Machine learning approaches for modeling the Extractive Desulfurization in the conventional batch mode

In the conventional batch mode, machine learning approaches were used to predict extractive desulfurization. 23 real experimental data points on sulfur removal were used for the model s development. Radial Basis Function (RBF) and Support Vector Machine (SVM) networks were applied to develop a black-box model of the process. The input parameters of the models were the initial concentrations of sulfur (ppm), reaction temperature (℃), and residence time (min). To create an optimal model, a trial-and-error strategy based on analyzing all possible configurations was used. The outcomes of both RBF and SVM networks demonstrate a good agreement between the experimental data and the model predicted values when considering statistical measures such as correlation coefficients of more than 0.998, mean square errors, the absolute average deviation, and the absolute average relative deviation of less than 3.5%.