Prediction of sulfur content in desulfurization process using a fuzzy-logic based model

In petroleum industry, hydrodesulphurization (HDS) process is considered as one of the crucial catalytic units in which the sulfur is mostly eradicated. The modeling of HDS process is very important for the proper understanding of the process operation to be optimized. The studies conducted, in this area, focused on predicting parameters using analytical, empirical and numerical approaches. However, a typical desulfurization process is constantly faced with an uncertainty, which should be considered in a reasoning way. Therefore, this work aims to explore the use of fuzzy logic (FL) inference system in creating models of the HDS process for the prediction of sulfur reduction from oil. In order to validate the proposed model, we employed experimental data from the HDS setup. The simulated sulfur content results obtained from the proposed model correspond closely to the real experimental values. The outstanding performance of the developed FL-based model suggests its potential in predicting sulfur content for optimization of the HDS process. The model demonstrates promising results in terms of high correlation (R² =0.98) and minimal percentage of error (AARE=0.072).