Kare ve yuvarlak silindir etrafındaki ısı transferinin modellenmesi: yeni YSA temelli bir yaklaşım

Öz

Yapay sinir ağları (ANN) insan beyninin bir modellemesidir. Bu çalışmanın amacı da ANN ile farklı silindirler etrafındaki ısı dağılımını tahmin etmektir. Çalışma kapsamında kare ve daire silindirler ele alınmıştır. Bu çalışmada, silindirlerin sıcaklık analizi, tam arka planda ne yaptığı bilinmeyen bir paket program kullanılmadan, fortran dili kullanılarak gerçekleştirilmiştir. Kod yazarak elde edilen sonuçlar daha güvenilir sonuçlardır. Çalışma iki boyutlu olarak ele alınmıştır. ANN ile verilerin eğitilmesinde en yaygın kullanılan 3 farklı algoritma (Levenberg–Marguardt (LM), Pola-Ribiere Conjugate Gradient (CGP) ve Scaled Conjugate Gradient (SCG)) kullanılmıştır. Silindir tipi, x-koordinatı ve y koordinatı girdi verileri, sıcaklık ise çıktı verisidir. En uygun algoritma LM-18 algoritması olarak bulunmuştur. Yapay sinir ağları ile gerçek değerlerin birbirine yakınlığı istatistiksel olarak değerlendirilmiştir. Bunlar R2, CoV ve RMSE'dir. LM-18 algritmasının eğitim aşamasındaki R2, CoV ve RMSE değerleri sırasıyla 0.9939, 0.0044, 0.0107; test aşamasındaki değerleri sırasıyla 0.9850, 0.0043, 0.0190'dir. R2 değerinin 1'e bu kadar yakın olması ANN'nin çok iyi çalıştığının da göstergesidir.

Anahtar Kelimeler

• Levenberg-Marquardt
• Levenberg-Marquardt
• Isı transferi
• Sayısal benzetim
• Yapay sinir ağları

Modeling of heat transfer around a square and a circle: a novel ANN-based approach

Öz

Artificial neural network (ANN) is a modelling of the human brain. The aim of this study is to estimate the heat distribution with ANN around different cylinders. Within the scope of the study, square and circular cylinders were discussed. In this study, the temperature analysis of the cylinders was carried out with a program written in Fortran, not using a package program whose exact background is unknown. The results obtained from a writing code are more reliable. The study is discussed in two dimensions. The 3 most commonly used algorithms (Levenberg – Marguardt (LM), Pola-Ribiere Conjugate Gradient (CGP) and Scaled Conjugate Gradient (SCG)) were used to train with ANN. Cylinder type, x-coordinate and y-coordinate were the input variables; and temperature was the output variable. The most suitable algorithm was found to be LM-18 algorithm. The proximity of artificial neural networks and real values was evaluated statistically. These were R2, CoV and RMSE. R2, CoV and RMSE values in the training phase of Levenberg – Marguardt -18 neuron were determined to be 0.9939, 0.0044, 0.0107 while their values in the test phase were 0.9850, 0.0043 and 0.0190 respectively. The fact that the R2 value is so close to 1 is an indication that ANN is working very well.

Anahtar Kelimeler

• Levenberg-Marquardt
• heat transfer
• numerical simulation
• artificial neural network.

Kaynakça

1. R. Franke, W. Rodi and B. Schönung, Numerical calculation of laminar vortex-shedding flow past cylinders. Journal of Wind Engineering and Industrial Aerodynamics, 35, 237-257, 1990. https://doi.org/ 10.1016/ 0167-6105(90)90219-3.
2. A. Sharma and V. Eswaran, Heat and fluid flow across a square cylinder in the two-dimensional laminar flow regime. Numerical Heat Transfer, Part A, 45, 247–269, 2004. https://doi.org/10.1080/10407780490278562.
3. A. Sohankar, C. Norberg and L. Davidson, Low-reynolds number flow around a square cylinder at incidence: study of blockage, onset of vortex shedding and outlet boundary condition. International Journal for Numerical in Fluids, 26, 39–56, 1998. https://doi.org/10.1002/(SICI)10970363(19980115)26:1<39::AID-FLD623>3.0.CO;2-P.
4. D. Chatterjee, G. Biswas and S. Amiroudine, Numerical investigation of forced convection heat transfer in unsteady flow past a row of square cylinders. International Journal of Heat and Fluid Flow, 30, 1114-1128, 2009. https://doi.org/10.1016/j.ijheatfluidflow. 2009.09.004
5. S. Malavasi and A. Guadagnini, Interactions between a rectangular cylinder and a freesurface flow. Journal of Fluids and Structures, 23, 1137–1148, 2007. https://doi.org/10.1016/j.jfluidstructs.2007.04.002.
6. J. Bai, N. Ma and X. Gu, Study of interaction between wave-current and the horizontal cylinder located near the free surface. Applied Ocean Research, 67, 44–58, 2017. https://doi.org/10.1016/j.apor.2017.06.004.
7. R. Scardovelli and S. Zaleski, Direct numerical simulation of free-surface and interfacial flow. Annual Review of Fluid Mechanics, 31, 567–603, 1999. https://doi.org/10.1146/annurev.fluid.31.1.567.
8. I-H. Liu, J. Riglin, WC. Schleicher and A. Oztekin, Flow past a plate in the vicinity of a free surface. Ocean Engineering, 111, 323–334, 2016. https://doi.org/ 10.1016/j.oceaneng.2015.11.009.

