مدل‌سازی تبدیل گاز سنتز و بررسی درصد تبدیل هیدروژن و منوکسیدکربن توسط شبکه عصبی براساس آزمایشات تجربی در راکتور بستر ثابت

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی شهید نیکبخت، دانشگاه سیستان و بلوچستان، زاهدان، ایران

2 گروه مهندسی شیمی، دانشگاه صنعتی بیرجند، بیرجند، ایران

چکیده

در این پژوهش، براساس داده‌ها و آزمایشات تجربی به بررسی درصد تبدیل هیدروژن و منوکسیدکربن و طراحی مدل آنها براساس طراحی آزمایش و شبکه عصبی پرداخته شد. داده‌های آزمایشگاهی براساس پنج متغیر ورودیو براساس طراحی مکعب مرکزی تعیین گردید. این پنج متغیر موثر عبارتند از: دما، فشار راکتور، نسبت هیدروژن به منوکسید کربن در خوراک، فشار جزئی هیدروژن و منوکسید کربن در راکتور. شرایط عملیاتی راکتور، دما ( oC340-320)، فشار (bar gauge 8-2)، نسبت هیدروژن به منوکسیدکربن (2/2- 8/0)، فشار جزئی منوکسیدکربن (bar gauge 7/2-3/0) و فشار جزئی هیدروژن (bar gauge 5/2-3/0) می‌باشد. برای بررسی و به‌دست آوردن مدل درصد تبدیل‌ها، از دو روش پاسخ سطح و شبکه عصبی استفاده گردید. برای بررسی توانمندی هر دو روش، دو پارامتر مهم خطای آماری شامل مجذور میانگین خطا و انحراف نسبی میانگین مطلق محاسبه شد. نتایج به‌دست آمده از هر دو مدل پاسخ سطح و شبکه عصبی با نتایج تجربی مقایسه شد. مشاهده گردید که هر دو مدل تطابق خوبی با داده‌های تجربی دارند. برای محاسبه بیشینه درصد تبدیل برای هر دو مدل، شبکه عصبی با الگوریتم ژنتیک مدل شده و نقاط بیشینه هر دو مدل غیرخطی به‌دست آمد. در پایان، مدل‌های حاصله تحلیل شده و نقاط بیشینه مورد بررسی قرار گرفت. همچنین این مدل می‌تواند برای به‌دست آوردن محصولات انتخابی با ارزش افزوده بالا نیز به‌کار گرفته شود.
 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Investigation of H2 and CO and Modeling of Syngas Conversion by Artificial Neural Network Based on Experimental Data in a Fixed-bed Reactor

نویسندگان [English]

  • Afshin Razmjooie 1
  • Hossein Atashi 1
  • Farhad Shahraki 1
  • Mehdi Shiva 2
1 Department of Chemical Engineering, University of Sistan and Baluchestan, Zahedan, Iran
2 Department of Chemical Engineering, Birjand Industrial University, Birjand, Iran
چکیده [English]

In this research, the application of design of experiment and artificial neural network on conversion of H2 and CO were studied based on the experimental data. The experimental data has been collected from five independent variables based on central composite design such as temperature and pressure of reactor, H2/CO feed ratio, and partial pressure of H2 and CO in reactor. The operating conditions are: T = 320-340°C, P = 2-8 barg, H2/CO = 0.8-2.2, PCO = 0.3-2.7 barg, and PH2 = 0.3-2.5 barg. To generate the conversion models, two methods consist of response surface methodology and artificial neural network were used. The capability and sensitivity of both models were evaluated by some statistical parameters including mean square error and absolute average relative deviation. The result of both models were compared with experimental data and show the best results. To evaluate the maximum conversion of (H2 and CO), a hybrid ANN/GA was performed to solve the nonlinear both models. Finally, all quadratic equations and maximum of both models were performed, and the results were concluded. Also, this method can be used to produce the valuable selective production.
 

