Black Box Modelling of Gasoil Hydrotreating by Artificial Neural Networks


gas oil
artificial neural networks.

How to Cite

Ghazi Otmanine, Kahina Bedda, Noureddine Bentahar. Black Box Modelling of Gasoil Hydrotreating by Artificial Neural Networks. Int. J. Petrol. Technol. [Internet]. 2014Nov.17 [cited 2022Jan.28];1(1):21-32. Available from:


Hydrotreating of gasoil is one of the most important processes in petroleum refining; it helps to improve the characteristics of diesel fuel to make it meet the required specifications and pollution standards. Modelling of this process would, among other things, allow to predict the product quality as a function of different process variables (temperature, pressure, space velocity). There are several modelling techniques, among them the Black Box type modelling by Artificial Neural Networks (ANNs), which is used to model the hydrotreating process at pilot scale. The approach used in this work is an artificial intelligence approach. The model developed is a neural network Multi Layer Perceptron (MLP) type. Network learning (NL) is carried out according to the Backpropagation Gradient algorithm with momentum; The Early Stopping (ES) technique has been used to prevent the effect of overfitting and thereby ensure a good generalization of the model. Experimental and predicted results show good agreement with an error not exceeding 4%.


Leprince P. Le Raffinage du Pétrole: Procédés de transformation. Editions Technip, Paris 1998; Vol. 3.

Courty P, Gruson JF. Refining clean fuel for the future. Oil Gas Sci Technol – Rev IFP 2001; 56: 551-524.

Kaminskii EF, Khavkin VA, Kurganov MV, et al. Production of ecological clean diesel fuels. Chem Technol Fuels Oils 1996; 32(2): 68-70

Bensaïd B, Saint-Antonin V. Le Diesel aux Etats-Unis, Panorama. Institut Français du Pétrole, Paris 2004.

Truex TJ, Pierson WR, McKee DE. Sulphate in Diesel Exhaust Environ Sci Technol 1980; 14(9): 1118-1121.

Guibet JC. in: Techniques de l’ingénieur, Carburants liquides, BE 8545 1998.

Guibet JC. Carburants et Moteurs. Editions Technip, Paris 1997; Vol. 2: pp. 505-506.

Girard C, Guibet JC, Billon A, et al. Technico-economic aspects and environmental impact of gas-oil desulphurization. International Congress: State of the Art. Potential. SIA, Lyon, France 1993.

Heinrich G, Kasztelan S, Kerdraon L. Diesel fuel upgrading: hydroprocessing for deep desulphurization and/or aromatics saturation, IFP Publication, Industrial Direction, Paris 1994.

Monot F, Warzywoda M. Désulfuration microbiologique des produits pétroliers. In: Vandecasteele J-P (ed) Microbiologie pétrolière, Concepts Implications Environnementales, Editions Technip, Paris 2005; Vol. I: pp. 737-755.

Lacey PJ, Lestz SJ. Effects of low lubricity fuels on diesel injection pumps. Part 1: field performance, part 2: laboratory evaluation. SAE 920823 and 920824 1992.

Korres DM, Anastopoulos GE, Lois A, et al. A neural network approach to the prediction of diesel fuel lubricity. Fuel 2002; 81: 1243-1250.

Knudsen GK, Cooper HB, Topsoe H. Catalyst and process technologies for ultra low sulphur diesel. Appl Catal A 1999; 189: 205-215.

Eijsbouts S. Life cycle of hydroprocessing catalysts and total catalyst management. Stud Surf Sci Catal 1999; 127: 21-36.

Fujikaa T, Kimura H, Kiriyama K, et al. Development of ultradeep HDS catalysts for production of clean diesel fuels. Catal Today 2006; 111: 188-193.

Deuk KL, In Chul L, Seong IW. Effects of transition metal addition to Co/Mo ?-Al2O3 catalyst on the hydrotreating reactions of atmospheric residual oil. Appl Catal A 1994; 109(2): 195-210.

Grange P, Vanhaeren X. Hydrotreating catalysts, and old story with new challenges. Catal Today 1997; 36: 375-391.

Pinzon HM, Merino LI, Centeno A, et al. Performance of noble metal-Mo/?Al2O3 catalysts: Effect of preparation parameters. Stud Surf Sci Catal 1999; 127: 97-104.

Pessayre S, Geantet C, Bacaud R, et al. Platinum doped hydrotreating catalysts for deep hydrodesulfurization of diesel fuels. I & EC Research 2007; 46: 3877-3883.

Ramirez S, Cabreara C, Aguilar C, et al. Two stages light gasoil hydrotreating for low sulphur diesel production. Catalysis Today 2004; 98: 323-332.

Vradman L, Landau MV, Herskowitz M. Deep desulphurization of diesel fuels: kinetic modeling of model compounds in trickle-bed. Catal Today 1999; 48: 41-48.

Cotta RM, Maciel MRW, Filho RM. A cape of HDT industrial reactor for middle distillates. Comput Chem Eng 2000; 24: 1731-1735.

Froment GF. Modeling in the development of hydrotreatment processes. Catal Today 2004; 98: 43-54.

Murali C, Voolapalli RK, Ravichander N, et al. Trickle bed reactor model to simulate the performance of commercial diesel hydrotreating unit. Fuel 2006; doi:10. 1016/j.fuel. 09 019.

Boumahrat M, Gourdin A. Méthodes numériques appliquées. Office des Publications Universitaires, Algérie 1993.

William L, Luyben. Process modelling, simulation and control for chemical engineers. Mc Graw-Hill, International Edition, USA 1990.

Wang Z, Yang B, Chen CJ. Modelling and optimization for the secondary reaction of FCC gasoline based on the fuzzy neural network and genetic algorithm. Chem Eng Process 2007; 46: 175-180.

Farouk S, Mjalli S, A-Ashed HE, et al. Use of artificial neural network black-box modelling for the prediction of waste water treatment plants performance. Environ Manage 2007; 83: 329-338.

Reza M, Nasr J, Givi MM. Modeling of crude oil fouling in preheat exchangers of refinery distillation units. Appli Therm Eng 2006; 26: 1572-1527.

Dreyfus G, Martinez JM, Samuelides M, et al. Réseaux de neurones: Méthodologie et applications, Editions Eyrolles, Paris 2004.

Corriou JP. Les réseaux de neurones pour la modélisation et la conduite des procédés, Lavoisier Technique et Documentation, Paris 1995.

Nerrand O, Roussel-Ragot P, Personnaz L, Dreyfus G, Marcos S. Neural networks and nonlinear adaptive filtering: unifying concept and new algorithms. Neural Comput 1993; 5: 165-197.

Weimin L, Wenkai L, Hui C-W. Integrating neural network models for refinery planning. Comput Aided Chem Eng 2003; 15: 1304-1309. 8th International Symposium on Process Systems Engineering doi: 10.1016/S1570-7946

Baroutian S, Aroua MK, Raman AA, Sulaiman NM. Estimation of vegetable oil-based ethyl esters biodiesel densities using artificial neural networks. J Appl Sci 2008; 8(17): 3005-3011.

Ramadhas AS, Jayray S, Muraleedhanan C Padmakumari KJ. Artificial Neural Networks used for the prediction of cetane number of Biodiesel. J Renewable Energy 2006; 31: 2524-2533.

Barron AR. Universal Approximation bounds for superposition of a sigmoidal function. IEEE T Inform Theory 1993; IT-39: 930-945.

Demuth H, Beale M, Hagan M. Neural Network Toolbox 5: User’s Guide, Guide d’utilisation des réseaux de neurones sur le logiciel MATLAB 2007.