Machine learning comparison of cooling performance of a Counterflow Ranque–Hilsch Vortex Tube system using different fluids

Yıl 2024, Cilt: 13 Sayı: 2, 621 - 631, 15.04.2024

Murat Korkmaz Ayhan Doğan Volkan Kırmacı

https://doi.org/10.28948/ngumuh.1310811

Öz

Today, when heating or cooling processes are carried out, environmentally harmful refrigerants are used. The Counterflow Ranque-Hilsch Vortex Tube (CFRHVT) consists of a simple tube. In RHVT, the heating and cooling process is done with the help of a pressurized fluid, causing little harm to the environment. In this study, 2, 3, 4, 5 and 6 orifice nozzles made of polyamide and brass materials were used in all experiments. At the same time, data were taken with air and oxygen gases as pressurized fluids during the experiments, and at every 0.5 bar, variables between 1.5bar and 7 bar. With the results obtained in the experiments, predictions were made with Support vector machines (SVM), Gaussian process regression (GPR), Linear regression (LR), Ensemble of Tree (ET) and Regression Trees (RT) models from machine learning methods. Five-fold analyses were performed with the k-fold cross-validation method for the validation processes as a result of the investigation. They obtained the best estimation result with the GSR method with 0.99 in the comparisons made with pressured fluids, oxygen and air, and polyamide and brass as the materials. The results show that the cost of experimental setup can be reduced and significant time savings can be achieved using machine learning.

Anahtar Kelimeler

Cooling, Heating, Vortex Tube, Machine Learning

Farklı akışkanlar kullanılan Karşıt Akışlı Ranque–Hilsch Vorteks Tüp sisteminin soğutma performansının makine öğrenimiyle karşılaştırılması

Öz

Günümüzde ısıtma veya soğutma işlemleri yapıldığında çevreye zarar veren soğutucu akışkanlar kullanılmaktadır. Karşıt Akışlı Ranque-Hilsch Vorteks Tüpü (KARHVT) basit bir borudan oluşmaktadır. RHVT de ısıtma ve soğutma işlemi basınçlı bir akışkan yardımıyla yaparak çevreye çok az zarar vermektedir. Bu çalışmada, tüm deneylerde polyamid ve pirinç malzemelerden yapılan 2, 3, 4, 5 ve 6 orfisli nozullar kullanılmıştır. Aynı zamanda deneyler esnasında basınçlı akışkan olarak hava ve oksijen gazları ile 1.5 bar ile 7 bar arasında her 0.5 bar değişkenlerinde veriler alınmıştır. Deneylerde alınan sonuçlar ile makine öğrenimi yöntemlerinden Destek vektör makineleri (DVM), Gauss süreç regresyonu (GSR), Lineer regresyonu (LR), Ağaç toplulukları (AT) ve Regresyon Ağaçları (RA) modelleri tahmin edilmiştir. Doğrulama işlemleri için k-fold çapraz doğrulama yöntemi ile beş katlı olarak analizler yapılmıştır. Analizler sonucunda basınçlı akışkanlar oksijen ve hava, malzemelerden polyamid ve pirinç ile yapılan karşılaştırmalarda en iyi tahmin sonucunu 0,99 ile GSR metoduyla elde edilmiştir. Sonuçlar makine öğrenimi kullanılarak deney düzeneği kurulum maliyetlerinin azaltılabileceğini ve önemli zaman tasarrufu elde edilebileceğini göstermektedir.

