Nashrieh Shimi va Mohandesi Shimi Iran

Nashrieh Shimi va Mohandesi Shimi Iran

Modeling Viscosity of Refrigerant and Lubricant Mixtures Using Artificial Neural Network (ANN)

Document Type : Research Article

Authors
Hamideh Zolfagari,
Fakhri Yousefi
Rezvan Karimi
Department of Chemistry, Faculty of Basic Sciences, Yasuj University, Yasuj, I.R. IRAN
Abstract
In this research, artificial neural networks(ANNs) have been used to predict the viscosity of lubricant/refrigerant mixtures. Temperature, pressure, molecular weight, the mole fraction of refrigerant, and viscosity of refrigerant are used as input variables and viscosity of refrigerant + lubricant mixtures is used as a target. The total number of experimental data point of viscosity that used in this study is 1053 that is trained, validated, and tested with random70%(837 data points), 15% (158 data points), and 15% (158 data points), respectively. The results of the AAD% for the train, validation and test sets of data are 0.39, 0.48, and 0.49, respectively. Therefore, studied ANN models with 15 neurons in a hidden layer are in good agreement with experimental data.
Keywords
Viscosity
Artificial neural network
Lubricant and refrigerant mixtures
Middle layer

Subjects

[1] NSI/ASHRAE Standard 34-2001, “Designation and Safety Classification of Refrigerants”, (2010).
[2] Haaf S., Henrici H. “Refrigeration Technology” in “Ullmann’s Encyclopedia of Industrial Chemistry”, Wiley-VCH, 2002.
[3] Bartz W., Tribology, Lubricants and Lubrication Engineering—A Review, Wear., 49: 1-18 (1978).
[4] Donnet C., Erdemir A.,  Historical Developments and New Trends in Tribological and Solid Lubricant Coatings, Surface and Coatings Technology, 180: 76-84 (2004).
[5] Martín-Alfonso J., Valencia C., Sánchez M., Franco J., Gallegos C., Development of New Lubricating Grease Formulations Using Recycled LDPE as Rheology Modifier Additive, European Polymer Journal, 43,149-139 (2007).
[6] Scharf, C.R., Twining, S.R., Todd, P.R., "Functionalized Polymer as Grease Additive", ed: Google Patents, (2001).
[7] Mermond Y., Feidt M., Marvillet C., Thermodynamic and Physical Properties of Mixtures of Refrigerants and Oils, International Journal of Refrigeration, 22: 569-579 (1999).
[8] Marsh, K. N., Kandil, M. E., Review of Thermodynamic Properties of Refrigerants+ Lubricant Oils, Fluid Phase Equilibria, 199: 319-334 (2002).‏
[9] Dayhoff J.E., Neural Networks Principles. Prentice-Hall International, U.S.A, 1990.
[10] البرزی، م؛ آشنایی با شبکه‌های عصبی، انتشارات دانشگاه صنعتی شریف، ص. 37 (1380).
[11] Zolfaghari, H., Yousefi, F. Thermodynamic Properties of Lubricant/Refrigerant Mixtures Using Statistical Mechanics and Artificial Intelligence, International Journal of Refrigeration, 80: 130-144(2017).
[12] Zolfaghari, H., Yousefi, F. PVT Properties of Pure Lubricants Using Equations of State and Artificial Intelligence, Physical Chemistry Research, 7:181-200(2019).
]13[ سایت : انجمن هوش مصنوعی ایران به نشانی www.artificial.ir
[14] Rumelhurt. D. E., Hinton. G.E., Williams R. j., Learning Internal Representations by Error Propagation. Parallel Data Processing, 1: 318 (1986).
[15] Hirose Y., Yamashita K., Hijiya S., Back- Propagation Algorithm which Variesnumber of Hidden Units, Neural Networks, 4: 61-66 (1991).
[16] غضنفری، ی؛ و کاظمی، ز؛ "اصول و مبانی سیستم های خبره – با فصولی درباره شبکه عصبی مصنوعی و تئوری مجموعه فازی"، دانشگاه علم و صنعت ایران، ص 648 (1382).
[17] ثقه الاسلامی، ن؛ کریمی، ه؛ اخوت، ا؛ وطن‌خواه، غ؛ "اصول و کاربرد شبکه‌های عصبی در صنایع نفت و گاز". تهران: نشر جهش (1388).
 [18] Monsalvo M.A., Baylaucq A., Reghem P., Qui˜nones-Cisneros S.E., Boned C., Viscosity Measurements and Correlations of Binary Mixtures: 1,1,1,2-tetrafluoroethane (HFC134a) + Tetraethylene Glycoldimethylether (TEGDME), Fluid Phase Equilibria, 233: 1–8 (2005).
[19] María J.P. Comuñas, Antoine Baylaucq, Christian Boned, Josefa Fernández, Dynamic Viscosity for HFC-134a + Polyether Mixtures up to 373.15 K and140 MPa at Low Polyether Concentration. Measurements and Modelling, Industrial & Engineering Chemistry Research, 43: 804–814 (2004).
[20] Mat´ıas A. Monsalvo, Antoine Baylaucq, Sergio E. Qui˜nones-Cisneros, Christian Boned., High-Pressure Viscosity Behavior of x 1,1,1,2-tetrafluoroethane(HFC-134a) + (1−x) triethylene glycol dimethylether (TriEGDME)mixtures: Measurements and Modeling, Fluid Phase Equilibria, 247: 70–79 (2006).
[21] Pensado A.S., P´adua A.A.H., Comu˜nas M.J.P., Fern´andez J., Viscosity and Density Measurements for Carbon Dioxide + Pentaerythritolester Lubricant Mixtures at Low Lubricant Concentration, J. of Supercritical Fluids, 44: 172–185 (2008).
[22] Pensado A. S.,  H. Padua A. A., Comunas  M. J. P., Fernandez J., High-Pressure Viscosity and Density of Carbon Dioxide 1 Pentaerythritol Ester Mixtures: Measurements and Modeling, AIChE Journal, 54: 1625-1636 (2008).
[23] Tomida D., Kumagai A., Yokoyama C., Viscosity Measurements and Correlation of the Squalane + CO2 Mixture, International Journal of Thermophysics, 28: 133-145 (2007).
[24] Katsuya Takigawa., Stanley I.Sandler., Akimichi Yokozeki., Solubility and Viscosity of refrigerant/Lubricant Mixtures: Hydrofluorocarbon/Alkylbenzene Systems, International Journal of Refrigeration, 25: 1014–1024 (2002).
[25] Bair S., Baker M., Pallister D.M., The High-Pressure Viscosity of Refrigerant/Oil Systems, Lubrication Science, 6: 377-394 (2017).
[26] Moisés A., Marcelino Neto., Jader R. Barbosa Jr., Solubility, Density and Viscosity of Mixtures of Isobutane (R-600a) and a Linear Alkylbenzene Lubricant, Fluid Phase Equilibria, 292: 7-12 (2010).