بررسی جذب گازهای خالص متان، کربن دی اکسید و نیتروژن برروی زئولیت 13X با استفاده از شبکه عصبی مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

دانشکده مهندسی شیمی، پردیس دانشکده‌های فنی، دانشگاه تهران، ایران

چکیده

یکی از راه‌های جلوگیری از گرم شدن کره زمین و افزایش ارزش حرارتی گاز طبیعی، جذب کربن دی اکسید و نیتروژن، با استفاده از زئولیت‌ها است. در این مطالعه، نتایج تجربی جذب سه گاز متان، کربن دی اکسید و نیتروژن توسط زئولیت 13X، با استفاده از شبکه عصبی مصنوعی مورد بررسی قرار گرفت. دما و فشار به‌عنوان ورودی‌های سیستم و ظرفیت جذب به‌عنوان خروجی در نظر گرفته شد. در همه مدل‌ها از الگوریتم پس انتشار لونبرگ- مارکوآرت برای آموزش شبکه استفاده شد. جهت تعیین توابع انتقال بهینه در لایه‌های پنهان و خروجی و نرون بهینه از شاخص‌های ضریب تعیین، خطای میانگین مربعات، مجموع خطاهای مربع و خطای میانگین مربع ریشه استفاده شد. نرون بهینه برای متان، کربن دی اکسید و نیتروژن به‌ترتیب 10، 10 و 15 به‌دست آمد. همچنین بهترین نتایج برای توابع انتقال، Logsig و Tansig برای متان، Logsig و Purelin برای کربن دی اکسید و نیتروژن به‌ترتیب برای لایه پنهان و لایه خروجی به‌دست آمدند. ضریب تعیین در شرایط بهینه برای متان، کربن دی اکسید و نیتروژن به‌ترتیب 9970/0، 9842/0 و 9937/0 به‌دست آمد. در پایان درصد انحراف میانگین برای نتایج پیش‌بینی شده توسط شبکه عصبی با نتایج توسط مدل لانگمویر و مدل Sips وابسته به دما مقایسه شد که نشان از دقت بالای شبکه عصبی مصنوعی نسبت به دو مدل است.
 

کلیدواژه‌ها


عنوان مقاله [English]

Investigation of Adsorption of Methane, Carbon Dioxide and N2 on Zeolite 13X Using Artificial Neural Network

نویسندگان [English]

  • Hojatollah moradi
  • Hedayat Azizpour
  • hossein bahmanyar
School of Chemical Engineering, College of Engineering, University of Tehran, Iran
چکیده [English]

One of the most important processes for avoiding global warming and increasing the heating value of natural gas is adsorption and separation of carbon dioxide and nitrogen using zeolite. In this study, experimental results of adsorption of methane, carbon dioxide and nitrogen by zeolite 13X was assessed using artificial neural network. The temperature and pressure was considered as inputs, and adsorption capacity was considered as the output of system. In all models, Levenberg-Marquardt back-propogation was used for training of the network. To find the optimum transfer function in hidden and output layers and optimum number of neurons, coefficient of determination, sum of squared errors, mean square error were calculated. Optimized number of neurons for methane, carbon dioxide and nitrogen was obtained 10, 10, and 15 respectively. Moreover, the best transfer functions were Logsig and Tansig for methane, Logsing and Pureline for carbon dioxide and nitrogen for hidden and output layers. In the end, average deviation percentage for predicted results with neural network was compared with the results obtained by Langmuir and dependent on temperature sip models. It indicates that neural network has high accuracy in comparison with other two models.
 

کلیدواژه‌ها [English]

  • Natural Gas
  • Carbon Dioxide
  • Zeolite 13X
  • Modeling
  • Artificial Neural Network
[1]. Cavenati S, Grande CA, Rodrigues AE (2004). Adsorption equilibrium of methane, carbon dioxide, and nitrogen on zeolite 13X at high pressuresو Journal of Chemical & Engineering Data, 49: 4, 1095-1101.##

[2]. Kareem FAA, Shariff AM, Ullah S, Keong LK,  Mellon N (2018). Total and partial uptakes of multicomponent vapor-gas mixtures on 13X zeolite at 343K: Experimental and modeling study. Microporous and Mesoporous Materials, 258: 95-113. ##

[3]. Darman NH,  Harun AR (2006) Technical challenges and solutions on natural gas development in malaysia, presented in the petroleum policy and management project, In 4th Workshop on the China-Shichuan Basin Case Study, Beijing. ##

[4]. Gholipour F,  Mofarahi M (2016) Adsorption equilibrium of methane and carbon dioxide on zeolite 13X: Experimental and thermodynamic modeling, The Journal of Supercritical Fluids, 111, 47-54. ##

[5]. Hotchkiss ER, Hall Jr RO, Sponseller RA, Butman D, Klaminder J, Laudon H, Karlsson J (2015) Sources of and processes controlling CO2 emissions change with the size of streams and rivers, Nature Geoscience, 8, 9: 696-699. ##

