Prediction of Sulfur Content in Desulfurization Process Using a Fuzzy-Logic Based Model

Abstract:

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).

• Periodical: Solid State Phenomena (Volume 287)
• Pages: 80-85
• DOI: https://doi.org/10.4028/www.scientific.net/SSP.287.80
• Online since: February 2019
• Authors: Hamdi A. Al-Jamimi*
• Keywords: Desulphurization, Fuzzy Logic, Prediction Models, Sulfur Content

References

[1] L. A. Zadeh, Fuzzy Sets, Information and Control,, vol. 8 pp.338-353, (1965).

[2] M. Kazemimoghadam and N. Sadeghi, Modeling Desulfurization of diesel by use of polymer membranes with the help of Artificial Neural Network,, Research and Reviews in Environmental Chemistry, vol. 1, pp.1-7, (2017).

[3] G. Bellos, et al., Modelling of the performance of industrial HDS reactors using a hybrid neural network approach,, Chemical Engineering and Processing: Process Intensification, vol. 44, pp.505-515, (2005).

DOI: 10.1016/j.cep.2004.06.008

[4] D. Salari and K. Rostamizadeh, Oxidative Desulfurization of Fuel Oil: Modeling Based on Artificial Neural Network,, Petroleum Science and Technology, vol. 26, pp.382-397, (2008).

DOI: 10.1080/10916460600809592

[5] I. Lukec, et al., Prediction of sulphur content in the industrial hydrotreatment process,, Fuel Processing Technology, vol. 89, pp.292-300, (2008).

DOI: 10.1016/j.fuproc.2007.11.032

[6] E. Arce-Medina and J. I. Paz-Paredes, Artificial neural network modeling techniques applied to the hydrodesulfurization process,, Mathematical and Computer Modelling, vol. 49, pp.207-214, (2009).

DOI: 10.1016/j.mcm.2008.05.010

[7] W. Wang, et al., Simulation of hydrodesulfurization using artificial neural network,, The Canadian Journal of Chemical Engineering, vol. 88, pp.801-807, (2010).

[8] Z. Hajjar, et al., Artificial intelligence techniques for modeling and optimization of the HDS process over a new graphene based catalyst,, Phosphorus, Sulfur, and Silicon and the Related Elements, vol. 191, pp.1256-1261, (2016).

DOI: 10.1080/10426507.2016.1166428

[9] S. Shokri, et al., Integrating principal component analysis and vector quantization with support vector regression for sulfur content prediction in HDS process,, Chemical Industry and Chemical Engineering Quarterly, vol. 21, pp.379-390, (2015).

DOI: 10.2298/ciceq140418039s

[10] S. Shokri, et al., Soft sensor design for hydrodesulfurization process using support vector regression based on WT and PCA,, Journal of Central South University, vol. 22, pp.511-521, (2015).

DOI: 10.1007/s11771-015-2550-6

[11] L. A. Zadeh, Fuzzy sets,, Information and control, vol. 8, pp.338-353, (1965).

[12] E. H. Mamdani and S. Assilian, An experiment in linguistic synthesis with a fuzzy logic controller,, Int. J. Man-Mach. Stud., vol. 7, p.1–13, (1975).

DOI: 10.1016/s0020-7373(75)80002-2

[13] B. Rezaee, Desulfurization process using Takagi–Sugeno–Kang fuzzy modeling,, The International journal of advanced manufacturing technology, vol. 46, pp.191-197, (2010).

DOI: 10.1007/s00170-009-2031-x