کلیدواژه‌ها [English]

  • Fischer-tropsch Synthesis
  • Conversion of Syngas (or Synthesis Gas)
  • Response Surface Methodology
  • Artificial Neural Network
  • Genetic Algorithm
[1]. Fu T., Lv J. and Li Z. , “Effect of carbon porosity and cobalt particle size on the catalytic performance of carbon supported cobalt fischer–tropsch catalysts,” Industrial & Engineering Chemistry Research, Vol. 53(4): pp. 1342-1350, 2014.##
[2]. Adib, H., Haghbakhsh R., Saidi M., Ali Takassi M., Sharifi F., Koolivand M., Rahimpour M. R. and Keshtkari S., “Modeling and optimization of fischer–tropsch synthesis in the presence of co (iii)/al 2 o 3 catalyst using artificial neural networks and genetic algorithm,” Journal of Natural Gas Science and Engineering, Vol. 10, pp. 14-24, 2013..##
[3]. Bayat, M., Hamidi M., Dehghani Z., Rahimpour M. R. and A. Shariati, “Sorption-enhanced reaction process in fischer–tropsch synthesis for production of gasoline and hydrogen: mathematical modeling,” Journal of Natural Gas Science and Engineering, Vol. 14, pp. 225-237, 2013.##
[4]. Chiang S. W., Chang Ch. Ch., Shie J. L., Chang Ch. Y., Ji D. R. and Tseng J. Y., “Synthesis of alcohols and alkanes over potassium and vanadium promoted molybdenum carbides,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 43(6), pp. 918-925, 2012.##
[5]. Hemmati, M.R., Hemmati M. R., Kazemeini M., Khorasheh F. and Zarkesh J., “Investigating the effect of cacination repetitions on the lifetime of Co/γ-Al2O3 catalysts in fischer–tropsch synthesis utilising the precursor›s solution affinities,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 44(2): pp. 205-213, 2013.##
[6]. Feyzi M., Khodaei M. M. and Shahmoradi J., “Effect of sulfur on the catalytic performance of fe–Ni/al2O3 catalysts for light olefins production,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 45(2): pp. 452-460, 2014.##
[7]. Schulz H., “Short history and present trends of fischer–tropsch synthesis,” Applied Catalysis A: General, Vol. 186(1): pp. 3-12, 1999.##
[8]. Calemma V., Correra S., Perego C., Pollesel P. and Pellegrini P. L., “Hydroconversion of fischer–tropsch waxes: assessment of the operating conditions effect by factorial design experiments,” Catalysis today, Vol. 106(1): pp. 282-287, 2005.##
[9]. Shiva M., Atashi H., Mirzaei A. A., Arsalanfar M. and Zare A., “Study of syngas conversion to light olefins by statistical models,” Fuel, Vol. 123: pp. 205-210, 2014.##
[10]. Shiva M., Atashi H., Tabrizi F. F., Mirzaei A. A. and Zare A., “The application of hybrid doe/ann methodology in lumped kinetic modeling of fischer–tropsch reaction,” Fuel Processing Technology, Vol. 106, pp. 631-640, 2013.##
[11]. Sharma B. K., Sharma M. P., Kumar Roy S., Tendulkar Sh. B., Tambe S. S. and Kulkarni B. D., “Fischer–tropsch synthesis with Co/Sio 2–Al2O3 catalyst and steady-state modeling using artificial neural networks,” Fuel, Vol. 77(15): pp. 1763-1768, 1998.##
[12]. Zahedi G., Lohi A. and Mahdi K., “Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor,” Fuel Processing Technology, Vol. 92(9), pp. 1725-1732, 2011.##
[13]. Zarenezhad B. and Aminian A., “Predicting the vapor-liquid equilibrium of carbon dioxide+ alkanol systems by using an artificial neural network,” Korean Journal of Chemical Engineering, Vol. 28(5): pp. 1286-1292, 2011.##
[14]. Baş D., Dudak F. C. and Boyacı I. H., “Modeling and optimization iv: investigation of reaction kinetics and kinetic constants using a program in which artificial neural network (ann) was integrated,” Journal of Food Engineering, Vol. 79(4), pp. 1152-1158, 2007.##
