Prediction of biodiesel iodine value from its fatty acids composition using a novel approach

抄録

Biodiesel as an environmental-friendly and renewable fuel assigns a great potential to substitution of petroleum diesel. Iodine value (IV) is an indicator to evaluate the degree of unsaturation (DU) of biodiesel. It reflects the biodiesel degradation and oxidation stability (OS) and also has an effect on viscosity, low-temperature flow properties, and the combustion performance. The main aim of this present work was to develop an accurate model based on RF-WOA-LSSVM algorithm to estimate biodiesel IV. The 14 fatty acid methyl esters (FAMEs) are involved variables for development of the models. The performance of developed RF-WOA-LSSVM model was compared using statistical criteria such as correlation coefficient (R²), root mean square error (RMSE) and mean absolute percent error (MAPE). It was determined that R² of RF-WOA-LSSVM model was 0.9989. In addition, the outcomes of the proposed model are compared with those from Knothe (2002)’s model indicating the great potential of the RF-WOA-LSSVM model to estimate the biodiesel IV.