9. O. Arslan and O. Yetik, ANN based optimization of supercritical ORC-binary geothermal power plant: Simav case study. Applied Thermal Engineering, 31, 3922-3928, 2011. https://doi.org/10.1016/ j.applthermaleng. 2011.07.041.
10. O. Arslan and O. Yetik. ANN modeling of an ORC-Binary geothermal power plant: Simav case study. Energy Sources, Part A: Recovery, Utilization and Environmental Effects, 36, 418-428, 2014. https://doi.org/10.1080/15567036.2010.542437.
11. A. Sochinskii, D. Colombet, M. Muñoz, F. Ayela and N. Luchier, Flow and heat transfer around a diamond-shaped cylinder at moderate Reynolds number. International Journal of Heat and Mass Transfer, 142, 118435, 2019. https://doi.org/10.1016/ j.ijheatmasstransfer.2019.118435.
12. M. K. Dash and S. K. Dash, Natural convection heat transfer and fluid flow around a thick hollow vertical cylinder suspended in air: a numerical approach. International Journal of Thermal Sciences, 152, 106312, 2020. https://doi.org/10.1016/ j.ijthermalsci.2020.106312.
13. S. Hina, A. Shafique and M. Mustafa, Numerical simulations of heat transfer around a circular cylinder immersed in a shear-thinning fluid obeying cross model. Physica A, 540, 123184, 2020. https://doi.org/10.1016/j.physa.2019.123184.
14. P. Géczy-Víg and I. Farkas, Influence of the time step in ANN modelling of thermal stratification of solar storage. Proceedings of the 17th World Congress, pp. 9575-9578, Seoul, Korea, 6-11 July 2008.
15. K. Goudarzi, A. Moosaei and M. Gharaati, Applying artificial neural networks (ANN) to the estimation of thermal contact conductance in the exhaust valve of internal combustion engine. Applied Thermal Engineering, 87, 688-697, 2015. https://doi.org/ 10.1016/j.applthermaleng.2015.05.060.
16. T. E. Boukelia, O. Arslan and M. S. Mecibah, Potential Assessment of a parabolic trough solar thermal power plant considering hourly analysis: ANN-based approach. Renewable Energy, 105, 324-333, 2017. https://doi.org/10.1016/j.renene.2016.12.081.
17. M. Esfe, S. Esfandeh, M. Afrand, M. Rejvani and S. Rostamian, Experimental evaluation, new correlation proposing and ANN modeling of thermal properties of EG based hybrid nanofluid containing znodwcnt nanoparticles for internal combustion engines applications. Applied Thermal Engineering, 133, 452-463, 2018. https://doi.org/10.1016/ j.applthermaleng. 2017.11.131.
18. R. Shankar, K.R. Balasubramanian, S.P. Sivapirakasam and K. Ravikumar, ANN and RSM models approach for optimization of HVOF coating. Materials Today: Proceedings, (Article in press) 2020. https://doi.org/10.1016/j.matpr.2020.01.211.
19. J. Wanga, Y. Zhaia, P. Yaoa, M. Maa and H. Wang, Established prediction models of thermal conductivity of hybrid nanofluids based on artificial neural network (ANN) models in waste heat system. International Communications in Heat and Mass Transfer, 110, 104444, 2020. https://doi.org/10.1016/ j.icheatmasstransfer.2019.104444.
20. J. Robichaux, S. Balachandar and S.P. Vanka, Three-dimensional Floquet instability of the wake of square cylinder. Physics of Fluids, 11, 560–578, 1999. https://doi.org/10.1063/1.869930.
21. Y. Shimizu and Y. Tanida, Fluid forces acting on cylinders of rectangular cross section. Transc JSME B, 44, 2699–2706, 1978.
22. A. Sohankar and A. Etminan, Forced-convection heat transfer from tandem square cylinders in cross flow at low Reynolds numbers. International Journal for Numerical Methods in Fluids, 60, 733-751, 2009. https://doi.org/10.1002/fld.1909.
23. D. Chatterjee and B. Mondal, Forced convection heat transfer from tandem square cylinders for various spacing ratios. Numerical Heat Transfer Part A: Applications, 61, 381–400, 2012. https://doi.org/10.1080/10407782.2012.647985.
24. X. Qian, D. Xuan, X. Zhao and Z. Shi, Heat dissipation optimization of lithium-ion battery pack based on neural networks. Applied Thermal Engineering, 162, 114289, 2019. https://doi.org/10.1016/ j.applthermaleng.2019.114289.
25. A. Yüksek, H. Bircan, M. Zontul ve O. Kaynar, Sivas ilinde yapay sinir ağları ile hava kalitesi modelinin oluşturulması üzerine bir uygulama. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi, 8, 97-112, 2007.
26. S. Tanweer, A. Dewan and S. Sanghi, Influence of gap-ratio on flow dynamics and heat transfer for a square cylinder approaching a moving wall in turbulent regime. International Journal of Heat and Mass Transfer, 172, 121122, 2021. https://doi.org/ 10.1016/j.ijheatmasstransfer.2021.121122.
27. K. Khanafer and K. Vafai, Effect of a circular cylinder and flexible wall on natural convective heat transfer characteristics in a cavity filled with a porous medium. Applied Thermal Engineering, 181, 115989, 2020. https://doi.org/10.1016/j.applthermaleng.2020.115989.