Response Surface Methodology and Artificial Neural Network Analysis of Crude Palm Kernel Oil Biodiesel Production

Abstract Response surface methodology (RSM) and Artificial neural network (ANN) analysis of crude palm kernel oil (CPKO) biodiesel production, using KOH and NaOH catalysts, were carried out in this research work. The four process parameters considered during the production process and modelling stages were 6–12 mole ratio of methanol/oil, 0.7–1.7 wt/wt% catalyst concentration, 48–62°C reaction temperature and 50–90 minutes reaction time. Log sigmoid function and Levenberg marquardt technique were adopted in ANN while Box-Benkhen method was utilised for RSM. The results revealed that KOH catalyst process produced higher yield of biodiesel (87 – 99%), compared to the yield obtained from NaOH catalysed process (79 – 91%). The regression coefficients for RSM models were 0.9324 for KOH catalysed process and 0.8935 for NaOH catalysed process, while the overall correlation coefficients for ANN models were 0.82921 for KOH catalysed process and 0.89396 for NaOH catalysed process, an implication that RSM is a better analytical tool (compare to ANN) in models formulation.