[15]. Souza M. J., Fernandes F., Pedrosa A. and Araujo A. S., “Selective cracking of natural gasoline over hzsm-5 zeolite,” Fuel Processing Technology, Vol. 89(9), pp. 819-827, 2008.##
[16]. Elavarasan P., Kondamudi K. and Upadhyayula S., “Statistical optimization of process variables in batch alkylation of p-cresol with tert-butyl alcohol using ionic liquid catalyst by response surface methodology,” Chemical Engineering Journal, Vol. 155(1): pp. 355-360, 2009.##
[17]. Rao T. M., Vico-Ruiz E., Bañares M. A. and Deo G., “Obtaining the best composition of supported V2O5–moo 3/Tio 2 catalyst for propane odh reaction,” Journal of Catalysis, Vol. 258(2), pp. 324-333, 2008.##
[18]. Jafarzadeh N. K., Sharifnia Sh., Hosseini S. N. and Rahimpour F., “Statistical optimization of process conditions for photocatalytic degradation of phenol with immobilization of nano Tio2 on perlite granules,” Korean Journal of Chemical Engineering, Vol. 28(2), pp. 531-538, 2011.##
[19]. Baş D., Dudak F. C. and Boyacı I. H., “Modeling and optimization iii: reaction rate estimation using artificial neural network (ann) without a kinetic model,” Journal of Food Engineering, Vol. 79(2), pp. 622-628, 2007.##
[20]. Chen, H. and A.A. Adesina, “Design of a multimetallic catalyst system for hydrocarbon synthesis: a statistical optimisation procedure,” Applied Catalysis A: General, Vol. 162(1-2), pp. 47-56, 1997.##
[21]. Eisenacher, K. and A.A. Adesina, “A statistical evaluation of preparation conditions on the performance of ce-promoted co-mo fischer-tropsch catalyst,” Korean Journal of Chemical Engineering, 17(1), pp. 71-75, 2000.##
[22]. Farias F. E., Sales F. G. and Fernandes F. A., “Effect of operating conditions and potassium content on fischer-tropsch liquid products produced by potassium-promoted iron catalysts,” Journal of Natural Gas Chemistry, Vol. 17(2), pp. 175-178, 2008.##
[23]. Serra J. M., Corma A., Chica A., Argente E. and Botti V., “Can artificial neural networks help the experimentation in catalysis?» Catalysis Today, Vol. 81(3), pp. 393-403, 2003.##
[24]. Gunst R.F., “Response surface methodology: process and product optimization using designed experiments,” Technometrics, Vol. 38(3), pp. 284-286, 1996.##
[25]. Samarasinghe S., “Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition,”  CRC Press, 2006.##
[26]. Aghaeinejad-Meybodi, A., Ebadi A., Shafiei S., Khataee A. R. and Rostampour M., “Modeling and optimization of antidepressant drug fluoxetine removal in aqueous media by ozone/H2O2 process: comparison of central composite design and artificial neural network approaches,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 48, pp. 40-48, 2015.##
[27]. Karimi F., Rafiee S., Taheri-Garavand A. and Karimi M., “Optimization of an air drying process for artemisia absinthium leaves using response surface and artificial neural network models,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 43(1), pp. 29-39, 2012.##
[28]. Sodeifian G., Sajadian S. A. and Ardestani N. S., “Evaluation of the response surface and hybrid artificial neural network-genetic algorithm methodologies to determine extraction yield of ferulago angulata through supercritical fluid,” Journal of the Taiwan Institute of Chemical Engineers, Vol. 60, pp. 165-173, 2016.##
[29]. Shen C., L. Wang and Li Q., “Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method,” Journal of Materials Processing Technology, Vol. 183(2), pp. 412-418, 2007.##