文献类型：期刊文献

英文题名：Study on Residual Oil HDS Process with Mechanism Model and ANN Model

作者：Ma Chengguo[1];Weng Huixin[1]

机构：[1]E China Univ Sci & Technol, Res Ctr Petr Proc, Shanghai 200237, Peoples R China

年份：2009

期号：1

起止页码：39

外文期刊名：CHINA PETROLEUM PROCESSING & PETROCHEMICAL TECHNOLOGY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000266082200019)】；

语种：英文

外文关键词：residual oil; hydrodesulfurization (HDS); mechanism model; artificial neural network (ANN) model

摘要：Based on the Residual Oil Hydrodesulfurization Treatment Unit (S-RHT), the n-order reaction kinetic model for residual oil HDS reactions and artificial neural network (ANN) model were developed to determine the sulfur content of hydrogenated residual oil. The established ANN model covered 4 input variables, 1 output variable and 1 hidden layer with 15 neurons. The comparison between the results of two models was listed. The results showed that the predicted mean relative errors of the two models with three different sample data were less than 5% and both the two models had good predictive precision and extrapolative feature for the HDS process. The mean relative error of 5 sets of testing data of the ANN model was 1.62%-3.23%, all of which were smaller than that of the common mechanism model (3.47%-4.13%). It showed that the ANN model was better than the mechanism model both in terms of fitting results and fitting difficulty. The models could be easily applied in practice and could also provide a reference for the further research of residual oil HDS process.