Prediction and optimization of biodiesel production by using ANN and RSM

Authors : Ceyla ÖZGÜR

Pages : 53-62

Doi:10.18245/ijaet.1057170

View : 20 | Download : 10

Publication Date : 2022-07-01

Article Type : Research Paper

Abstract :This experimental work examined the prediction and optimization of biodiesel production from pomegranate seed oil using Artificial Neural Networks insert ignore into journalissuearticles values(ANN); and Response Surface Methodology insert ignore into journalissuearticles values(RSM); with central composite design and The transesterification method chosen for biodiesel production. The Central Composite Design insert ignore into journalissuearticles values(CCD); optimization conditions were methanol/oil molar ratio insert ignore into journalissuearticles values(3:1 to 11:1);, catalyst rate insert ignore into journalissuearticles values(0.5 wt% to 1.50 wt%);, temperature insert ignore into journalissuearticles values(50 ℃ to 70 ℃); and time insert ignore into journalissuearticles values(45 min to 105 min);. The process factors were optimized by using CCD based on the RSM method and developed an ANN model to predict biodiesel yield. The optimum yield was found 95.68% with optimum process parameters as 8.01:1 methanol/oil molar ratio, 1.08 wt% catalyst rate, 70 ℃ temperature and 45 min time. The coefficient of determination insert ignore into journalissuearticles values(R2); acquired from the response surface methodology model is 0.9887 and is better when compared to the coefficient of determination insert ignore into journalissuearticles values(R2); of 0.9691 acquired from the Artificial neural network model. According to the results, using RSM and ANN models is beneficial for optimizing and predicting the biodiesel production process.
Keywords : ANN, optimization, prediction, pomegranate biodiesel, RSM