ANN and RSM Modelling and Optimization of Paraffins and Aromatics in Crude Oil Distillation Products’ Properties in Iraq

Abstract

Back-Propagation neural networks, as well as RSM-DOE techniques, were used to predict the properties of various compositions of Iraqi oil, which were presented in this study. Paraffin and Aromatics’ effect on petroleum properties, e.g., yield, density, calorific value, and other essential properties, were studied. The input-output data to the neural networks were obtained from existing local refineries in Iraq. Several network activation functions to simulate the hydrocracking process were tested and compared. the network function that gave satisfactory results in terms of convergence time and accuracy was adopted. The data were divided into training and testing parts. The results of the trained artificial neural network models for each one of the tested functions have been cross-validated with the experimental data. The network that compared well against this new set of data (i.e. testing data), with an average percent error always less than 3% for the various products of the hydrocracking unit were chosen for the study. Aromatics showed to have more profound effect on the Octane number at low concentrations of paraffin, while, for specific gravity and calorific value they have similar effects. As for boiling points and sulfur contents, aromatics have almost no effect at lower levels of paraffin.

Keywords

• RSM
• DOE
• Petroleum distillation
• Artificial neural networks
• Aromatics and paraffin

References

1. [1] Muhsin, W. A., Zhang, J. and Lee, J., “Modelling and Optimization of a Crude Oil Hydrotreating Process Using Neural Networks”, Chemical Engineering Transactions, 52: 211-6, (2016).
2. [2] Muhsin, W. A. S., Jie, Z. and Jonathan, L., “Modelling and Optimisation of a Crude Oil Hydrotreating Process Using Neural Networks”, 19th Conference on Process Integration, Modelling and Optimisation for Energy Saving and Pollution Reduction (PRES 2016). Newcastle University, (2016).
3. [3] Kaiser, M., De Klerk, A., Gary, J. and Handwerk, G., Petroleum Refining: Technology, Economics, and Markets New York: CRC Press, (2019).
4. [4] Speight, J. G., The chemistry and technology of petroleum New York: CRC Press, (2019).
5. [5] Ancheyta, J., Rana, M. S. and Furimsky, E., “Hydroprocessing of heavy petroleum feeds: Tutorial”, Catalysis Today, 109: 3-15, (2005).
6. [6] Bahmani, M., Sharifi, K., Shirvani, M., Street, M. and Street, N., “Product yields prediction of Tehran refinery hydrocracking unit using artificial neural networks”, Iranian Journal of Chemical Engineering, 7: 50-63, (2010).
7. [7] Kidoguchi, Y., Yang, C., Kato, R. and Miwa, K., “Effects of fuel cetane number and aromatics on combustion process and emissions of a direct-injection diesel engine”, JSAE Review, 21: 469-75, (2000).
8. [8] Tsurutani, K., Takei, Y., Fujimoto, Y., Matsudaira, J. and Kumamoto, M., “The effects of fuel properties and oxygenates on diesel exhaust emissions”, SAE Technical Paper, 1995 Oct 1, (1995).

