پیش‌بینی کارایی تعلیق شکن‌های تجاری جداکننده آب شور از امولسیون نفت خام به کمک ماشین بردار پشتیبان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی شیمی، دانشگاه صنعتی امیرکبیر (پلی تکنیک تهران)، تهران، ایرانن

2 دانشکده مهندسی شیمی، دانشگاه صنعتی امیرکبیر (پلی تکنیک تهران)، تهران، ایران

3 دانشکده مهندسی نساجی، دانشگاه صنعتی امیرکبیر (پلی تکنیک تهران)، تهران، ایران

10.22078/pr.2024.5189.3304

چکیده

امولسیون آب شور در نفت خام موجب کاهش ارزش نفت خام، مسمومیت کاتالیست‌ها در صنایع پایین دستی و خوردگی تجهیزات در بخش‌های مختلف انتقال، پالایش و نگهداری نفت خام می‌شود. متداول‌ترین روش صنعتی جداسازی آب شور از نفت خام، استفاده از ترکیبات شیمیایی می باشد.تامین ترکیبات شیمیایی مورد نیاز هزینه قابل توجهی دارد. به علاوه عملکرد تعلیق شکن‌های شیمیایی وابستگی بسیار زیادی به نوع نفت خام دارد. پیچیدگی موجود در ساختار نفت خام باعث می‌شود مدل سازی عملکرد تعلیق شکن‌ها دشوار باشد. به منظور کاهش تعداد پارامترهای مهم نفت خام از نسبت آسفالتین به مجموع رزین و آروماتیک به عنوان مولفه نفت خام استفاده شد. با توجه به پیچیدگی مدل مدنظر، از ماشین بردار پشتیبان به منظور پیش‌بینی عملکرد تعلیق شکن‌های تجاری استفاده شد. مهم‌ترین چالش در ماشین‌های بردار پشتیبان تنظیم فراپارامترها می باشد. در این مطالعه برای تنظیم فراپارامترها از معیار ریسک در پیش بینی راندمان های بالاتر از 85% و افزایش ضریب همبستگی استفاده شد. به منظور جمع‌آوری داده های مدل‌سازی، چهار نمونه نفت خام به همراه دو نمونه تعلیق شکن تجاری رایج در واحدهای بهره‌برداری میادین جنوب غرب کشورتهیه و با استفاده از روش بطری، عملکرد تعلیق شکن تجاری در شرایط عملیاتی مختلف بررسی شد. عملکرد الگوریتم پیشنهادی برای تنظیم فراپارامترها با الگوریتم بهینه‌سازی بیزین مورد مقایسه قرارگرفت. نتایج نشان می‌دهد تنظیم فراپارامترهای ماشین بردار پشتیبان با معیار ریسک کمک می‌کند یک مدل با دقت بهتر برای پیش‌بینی عملکرد تعلیق شکن‌های تجاری طراحی شود. با توجه به اهمیت مدل‌سازی عملکرد مواد تعلیق شکن در صنعت نفت، اعتبار سنجی مدل با یک نمونه امولسیون جدید مورد بررسی قرار گرفت. نتایج نشان می‌دهد ماشین بردار پشتیبان می‌تواند مدلی کارامد برای پیش‌بینی تعلیق شکن‌های تجاری ارائه کند. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Predicting the Performance of Commercial Demulsifiers for Separating Brine Water from Crude Oil Emulsion using Support Vector Machine

نویسندگان [English]

  • Hassan Talebi 1
  • Mehrdad Mozaffarian 2
  • Bahram Dabir 2
  • Nima Esmaeilian 3
1 Department of Chemical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
2 Department of Chemical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
3 Department of Textile Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
چکیده [English]

The emulsion of salt water in crude oil causes reduction of crude oil quality, catalyst poisoning in downstream industries, and equipment corrosion in various parts of crude oil transportation, refining and storage systems. The most common industrial method for separating saline water from crude oil is the application of chemical compounds. Procuring the required chemical compounds will cost a lot. In addition, the performance of chemical demulsifiers is highly dependent on the type and structure of crude oil. The complexity of crude oil’s structure makes it difficult to develop performance models for demulsifiers. In order to reduce the number of important parameters of crude oil in modeling, the ratio of asphaltene to the total of resin and aromatic was used as the discriminating factor of crude oil emulsion process. Considering the complexity of the considered model, a support vector machine was used to predict the performance of commercial demulsifiers. The most important challenge in support vector machines is tuning hyperparameters. To tune the hyperparameters in this study, the risk criterion was used in predicting efficiencies higher than 85% and increasing the correlation coefficient. In order to collect modeling data, four samples of crude oil along with two samples of common commercial demulsifiers were prepared in the Production units of the southwestern fields of the country, and the performance of commercial demulsifiers at different operating conditions was checked using the bottle test method. The performance of the proposed algorithm for tuning hyperparameters was compared with the Bayesian optimization algorithm. The results show that adjusting the support vector machine hyperparameter with the risk criterion helps to design a model with better accuracy for predicting the performance of commercial demulsifiers. Considering the importance of modeling the performance of demulsifiers in petroleum industry, the evaluation of the model was investigated with a new emulsion sample. The results show that support vector machine can provide an efficient model for predicting the performance of commercial demulsifiers.

