Optimizing natural gas liquids (NGL) production process: A multi-objective approach for energy-efficient operations using genetic algorithm and artificial neural networks

Iranian Journal of Numerical Analysis and Optimization

مقاله 9، دوره 14، Issue 2 - شماره پیاپی 29، شهریور 2024، صفحه 522-544   

نوع مقاله: Research Article

شناسه دیجیتال (DOI): 10.22067/ijnao.2024.83955.1303

نویسندگان

N. Sabeghi^{* 1}؛ B. Kiani Talaei²؛ R. Ghanbari³؛ K. Ghorbani-Moghadam⁴

¹Department of Mathematics, Faculty of Basic Sciences, Velayat University, Iranshahr, Iran.

²University of Sistan and Baluchestan, Zahedan, Iran.

³Ferdowsi university of Mashhad, Mashhad, Iran.

⁴Mosaheb Institute of Mathematics, Kharazmi University, Tehran, Iran.

چکیده

There are various techniques for separating natural gas liquid (NGL) from natural gas, one of which is refrigeration. In this method, the temper-ature is reduced in the dew point adjustment stage to condense the NGLs. The purpose of this paper is to introduce a methodology for optimizing the NGLs production process by determining the optimal values for specific set-points such as temperature and pressure in various vessels and equip-ment. The methodology also focuses on minimizing energy consumption during the NGL production process. To do this, this research defines a multi-objective problem and presents a hybrid algorithm, including a ge-netic algorithm (NSGA II) and artificial neural network (ANN) system. We solve the defined multi-objective problem using NSGA II. In order to de-sign a tool that is a decision-helper for selecting the appropriate set-points, the ability of the ANN algorithm along with multi-objective optimization is evaluated. We implement our proposed algorithm in an Iranian chemical factory, specifically the NGL plant, which separates NGL from natural gas, as a case study for this article. Finally, we demonstrate the effectiveness of our proposed algorithm using the nonparametric statistical Kruskal–Wallis test.

کلیدواژه‌ها

Natural gas liquid (NGL)؛ Multi-objective optimization؛ Artifi-cial neural network؛ NSGA II

مراجع

[1] Alipanahi, E., Moradkhani, M.A., Zolfaghari, A., and Bayati, B. Robust intelligent approaches to predict the CO2 frosting temperature in natural gas mixtures under cryogenic conditions. Int. J. Refrig. 154 (2023) 281–289.
[2] Amidpour, M., Hamedi, M.H., Mafi, M., Ghorbani, B., Shirmohammadi, R., and Salimi, M. Sensitivity analysis, economic optimization, and con-figuration design of mixed refrigerant cycles by NLP techniques. J. Nat. Gas Sci. Eng. 24, (2015) 144–155.
[3] Ansari, R.M., and Tade, M.O. Nonlinear model based multivariable control of a debutanizer. J. Process Control, 8(4) (1998) 279–286.
[4] Arora, S., Shen, W., and Kapoor, A. Neural network based computational model for estimation of heat generation in LiFePO4 pouch cells of different nominal capacities. Comput. Chem. Eng. 101 (2017) 81–94.
[5] Bahmani, M., Shariati, J., and Rouzbahani, A.N. Simulation and opti-mization of an industrial gas condensate stabilization unit to modify LPG and NGL production with minimizing CO2 emission to the environment. Chin. J. Chem. Eng. 25(3) (2017) 338–346.
[6] Chebeir, J., Salas, S.D., and Romagnoli, J.A. Operability assessment on alternative natural gas liquids recovery schemes. J. Nat. Gas Sci. Eng. 71, (2019) 102974.
[7] Davoudi, M., Aleghafouri, A., and Safadoost, A. Flaring networks assess-ment in South Pars Gas processing plant. J. Nat. Gas Sci. Eng. 21, (2014) 221–229.
[8] Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T.A.M.T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2) (2002) 182–197.

