摘要
Various simulation tools were used to develop an effective intelligent system to predict the effects of temperature and pressure on an oil extraction yield. Pomegranate oil was extracted using a supercritical CO2 （SC-CO2） process. Several simulation systems including a back-propagation neural network （BPNN）, a radial basis function neural network （RBFNN） and an adaptive- network-based fuzzy inference system （ANFIS） were tested and their results were compared to determine the best predictive model. The performance of these networks was evaluated using the coefficient of determination （R^2） and the mean square error （MSE）. The best correlation between the predicted and the experimental data was achieved using the BPNN method with an R^2 of 0.9948.
Various simulation tools were used to develop an effective intelligent system to predict the effects of temperature and pressure on an oil extraction yield. Pomegranate oil was extracted using a supercritical CO2 （SC-CO2） process. Several simulation systems including a back-propagation neural network （BPNN）, a radial basis function neural network （RBFNN） and an adaptive- network-based fuzzy inference system （ANFIS） were tested and their results were compared to determine the best predictive model. The performance of these networks was evaluated using the coefficient of determination （R^2） and the mean square error （MSE）. The best correlation between the predicted and the experimental data was achieved using the BPNN method with an R^2 of 0.9948.