9. [9] Karonis, D., Lois, E., Stournas, S. and Zannikos, F., “Correlations of exhaust emissions from a diesel engine with diesel fuel properties”, Energy & Fuels, 12: 230-8, (1998).
10. [10] Sienicki, E. J., Jass, R. E., Slodowske, W. J., McCarthy, C. I. and Krodel, A. L., “Diesel fuel aromatic and cetane number effects on combustion and emissions from a prototype”, 1991 diesel engine. SAE Technical Paper, 1990 Oct 1, (1991).
11. [11] Shekhawat, D., Berry, D. A., Haynes, D. J. and Spivey, J. J., “Fuel constituent effects on fuel reforming properties for fuel cell applications”, Fuel, 88: 817-25, (2009).
12. [12] Rodríguez-Fernández, J., Hernández, J. J. and Sánchez-Valdepeñas, J., “Effect of oxygenated and paraffinic alternative diesel fuels on soot reactivity and implications on DPF regeneration”, Fuel, 185: 460-7, (2016).
13. [13] Soriano, J. A., García-Contreras, R., Gómez, A. and Mata, C., “Comparative study of the effect of a new renewable paraffinic fuel on the combustion process of a light-duty diesel engine”, Energy, 189: 116337, (2019).
14. [14] Soriano, J. A., García-Contreras, R., Leiva-Candia, D. and Soto, F., “Influence on performance and emissions of an automotive diesel engine fueled with biodiesel and paraffinic fuels: GTL and biojet fuel farnesane”, Energy & Fuels, 32: 5125-33, (2018).
15. [15] Ruslan, M., Ahmed, I. and Khandelwal, B., “Evaluating effects of fuel properties on smoke emissions”, InTurbo Expo: Power for Land, Sea, and Air 2016 Jun 13 (Vol. 49750, p. V04AT04A046). ASME, (2016).
16. [16] Karavalakis, G., Short, D., Vu, D., Russell, R., Hajbabaei, M., Asa-Awuku, A. and Durbin, T. D., “Evaluating the effects of aromatics content in gasoline on gaseous and particulate matter emissions from SI-PFI and SIDI vehicles”, Environmental Science and Technology, 49(11): 7021-7031, (2015).
17. [17] Jehad, A. A. Y. and Eiman A. E. S., “Potential Utilization of Iraqi Associated Petroleum Gas as Fuel for SI Engines”, Jordan Journal of Mechanical and Industrial Engineering, 14: 349-359, (2020).
18. [18] Nagata, Y., Chu, K. H., “Optimization of a fermentation medium using neural networks and genetic algorithms”, Biotechnology Letters, 25: 1837-42, (2003).
19. [19] Razmi-Rad, E., Ghanbarzadeh, B., Mousavi, S. M., Emam-Djomeh, Z. and Khazaei, J., “Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by using artificial neural networks”, Journal of Food Engineering, 81: 728-34, (2007).
20. [20] Hornik, K., Stinchcombe, M. and White, H., “Multilayer feedforward networks are universal pproximators”, Neural Network, 2: 359-66, (1989).
21. [21] Wang, J., Wan, W., “Optimization of fermentative hydrogen production process using genetic algorithm based on neural network and response surface methodology”, International Journal of Hydrogen Energy, 34: 255-61, (2009).
22. [22] Maran, J. P., Sivakumar, V., Thirugnanasambandham, K. and Sridhar, R., “Artificial neural network and response surface methodology modeling in mass transfer parameters predictions during osmotic dehydration of Carica papaya L”, Alexandria Engineering Journal, 52: 507-16, (2013).
23. [23] Dahlan, I., Ahmad, Z., Fadly, M., Lee, K. T., Kamaruddin, A. H. and Mohamed, A. R., “Parameters optimization of rice husk ash (RHA)/CaO/CeO2 sorbent for predicting SO2/NO sorption capacity using response surface and neural network models”, Journal of Hazardous Materials, 178: 249-57, (2010).
24. [24] Anish, T. and Kumar, M.V. P., “Multi-objective optimization of a fluid catalytic cracking unit using response surface methodology”, Chemical Product and Process Modeling, (2022).
25. [25] Festus, A. M., Odunayo, T. Ore, and Oluwaseun, T. A., “Desulphurization of crude oil using caustic soda: process modelling and optimization”, Petroleum Science and Technology, 1-20, (2022).
26. [26] Nalini, G. and Shobhit, N., “Crude oil price prediction using artificial neural network”, Procedia Computer Science, 170: 642-647, (2020).
27. [27] Lluvia M., Megan, J. and Robin S., “Operational optimization of crude oil distillation systems using artificial neural networks”, Computers and Chemical Engineering, 59: 178-185, (2013).
28. [28] Vo Thanh, H., Yuichi, S. and Kyuro, S., “Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones”, Scientific reports, 10.1, 1-16, (2020).
29. [29] Alkinani, H. H., Al-Hameedi, A. T., Dunn-Norman, S., Flori, R. E., Alsaba, M. T. and Amer, A. S., “Applications of artificial neural networks in the petroleum industry: a review”, In SPE middle east oil and gas show and conference. OnePetro, (2019, March).
30. [30] https://www.enggcyclopedia.com/2011/01/octane-number/. Access date: 5.12.2022.
31. [31] Worsfold, P., Townshend, A., Poole, C. F. and Miró, M., “Encyclopedia of analytical science”, Elsevier, (2019).
32. [32] El-Bassiouny, A. A., Aboul-Fotouh, T. M. and Abdellatief, T. M., “Upgrading the commercial gasoline A80 by using ethanol and refinery products”, International Journal of Scientific and Engineering Research, 6(8): 405-417, (2015).