ABSTRACT
In the present study, results of parametric effects and optimization of extraction of rubber seed oil from under-utilized rubber seeds using response surface methodology (RSM) and artificial neural network (ANN) based on a statistically designed experimentation via the Box–Behnken design (BBD) are reported. A three-level, three-factor BBD was employed using rubber seed powder weight (X1), solvent volume (X2) and extraction time (X3) as process variables. A quadratic polynomial model was obtained to predict oil yield. The RSM model predicted an optimal oil yield of 42.98 wt.% at conditions of X1 (60 g), X2 (250 mL) and X3 (45 min) and validated experimentally as 42.64 wt.%. The ANN model predicted optimal oil yield of 43 wt.% at conditions of X1 (40 g), X2 (202 mL) and X3 (49.99 min) and validated as 42.96 wt.%. Both models are effective in describing the parametric effect of the considered operating variables on the extraction of oil from the rubber seeds. However, the ANN describes the effect more accurately than the RSM model, with a lower percentage relative error and absolute average deviation (AAD). The extracted oil possesses physicochemical properties that support biodiesel production and other industrial applications.
Acknowledgements
The authors appreciate the support provided by the University of the Witwatersrand (Wits), Johannesburg, South Africa, and the Petroleum Training Institute, Effurun, Nigeria.
Disclosure statement
No potential conflict of interest was reported by the authors.