Application of LSSVM for biodiesel production using supercritical ethanol solvent. Issue 17 (2nd September 2017)

• Record Type: Journal Article
• Authors: Liu, Zhenling; Baghban, Alireza
• Is Part Of: Energy sources. Volume 39:Issue 17(2017)
• Page Start: 1869
• Page End: 1874
• Publication Date: 2017-09-02
• Subjects: Biodiesel -- ethanol -- supercritical fluid -- least square support vector machine -- genetic algorithm; Natural resources -- Periodicals; Energy consumption -- Periodicals; Energy consumption -- Climatic factors -- Periodicals; Energy conversion -- Periodicals; Energy conversion -- Environment aspects -- Periodicals; Power (Mechanics) -- Periodicals; 333.7905
• DOI: 10.1080/15567036.2017.1380732
• Languages: English
• ISSNs: 1556-7036

Abstract

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.