Optimization of Oil Yield from the Macro Algae Spirogyra by Solvent Extraction Process Using RSM and ANN

Abstract

The present work was done to optimize the process parameters of the oil extraction from the algae species spirogyra by using n-hexane as the solvent using the Soxhlet apparatus. The response surface methodology (RSM) and artificial neural network (ANN) were employed to optimize the particle size of the algae powder, dryness level of the algae powder, solid to solvent ratio, reaction time, and extraction temperature of the oil extraction process. Also, the physiochemical properties of the extracted oil were investigated. The comparative evaluation was done between the RSM and ANN models to select the more precise and accurate model. The coefficient of determination, $R^2$ of 98.92%, and the mean absolute percentage deviation (MAPD) of 0.492% for ANN revealed that the current model created with a network topology of 3 : 11 : 1 with tansig (hyperbolic tangent sigmoid) transfer function in the input layer and purelin (pure linear) transfer function in the output layer trained with trainlm (Levenberg–Marquardt) algorithm found to provide the optimal solution with better accuracy in prediction of the output. The physicochemical properties investigated, such as heating value, flashpoint, density, viscosity, iodine number, acid value, saponification value, and cetane index, showed that the extracted oil from the algae spirogyra species can be used as an alternative fuel.