Comparison of different optimization techniques for microwave-assisted biodiesel production

Abstract

ABSTRACT Microwave-assisted biodiesel production from palm oil is becoming more and more important because of the greatly shortened reaction time and high energy-efficiency. In this novel research, an experimental study was conducted to optimize the experimental conditions of microwave-assisted biodiesel production. Response surface methodology (RSM), back propagation artificial neural network (BP-ANN) and Genetic algorithm improved BP-ANN (BPANN-GA) and were established and compared to optimize four operating parameters, including methanol/oil molar ratio (5:1–15:1), catalyst amount (0.75 –1.25 wt.%), temperature (60–70°C) and microwave time (20 –50 min). RSM, BP-ANN and BPANN-GA models were considered to be reliable in predicting biodiesel yield, BPANN-GA model (R2 = 0.9957) showed better accuracy than the RSM model (R2 = 0.9823) and BP-ANN model (R2 = 0.9867). The optimized process parameters were 14.9 methanol/oil molar ratio, 0.84 wt.% catalyst amount, 69°C temperature and microwave time of 49.3 min, the corresponding yield was 98.15%. The produced biodiesel properties were compared with ASTM D6571 standards. The results of the research are constructive for the optimization of microwave-assisted biodiesel experimental conditions when processing a small sample database.