کلیدواژه‌ها [English]

  • Demulsification
  • Chemical Demulsifier
  • Support Vector Machine (SVM)
  • Emulsion Stability Index
  • Artificial Intelligence

مراجع

[1]. Abdel Raouf M. E. (2012). Crude oil emulsions- composition stability and characterization, Edition 1, Crude Oil Emulsions- Composition Stability and Characterization, BoD–Books on Demand, InTech. https://doi.org/10.5772/2677.##
[2]. Vafajoo, L., Ganjian, K., and Fattahi, M. (2012). Influence of key parameters on crude oil desalting: An experimental and theoretical study, Journal of Petroleum Science and Engineering, 90, 107–111, doi.org/10.1016/j.petrol.2012.04.022.##
[3]. Bhardwaj, A. and Hartland, S. (1994). Dynamics of emulsification and demulsification of water in crude oil emulsions, Industrial & Engineering Chemistry Research, 33(5), 1271–1279. https://doi.org/10.1021/ie00029a025.##
[4]. Speight, J. G. (2014). Chapter 3 - Corrosion in Refinery Units (J. G. B. T.-O. and G. C. P. Speight (Ed.),39–66, Gulf Professional Publishing, doi.org/10.1016/B978-0-12-800346-6.00003-X.##
[5]. Talebi, H., Maghsoudy, S., and Habibzadeh, S. (2022). Synthesis and characterization of corrosion inhibitor nanoparticles in oil and gas industry, Iranian Chemical Engineering Journal, 21(124), 7–29, doi.org/10.22034/ijche.2021.309739.1144.##
[6]. Saad, M. A., Kamil, M., Abdurahman, N. H., Yunus, R. M., and Awad, O. I. (2019). An overview of recent advances in state-of-the-art techniques in the demulsification of crude oil emulsions, Processes, 7(7), 470, doi.org/10.3390/pr7070470.##
[7]. Ramirez-Corredores, M. M. (2017). Asphaltenes. In The Science and Technology of Unconventional Oils, 41–222, Elsevier, doi.org/10.1016/B978-0-12-801225-3.00002-4.##
[8]. Lashkarbolooki, M. and Ayatollahi, S. (2018). Effects of asphaltene, resin and crude oil type on the interfacial tension of crude oil/brine solution. Fuel, 223, 261–267. doi.org/https://doi.org/10.1016/j.Fuel.2018.03.029.##
[9]. Schorling, P. C., Kessel, D. G. and Rahimian, I. (1999). Influence of the crude oil resin/asphaltene ratio on the stability of oil/water emulsions, Colloids and Surfaces A: Physicochemical and Engineering Aspects, 152(1): 95–102, doi.org/10.1016/S0927-7757(98)00686-4.##
[10]. Kokal, S. and Al-Juraid, J. (1999). Quantification of various factors affecting emulsion stability: watercut, temperature, shear, asphaltene content, demulsifier dosage and mixing different crudes, In Proceedings - SPE Annual Technical Conference and Exhibition, 2 (PI), 91–99, doi.org/10.2118/56641-ms.##
[11]. Rondón, M., Pereira, J. C., Bouriat, P., Graciaa, A., Lachaise, J. and Salager, J. L. (2008). Breaking of water-in-crude-oil emulsions. 2. influence of asphaltene concentration and diluent nature on demulsifier action, Energy & Fuels, 22(2), 702–707. doi.org/10.1021/ef7003877.##
[12]. Ramalho, J. B. V. S., Lechuga, F. C. and Lucas, E. F. (2010). Effect of the structure of commercial poly (ethylene oxide-b-propylene oxide) demulsifier bases on the demulsification of water-in-crude oil emulsions: elucidation of the demulsification mechanism, Quimica Nova, 33, 1664–1670, https://doi.org/10.1590/S0100-40422010000800009 .##
[13]. Shi, Y., Chen, J. and Meng, H. (2022). Experimental study on the performance of an electric field enhanced separator for crude oil production fluid, Journal of Petroleum Science and Engineering, 212, 110315, doi.org/10.1016/j.petrol.2022.110315.##
[14]. Tadros, T. F. (2005). Applied Surfactants, Wiley, doi.org/10.1002/3527604812.##
[15]. Ahmadi, S., Khormali, A. and Meerovich Khoutoriansky, F. (2022). Optimization of the demulsification of water-in-heavy crude oil emulsions using response surface methodology, Fuel, 323, 124270, doi.org/10.1016/j.fuel.2022.124270.##
