Mustafa Kemal SEVİNDİR, Alişan GÖNÜL, Alican ÇEBİ, Hatice MERCAN

Yatay Pürüzsüz Borularda Yoğuşmadaki Nusselt Sayısının Belirlenmesi için Yapay Sinir Ağ Teknikleri

Bu çalışmada, literatürdeki hazır deneysel veriler kullanılarak, yatay pürüzsüz borularda yoğuşmadaki Nusselt sayısını belirlemek için yapay sinir ağları (ANN) yöntemi kullanılmıştır. R32, R134a ve %50/%50 ve %60/%40 R32/R125 azeotropik soğutucu karışımlarının yoğuşma ısı transferi dört farklı ANN yöntemi ile incelendi; Levenberg-Marquardt, Bayes düzenlenmesi, ölçeklenmiş eşlenik değişim ve esnek geri yayılımı. Deneysel veriler Dobson ve ark.[1]’nın çalışmalarından alınmıştır. Giriş parametreleri kütle akısı, kalite, hidrolik çap, Soliman'ın değiştirilmiş Froude sayısı, akışkan faz yoğunluğu ve çıkış parametresinin yoğuşmadaki Nusselt sayısının olduğu sıvı fazın dinamik viskozitesidir. Bu çalışmada, boru çapları aralığı 3,14-7,04 mm arasında ve kütle akı aralığı 50-800 kg/m2 arasındadır. Eğitim algoritmaları farklı nöron sayıları kullanılarak test edildi ve en iyi algoritma 8 nörona sahip Bayes düzenlenmesi olarak bulundu. ANN kullanılarak değerlendirilen Nu sayısının deney sonuçlarına göre ±%15 hata payı olduğu gözlenmiştir. Ayrıca, artan kütle akı oranları için hata payı ±%5 civarındadır.

Anahtar Kelimeler:

Yoğuşma, Yapay sinir ağları, Soğutucu akışkan, Nusselt sayısı, Yatay pürüzsüz boru

Artificial Neural Network Techniques for the Determination of Condensation Nusselt Number in Horizontal Smooth Tubes

In this study, using readily available experimental data in the literature, artificial neural networks (ANN) method is adopted to specify condensation Nusselt number in horizontal smooth tubes. Condensation heat transfer of R22, R134a and 50/50 and 60/40 of the R32/ R125 azeotropic refrigerant mixtures were examined with four different ANN methods. The experimental data is taken from the study of Dobson et al. [1]. The input parameters are mass flux, quality, hydraulic diameter, Soliman's modified Froude number, density of fluid phase and dynamic viscosity of liquid phase where the output parameter is the condensation Nusselt number. In this study the interval for tube diameters is between 3.14-7.04 mm, and the interval for mass flux is between 50-800 kg/m2s. The training algorithms are tested using different neuron numbers and the best algorithm was found as Bayesian regularization having 8 neurons. It is observed that the Nu number evaluated using ANN is ± 15% error margin compared to experimental results. Furthermore, for increasing mass flux rates the error margin is around ± 5%.

Keywords:

Condensation, Artificial neural networks, Refrigerant, Nusselt number, Horizontal smooth tube,

PDF

___

[1] Dobson, M. K., Chato, J. C., Wattelet, J. P., Gaibel, J. A., Ponchner, M., Kenney, P.J., Shimon, R.L., Villaneuva, T.C., Rhines, N.L., Sweeney, K.A., Allen, D.G., Hershberger, T.T. 1994. Heat transfer and flow regimes during condensation in smooth horizontal tubes, ACRC TR-57 Project.
[2] Azizi, S., Ahmadloo, E. 2016. Prediction of heat transfer coefficient during condensation of R134a in inclined tubes using artificial neural network, Applied Thermal Engineering, 106 (2016) 203-210.
[3] Boyko, L.D., Kruzhilin, G.N. 1967. Heat transfer and hydraulic resistance during condensation of steam in a horizontal tube and in a bundle of tubes, International. Journal of Heat and Mass Transfer, 10 (1967) 361–373.
[4] Shah, M.M. 1979. A general correlation for heat transfer during film condensation inside tubes, International. Journal of Heat and Mass Transfer, 22 (1979) 547–556.
[5] Dobson, M. K., Chato, J. C. 1998. Condensation in smooth horizontal tubes, ASME Journal of Heat Transfer, 120 (1998) 193–213.
[6] Kim, D., Ghajar, A.J. 2002. Heat transfer measurement and correlations for air–water flow of different flow patterns in a horizontal tube, Experimental Thermal and Fluid Science, 25 (2002) 659–676.
[7] Jung, D., Song, K., Cho, Y., Kim, S. 2003. Flow condensation heat transfer coefficients of pure refrigerant, International Journal of Refrigeration, 26 (2003) 4–11.
[8] Thome, J.R., El Hajal, J., Cavallini, A. 2003. Condensation in horizontal tubes. Part II: New heat transfer model based on flow regimes, International Journal of Heat and Mass Transfer, 46 (2003) 3365–3387.
[9] Cavallini, A., Del Col, D., Doretti, L., Matkovic, M., Rossetto, L., Zilio, C., Censi, G. 2006. Condensation in horizontal smooth tubes: a new heat transfer model for heat exchanger design, Heat Transfer Engineering, 27 (2006) 31–38.
[10] Huang, X., Ding, G., Hu, H., Zhu, Y., Peng, H., Gao, Y., Dengo, B, 2010. Influence of oil on flow condensation heat transfer of R410A inside 4.18 mm and 1.6 mm inner diameter horizontal smooth, International Journal of Refrigeration 33-1 (2010) 158-169.
[11] Hosoz, M.H., Ertunc, M. 2006. Modeling of a cascade refrigeration system using artificial neural networks, International Journal of Energy Research, 30 (2006) 1200–1215.
[12] Arcaklioglu, E., Erisen, A., Yilmaz, R. 2004. Artificial neural network analysis of heat pumps using refrigerant mixtures, Energy Conversation and Management, 45 (2004) 1917– 1929.
[13] Islamoglu, Y. 2003. A new approach for the prediction of the heat transfer rate of the wire-on-tube type heat exchanger—use of an artificial neural network model, Applied Thermal Engineering, 23 (2003) 243–249.
[14] Sencan, A., Kose, I.I., Selbas, R. 2011. Prediction of thermophysical properties of mixed refrigerants using artificial neural network, Energy Conversation and Management, 52 (2011) 958–974.
[15] Demir, H., Ağra, Ö., Atayılmaz, Ş.Ö. 2009. Generalized neural network model of alternative refrigerant (R600a) inside a smooth tube, International Communications in Heat and Mass Transfer, 36 (2009) 744–749.
[16] Balcilar, M., Dalkilic, A.S., Wongwises, S. 2011. Artificial neural network techniques for the determination of condensation heat transfer characteristics during downward annular flow of R134a inside a vertical smooth tube, International Communications in Heat and Mass Transfer, 38 (2011) 75–84.
[17] Zdaniuk, G.J., Chamra, L.M., Walters, D.K. 2007. Correlating heat transfer and friction in helically-finned tubes using artificial neural networks, International Journal of Heat and Mass Transfer, 50 (2007) 4713–4723.
[18] Wang, WW.W., Radcliff, T. D., Christensen, R. N. 2002. A condensation heat transfer correlation for millimeter-scale tubing with flow regime transition, Experimental Thermal and Fluid Science, 26-5 (2002) 473-485.