Production and optimization of soybean biodiesel production at fixed temperature 50 °C with RSM and ANN.

Abstract

The study examined the extraction of bio-oil from soybean and the optimization of the production of the transesterification process using response surface methodology (RSM) and artificial neural network (ANN). This research uniquely highlights the utilization of soybean oil, a sustainable feedstock, and combines RSM and ANN methodologies to enhance the precision of biodiesel optimization at fixed temperature. The RSM-optimized conditions for maximum production were determined to be a 1.82% catalyst concentration, 8:1 methanol-to-oil ratio, 50 °C temperature, and 34-min time, resulting in an 80.86% biodiesel yield. Prediction models were created using transesterified soybean oil and the Box-Behnken architecture, varying three parameters of the process like the rate of reaction, m-ratio, and catalyst concentration time at a fixed temperature of 50. The RSM model and ANN model have been developed by using Box-Behnken design and by a trainlm algorithm having 4 neurons in the hidden layer (3:4:1). Developed models of RSM and ANN have been checked for the performance of biodiesel. The highest value of R² = 0.989 and the lowest value of RMSE = 0.633 have been obtained, which is better than RSM.