Abstract
In this paper, an Artificial Neural Network (ANN) model for the simulation of an industrial Hydrotreater Unit (HU) is presented. Hydrotreating is an important oil refinery processes, but due to its complexity, the modeling poses a great challenge. The proposed model predicts hydrogen demand, outlet API, and sulfur weight percent as a function of inlet API and sulfur weight percent for seven different feedstocks. This study determines the optimum architecture of ANN in order to achieve good generalization. The results show ANN capability to predict the measured data. The ANN model is also compared to those of an existing simulator available at a local refinery. The comparison confirms the superiority of the ANN model.