Application of LSSVM for biodiesel production using supercritical ethanol solvent

ABSTRACT The best method for producing the required biodiesels is supercritical transesterification of triglycerides. The number of investigations about the prediction of biodiesels that yield supercritical fluids such as ethanol is not very much yet. In the recent decade, SVM was used very much as a data analyzing tool. Least Squares Vector Machine (LSSVM) method is a least square version of support vector machine. This method is capable of data analyzing and pattern recognizing, which cause that this method is popular in practical problems. The purpose of this study is evaluating the performance of Least Square Support Vector Machine (LSSVM) model in predicting the biodiesel yield as a function of temperature, pressure, reaction time, and ethanol/oil ratio. A genetic algorithm is capable to determine the optimal value of critical parameters. Based on the achieved results, it can be concluded that proposed LSSVM model is a reliable model for predicting biodiesel yield.

[1]  Alireza Bahadori,et al.  On the estimation of viscosities and densities of CO2-loaded MDEA, MDEA + AMP, MDEA + DIPA, MDEA + MEA, and MDEA + DEA aqueous solutions , 2017 .

[2]  A. Mohammadi,et al.  Rigorous modeling of CO2 equilibrium absorption in ionic liquids , 2017 .

[3]  M. Paneque,et al.  Ethics and Biofuel Production in Chile , 2015 .

[4]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[5]  Yukihiko Matsumura,et al.  Artificial Neural Network Modeling to Predict Biodiesel Production in Supercritical Methanol and Ethanol Using Spiral Reactor , 2015 .

[6]  Y. Matsumura,et al.  A novel spiral reactor for biodiesel production in supercritical ethanol , 2015 .

[7]  Alireza Bahadori,et al.  Phase equilibrium modelling of natural gas hydrate formation conditions using LSSVM approach , 2016 .

[8]  David Haussler,et al.  Proceedings of the fifth annual workshop on Computational learning theory , 1992, COLT 1992.

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  Alireza Baghban,et al.  Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches , 2015 .

[11]  Alireza Baghban,et al.  Prediction viscosity of ionic liquids using a hybrid LSSVM and group contribution method , 2017 .

[12]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[13]  A. Mohammadi,et al.  Prediction of CO2 loading capacities of aqueous solutions ofabsorbents using different computational schemes , 2017 .

[14]  Johan A. K. Suykens,et al.  Optimal control by least squares support vector machines , 2001, Neural Networks.

[15]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[16]  Alireza Baghban,et al.  Phase equilibrium modeling of semi-clathrate hydrates of seven commonly gases in the presence of TBAB ionic liquid promoter based on a low parameter connectionist technique , 2015 .