Optimization of biodiesel production from Thevetia peruviana seed oil by adaptive neuro-fuzzy inference system coupled with genetic algorithm and response surface methodology
Oil was extracted from Thevetia peruviana seeds and converted to FAME. The FFA of the oil was first reduced to <1% by esterification process. The conversion of the esterified oil to FAME was modeled using ANFIS and RSM. The developed models by ANFIS and RSM for transesterification process had R2 ≈ 1. GA and RSM gave the maximum FAME yield of 99.8 wt.% and 98.8 wt.%, respectively.