[16]. Adewunmi, A. A., Kamal, M. S. and Olatunji, S. O. (2022). Demulsification of crude oil emulsions using ionic liquids: A computational intelligence approach, Journal of Petroleum Science and Engineering, 208, 109279, doi.org/10.1016/j.petrol.2021.109279.##
[17]. Dhandhi, Y., Prakash, O., Naiya, T. K. and Guria, C. (2022). Statistical design and process optimization for using chemical demulsifiers for the dehydration of the crude oil, Journal of Petroleum Science and Engineering, 217, 110876, doi.org/10.1016/j.petrol.2022.110876.##
[18]. Uetani, T., Kai, J., Hitomi, T., Seino, H., Shimbori, K. and Yonebayashi, H. (2020). Experimental investigation of crude-oil emulsion stability: effect of oil and brine compositions, asphaltene, wax, toluene insolubles, temperature, shear stress, and water cut, In SPE Production and Operations, 35, 2: 320–334, doi.org/10.2118/192064-PA.##
[19]. Kazemzadeh, Y., Ismail, I., Rezvani, H., Sharifi, M. and Riazi, M. (2019). Experimental investigation of stability of water in oil emulsions at reservoir conditions: Effect of ion type, ion concentration, and system pressure, Fuel, 243, 15–27, doi.org/10.1016/j.fuel.2019.01.071.##
[20]. Lashkarbolooki, M. and Ayatollahi, S. (2018). The effects of pH, acidity, asphaltene and resin fraction on crude oil/water interfacial tension, Journal of Petroleum Science and Engineering, 162, 341–347, doi.org/10.1016/j.petrol.2017.12.061.##
[21]. Malley, J. D., Malley, K. G. and Pajevic, S. (Eds.). (2011). Error analysis and model validation, In statistical learning for biomedical data, 215–244, Cambridge University Press, doi: 10.1017/CBO9780511975820.012.##
[22]. Wang, Y. G., Wu, J., Hu, Z.-H. and McLachlan, G. J. (2023). A new algorithm for support vector regression with automatic selection of hyperparameters, Pattern Recognition, 133, 108989, doi.org/10.1016/j.patcog.2022.108989.##
[23]. Apriyadi, M. R., Ermatita and Rini, D. P. (2023). Hyperparameter optimization of support vector regression algorithm using metaheuristic algorithm for student performance prediction, International Journal of Advanced Computer Science and Applications, 14(2), 144–150, doi.org/10.14569/IJACSA.2023.0140218.##
[24]. Zhou, T., Hu, Q., Hu, Z. and Zhen, R. (2022). An adaptive hyper parameter tuning model for ship fuel consumption prediction under complex maritime environments, Journal of Ocean Engineering and Science, 7(3), 255–263, doi.org/10.1016/j.joes.2021.08.007.##
[25]. Alvarado, J. G., Delgado-Linares, J. G., Forgiarini, A. M. and Salager, J. L. (2019). Breaking of water-in-crude oil emulsions. 8. demulsifier performance at optimum formulation is significantly improved by a small aromatic content of the oil, Energy & Fuels, 33(3), 1928–1936, doi.org/10.1021/acs.energyfuels.8b03994.##
[26]. Umar, A. A., Nnakenyi, N. I., Abba, M. K. and Roy-Omeni, I. H. (2021). Surfactants as integral components of chemical demulsifiers BT - surfactants in upstream E&P (T. Solling, M. Shahzad Kamal, & S. M. Shakil Hussain (Eds.), 443–466, Springer International Publishing, doi.org/10.1007/978-3-030-70026-3_16##
[27]. Awad, M. and Khanna, R. (2015). Support Vector Regression, In Efficient Learning Machines, 67–80, Apress, doi.org/10.1007/978-1-4302-5990-9_4.##
[28]. Forghani, Y., Tabrizi, R. S., Yazdi, H. S., & Akbarzadeh-T, M. R. (2008). Support Vector Machines, In 2011 1st International eConference on Computer and Knowledge Engineering, ICCKE 2011, Springer New York, doi.org/10.1007/978-0-387-77242-4.##
پژوهش نفت
دوره 34، 1403-1 - شماره پیاپی 134
فروردین و اردیبهشت 1403
صفحه 3-23

فایل ها

هم رسانی

ارجاع به این مقاله

آمار