[9] Dos Santos, R. M., Szklo, A., Lucena, A., and Poggio, M. Evaluating strategies for monetizing natural gas liquids from processing plants–Liquid fuels versus petrochemicals. J. Nat. Gas Sci. Eng. 99 (2022) 104413.
[10] Ebrahimi, A., and Khamehchi, E. Developing a novel workflow for nat-ural gas lift optimization using advanced support vector machine. J. Nat. Gas Sci. Eng. 28 (2016) 626–638.
[11] Fausett, L. V. Fundamentals of neural networks: architectures, algo-rithms and applications. Pearson Education India, 2006.
[12] Freund, J. E. Mathematical statistics. Second edition. Prentice-Hall, Inc., Englewood Cliffs, NJ, 1971.
[13] Kroese, D. P., Brereton, T., Taimre, T., and Botev, Z. I. Why the Monte Carlo method is so important today. Wiley Interdiscip. Rev.: Comput. Stat. 6(6) (2014) 386–392.
[14] Leperi, K.T., Yancy-Caballero, D., Snurr, R.Q., and You, F. 110th an-niversary: surrogate models based on artificial neural networks to simulate and optimize pressure swing adsorption cycles for CO2 capture. Ind. Eng. Chem. Res., 58(39), (2019) 18241–18252.
[15] Luyben, W. L. NGL demethanizer control. Ind. Eng. Chem. Res., 52(33), (2013) 11626–11638.
[16] Mehrpooya, M., Gharagheizi, F., and Vatani, A. An optimization of capital and operating alternatives in a NGL recovery unit. Chem. Eng. Technol.: Industrial Chemistry‐Plant Equipment‐Process Engineer-ing‐Biotechnology, 29(12), (2006) 1469–1480.
[17] Nascimento, C.A.O., Giudici, R., and Guardani, R. Neural network based approach for optimization of industrial chemical processes. Com-put. Chem. Eng. 24(9-10), (2000) 2303–2314.
[18] Park, Y.I., and Kim, J.H. Artificial neural network based prediction of ultimate buckling strength of liquid natural gas cargo containment system under sloshing loads considering onboard boundary conditions. Ocean Eng. 249, (2022) 110981.

[19] Roudari, S., Sadeghi, A., Gholami, S., Mensi, W., and Al-Yahyaee, K.H. Dynamic spillovers among natural gas, liquid natural gas, trade policy uncertainty, and stock market. Resour. Policy, 83, (2023) 103688.
[20] Rouzbahani, A.N., Bahmani, M., Shariati, J., Tohidian, T., and Rahim-pour, M.R. Simulation, optimization, and sensitivity analysis of a natural gas dehydration unit. J. Nat. Gas Sci. Eng. 21, (2014) 159–169.
[21] Safarvand, D., Aliazdeh, M., Samipour Giri, M., and Jafarnejad, M. Exergy analysis of NGL recovery plant using a hybrid ACOR‐BP neural network modeling: a case study. Asia‐Pacific J. Chem. Eng. 10(1) (2015) 133–153.
[22] Schweidtmann, A.M., Huster, W.R., Lüthje, J.T., and Mitsos, A. Deter-ministic global process optimization: Accurate (single-species) properties via artificial neural networks. Comput. Chem. Eng. 121, (2019) 67–74.
[23] Shang, C., Huang, X., Suykens, J.A., and Huang, D. Enhancing dy-namic soft sensors based on DPLS: A temporal smoothness regularization approach. J. Process Control, 28 (2015) 17–26.
[24] Shoghl, S.N., Naderifar, A., Farhadi, F., and Pazuki, G. Thermodynamic analysis and process optimization of a natural gas liquid recovery unit based on the Joule–Thomson process. J. Nat. Gas Sci. Eng. 96,(2021). 104265.
[25] Wang, Y., Zhang, Y., Wu, Z., Li, H., and Christofides, P.D. Operational trend prediction and classification for chemical processes: A novel convo-lutional neural network method based on symbolic hierarchical clustering. Chem. Eng. Sci. 225 (2020) 115796.
[26] Wasserman, L. All of nonparametric statistics. Springer Texts in Statis-tics. Springer, New York, 2006.
[27] Yunfei, Ch. and Fengqi, Y. Integrated planning, scheduling, and dynamic optimization for batch processes: MINLP model formulation and efficient solution methods via surrogate modeling. Ind. Eng. Chem. Res. 52(47) (2014) 16851–16869.