[6]. Heslop MJ, Mason G,  Buffham BA (2000) Absolute determination of the composition of binary gas mixtures by admixture of known components, Chemical Engineering Research and Design, 78, 8: 1061-1065. ##

[7]. Ullah S, Shariff AM, Bustam MA, Elkhalifah AEI, Gonfa G, Kareem FAA (2016) The role of multiwall carbon nanotubes in Cu‐BTC metal‐organic frameworks for CO2 adsorption, Journal of the Chinese Chemical Society, 63, 12: 1022-1032. ##

[8]. Ghaedi AM,  Vafaei A (2017) Applications of artificial neural networks for adsorption removal of dyes from aqueous solution: A review. Advances in colloid and interface science, 245, 20-39. ##

[9]. Nematollahi M, Jalali-Arani A,  Golzar K (2014) Organoclay maleated natural rubber nanocomposite. Predictionof abrasion and mechanical properties by artificial neural network and adaptive neuro-fuzzy inference, Applied clay science, 97, 187-199. ##

[10]. Golzar K, Amjad-Iranagh S, Modarress H (2014) Prediction of thermophysical properties for binary mixtures of common ionic liquids with water or alcohol at several temperatures and atmospheric pressure by means of artificial neural network, Industrial and Engineering Chemistry Research, 53, 17: 7247-7262. ##

[11]. Karimi H,  Yousefi F (2007) Correlation of vapour liquid equilibria of binary mixtures using artificial neural networks, Chinese Journal of Chemical Engineering, 15: 5, 765-771. ##

[12]. Fotoohi F, Amjad-Iranagh S, Golzar K, Modarress H (2016) Predicting pure and binary gas adsorption on activated carbon with two-dimensional cubic equations of state (2-D EOSs) and artificial neural network (ANN) method. Physics and Chemistry of Liquids, 54: 3, 281-302. ##

[13]. Kareem FAA, Shariff AM, Ullah S, Dreisbach F, Keong LK, Mellon N,  Garg S (2018) Experimental measurements and modeling of supercritical CO2 adsorption on 13X and 5A zeolites, Journal of Natural Gas Science and Engineering, 50, 115-127. ##

[14]. AbdulKareem FA, Shariff AM, Ullah S, See TL, Keong LK,  Mellon N (2018) Adsorption performance of 5A molecular sieve zeolite in water vapor–binary gas environment: experimental and modeling evaluation, Journal of Industrial and Engineering Chemistry, 64: 173-187. ##

[15]. Park Y, Ju Y, Park D,  Lee CH (2016) Adsorption equilibria and kinetics of six pure gases on pelletized zeolite 13X up to 1.0 MPa: CO2, CO, N2, CH4, Ar and H2, Chemical Engineering Journal, 292, 348-365. ##

[6]. Tanzifi M, Yaraki MT, Kiadehi AD, Hosseini SH, Olazar M, Bharti AK, Kazemi A (2018) Adsorption of amido black 10B from aqueous solution using polyaniline/SiO2 nanocomposite: experimental investigation and artificial neural network modeling, Journal of colloid and interface science, 510, 246-261. ##

[17]. Souza PR, Dotto GL, Salau NPG (2018) Artificial neural network (ANN) and adaptive neuro-fuzzy interference system (ANFIS) modelling for nickel adsorption onto agro-wastes and commercial activated carbon, Journal of environmental chemical engineering, 6, 6: 7152-7160. ##

[18]. Hoseinian FS, Rezai B, Kowsari E (2017) The nickel ion removal prediction model from aqueous solutions using a hybrid neural genetic algorithm. Journal of environmental management, 204, 311-317. ##

[19]. Franco DS, Duarte FA, Salau NPG, Dotto GL (2020) Analysis of indium (III) adsorption from leachates of LCD screens using artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANIFS), Journal of hazardous materials, 384, 121137. ##

[20]. Li W, Wei S, Jiao W, Qi G, Liu Y (2016) Modelling of adsorption in rotating packed bed using artificial neural networks (ANN), Chemical Engineering Research and Design, 114, 89-95. ##

[21]. Franco DS, Duarte FA, Salau NPG, Dotto GL (2019) Adaptive neuro-fuzzy inference system (ANIFS) and artificial neural network (ANN) applied for indium (III) adsorption on carbonaceous materials, Chemical Engineering Communications, 206, 11: 1452-1462. ##

[22]. Pakravan P, Akhbari A, Moradi H, Azandaryani AH, Mansouri AM, Safari M (2015) Process modeling and evaluation of petroleum refinery wastewater treatment through response surface methodology and artificial neural network in a photocatalytic reactor using poly ethyleneimine (PEI)/titania (TiO2) multilayer film on quartz tube. Applied Petrochemical Research, 5, 1: 47-59. ##

[23]. Schaap MG, Bouten W (1996) Modeling water retention curves of sandy soils using neural networks, Water Resources Research, 32: 10, 3033-3040. ##