Reliable estimation of optimal sulfinol concentration in gas treatment unit via novel stabilized MLP and regularization network

被引:6
作者
Asil, A. Garmroodi [1 ]
Shahsavand, A. [1 ]
机构
[1] Ferdowsi Univ Mashhad, Fac Engn, Dept Chem Engn, Mashhad, Iran
关键词
AGE; BTEX; Regularization network; MLP; Stabilized MLP; AQUEOUS-SOLUTIONS; NEURAL-NETWORKS; SELECTIVE ABSORPTION; SULFOLANE; H2S; CO2; MIXTURES; METHYLDIETHANOLAMINE; DIETHANOLAMINE; DEGRADATION;
D O I
10.1016/j.jngse.2014.09.033
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Proper technology or configuration for sulfur recovery units (SRUs) strongly depends on H2S concentration of inlet acid gas stream. Various acid gas enrichment (AGE) schemes with different solvents can be used to reduce the concentration of carbon dioxide and heavy aromatic hydrocarbons while enriching the H2S content of SRU feed stream. The present article uses combinations of Aspen-HYSYS software and two in-house artificial neural networks (namely, Regularization and stabilized multilayer perceptron networks) to compare the AGE capability of sulfinol-M (sulfolane + MDEA) solvent at optimal concentration with traditional MDEA solution when both of them are used in a conventional gas treating unit (GTU). The simulation results indicate that the optimal concentration of Sulfinol-M aqueous solution (containing 37 wt% Sulfolane and 45 wt% MDEA) will completely eliminate toluene and ethylbenzene from the SRU feed stream while removing 80% of benzene entering the GTU process. Furthermore, mole fraction of H2S in the SRU feed stream increases from the conventional 33.48 mol % to over 57 mol %. Increased H2S selectivity of optimal sulfinol-M aqueous solution will elevate the CO2 slippage through sweet gas stream at around 4.5 mol % which is still below the permissible threshold. To the best of our knowledge, the stabilized MLP network has not been addressed previously. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:791 / 804
页数:14
相关论文
共 45 条
  • [1] Support Vector Machine based modeling of an industrial natural gas sweetening plant
    Adib, Hooman
    Sharifi, Fatemeh
    Mehranbod, Nasir
    Kazerooni, Nooshin Moradi
    Koolivand, Mehdi
    [J]. JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2013, 14 : 121 - 131
  • [2] Al Utaibi A., 2010, United States Patent, Patent No. [US 2010/0219061 A1, 20100219061]
  • [3] Optimizations of Sulfolane concentration in propose Sulfinol-M solvent instead of MDEA solvent in the refineries of Sarakhs
    Angaji, Mahmood Torabi
    Ghanbarabadi, Hassan
    Gohari, Fatemeh Karimi Zad
    [J]. JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2013, 15 : 22 - 26
  • [4] Methyl-diethanolamine degradation - Mechanism and kinetics
    Chakma, A
    Meisen, A
    [J]. CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 1997, 75 (05) : 861 - 871
  • [5] Another look at statistical learning theory and regularization
    Cherkassky, Vladimir
    Ma, Yunqian
    [J]. NEURAL NETWORKS, 2009, 22 (07) : 958 - 969
  • [6] Chludzinski G., 1993, World Intellectual Property Organization, Patent Number, Patent No. [WO93,10883, 9310883]
  • [7] Crevier P.P., 2001, 51 LAUR REID GAS CON
  • [8] REGULARIZATION THEORY AND NEURAL NETWORKS ARCHITECTURES
    GIROSI, F
    JONES, M
    POGGIO, T
    [J]. NEURAL COMPUTATION, 1995, 7 (02) : 219 - 269
  • [9] Golub G. H., 1996, MATRIX COMPUTATIONS
  • [10] Haykin S., 1999, Neural Networks: A Comprehensive Foundation, DOI DOI 10.1017/S0269888998214044