseed oil methyl ester. Procedia Eng 38:853–860
Hong IK, Jeon GS, Lee SB (2014) Prediction of biodiesel fuel properties from fatty acid alkyl ester. J Ind Eng Chem 20:2348–2353
Wang L-B, Yu H-Y, He X-H, Liu R-Y (2012) Influence of fatty acid composition of woody biodiesel plants on the fuel properties. J Fuel Chem Technol 40:397–404
Agarwal M, Singh K, Chaurasia SP (2010) Prediction of biodiesel properties from fatty acid composition using linear regression and ann techniques. Indian Chem Eng 52:347–361
Ramírez-Verduzco LF (2013) Density and viscosity of biodiesel as a function of temperature: empirical models. Renew Sust Energy Rev 19:652–665
Knothe G, Steidley KR (2005) Kinematic viscosity of biodiesel fuel components and related compounds. Influence of compound structure and comparison to petrodiesel fuel components. Fuel 84:1059–1065
Knothe G (2002) Structure indices in FA chemistry. How relevant is the iodine value? JAOC 79:847–854
Acknowledgements
The authors are thankful for the support received from Coordination for the Improvement of Higher Education Personnel from Brazil (CAPES), National Council for Scientific and Technological Development from Brazil (CNPq) and Foundation for Research and Scientific and Technological Development of Maranhão (FAPEMA).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Lopes, M.V., Barradas Filho, A.O., Barros, A.K. et al. Attesting compliance of biodiesel quality using composition data and classification methods. Neural Comput & Applic 31, 539–551 (2019). https://doi.org/10.1007/s00521-017-3087-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3087-4