Anahtar Kelimeler

Soğutma, Isıtma, Vorteks Tüp, Makine Öğrenme

Kaynakça

• M. Korkmaz, A. Dogan, and V. Kırmacı, Performance Analysis of Counterflow Ranque – Hilsch Vortex Tube with Linear Regression, Support Vector Machines and Gaussian Process Regression Method, Gazi J. Eng. Sci., vol. 8, no. 2, pp. 361–370, 2022. https://doi. org/10.30855/gmbd.0705015.
• X. Han et al., The influence of working gas characteristics on energy separation of vortex tube, Appl. Therm. Eng., vol. 61, no. 2, pp. 171–177, 2013. https://doi.org/10.1016/j.applthermaleng.2013.07.027.
• R. Shamsoddini and A. H. Nezhad, Numerical analysis of the effects of nozzles number on the flow and power of cooling of a vortex tube, Int. J. Refrig., vol. 33, no. 4, pp. 774–782, 2010. https://doi.org/10.1016/j.ijrefrig .2009.12.029.
• Y. Xue, M. Arjomandi, and R. Kelso, The working principle of a vortex tube, Int. J. Refrig., vol. 36, no. 6, pp. 1730–1740, 2013. https://doi.org/10.1016/j.ijrefrig. 2013.04.016.
• N. Bej and K. P. Sinhamahapatra, Exergy analysis of a hot cascade type Ranque-Hilsch vortex tube using turbulence model, Energy Econ., vol. 45, no. 1947, pp. 13–24, 2014. https://doi.org/10.1016/j.ijrefrig.2014.05 .020.
• H. M. Skye, G. F. Nellis, and S. A. Klein, Comparison of CFD analysis to empirical data in a commercial vortex tube, Int. J. Refrig., vol. 29, no. 1, pp. 71–80, 2006. https://doi.org/10.1016/j.ijrefrig.2005.05.004.
• U. Behera et al., CFD analysis and experimental investigations towards optimizing the parameters of Ranque-Hilsch vortex tube, Int. J. Heat Mass Transf., vol. 48, no. 10, pp. 1961–1973, 2005. https://doi.org/10 .1016/j.ijheatmasstransfer.2004.12.046.
• M. A. Qyyum, A. A. Noon, F. Wei, and M. Lee, Vortex tube shape optimization for hot control valves through computational fluid dynamics, Int. J. Refrig., vol. 102, pp. 151–158, 2019. https://doi.org/10.1016/j.ijrefrig. 2019.02.014.
• J. Lewins and A. Bejan, Vortex tube optimization theory, Energy, vol. 24, no. 11, pp. 931–943, 1999. https://doi.org/10.1016/S0360-5442(99)00039-0.
• W. Wang, C. Wang, Y. Wei, and W. Song, A study on the wake structure of the double vortex tubes in a ventilated supercavity, J. Mech. Sci. Technol., vol. 32, no. 4, pp. 1601–1611, 2018. https://doi.org/10.1007 /s12206-018-0315-5.
• S. Anish, T. Setoguchi, and H. D. Kim, Computational investigation of the temperature separation in vortex chamber, J. Mech. Sci. Technol., vol. 28, no. 6, pp. 2369–2376, 2014. https://doi.org/10.1007/s12206-014-0529-0.
• F. Liang, H. Wang, and X. Wu, Study on energy separation characteristics inside the vortex tube at high operating pressure, Therm. Sci. Eng. Prog., vol. 14, no. September, p. 100432, 2019. https://doi.org/10.1016/j. tsep.2019.100432.
• D. G. Akhmetov and T. D. Akhmetov, Flow structure and mechanism of heat transfer in a Ranque–Hilsch vortex tube, Exp. Therm. Fluid Sci., vol. 113, no. December 2019, p. 110024, 2020. https://doi.org/10 .1016/j.expthermflusci.2019.110024.
• F. Liang, C. Xu, G. Tang, J. Wang, Z. Wang, and N. Li, Experimental investigation on the acoustic characteristics and cooling performance of the vortex tube, Int. J. Refrig., vol. 131, no. August, pp. 535–546, 2021. https://doi.org/10.1016/j.ijrefrig.2021.08.001.
• N. Li, G. Jiang, N. Gao, and G. Chen, Simple model for flow field division and flow structure calculation in a vortex tube, Int. J. Refrig., vol. 139, no. October 2021, pp. 48–59, 2022. https://doi.org/10.1016/j.ijrefrig. 2022.04.002.
• V. Kırmacı, Paralel bağlı karşıt akışlı ranque-hilsch vorteks tüp sisteminde farklı çalışma akışkanı ve nozul malzemesi kullanımının performansa etkisinin deneysel incelenmesi, Düzce Üniversitesi Bilim ve Teknol. Derg., vol. 8, no. 1, pp. 1204–1215, 2020. https://doi.org/10.29130/dubited.658242
• J. Wei et al., Machine learning in materials science, InfoMat, vol. 1, no. 3, pp. 338–358, 2019. https://doi.org/10.1002/inf2.12028
• F. Zhu et al., Biomedical text mining and its applications in cancer research, J. Biomed. Inform., vol. 46, no. 2, pp. 200–211, 2013. doi: https://doi .org/10.1016/j.jbi.2012.10.007.
• X. Zhou et al., Comparison of different machine learning algorithms for predicting air-conditioning operating behavior in open-plan offices, Energy Build., vol. 251, p. 111347, 2021. https://doi.org/10.1016/j. enbuild.2021.111347.
• V. A. Dev and M. R. Eden, Formation lithology classification using scalable gradient boosted decision trees, Comput. Chem. Eng., vol. 128, pp. 392–404, 2019. https://doi.org/10.1016/j.compchemeng.2019.06 .001.
• X. Chen, M. Zahiri, and S. Zhang, Understanding ridesplitting behavior of on-demand ride services: An ensemble learning approach, Transp. Res. Part C Emerg. Technol., vol. 76, pp. 51–70, 2017. https://doi.org/10.1016/j.trc.2016.12.018.
• I. Priyadarshini, S. Sahu, R. Kumar, and D. Taniar, A machine-learning ensemble model for predicting energy consumption in smart homes, Internet of Things, vol. 20, p. 100636, 2022. https://doi.org/10 .1016/j.iot.2022.100636.
• M. Sharifzadeh, A. Sikinioti-Lock, and N. Shah, Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression, Renew. Sustain. Energy Rev., vol. 108, pp. 513–538, 2019. https://doi.org/10. 1016/j.rser.2019.03.040.
• Z.-L. Ouyang, Z.-J. Zou, and L. Zou, Adaptive hybrid-kernel function based Gaussian process regression for nonparametric modeling of ship maneuvering motion, Ocean Eng., vol. 268, p. 113373, 2023. https://doi .org/10.1016/j.oceaneng.2022.113373.
• M. Pal and S. Deswal, Modelling pile capacity using Gaussian process regression, Comput. Geotech., vol. 37, no. 7, pp. 942–947, 2010. https://doi.org/10.1016/j .compgeo.2010.07.012.
• Q.-H. Luu, M. F. Lau, S. P. H. Ng, and T. Y. Chen, Testing multiple linear regression systems with metamorphic testing, J. Syst. Softw., vol. 182, p. 111062, 2021. https://doi.org/10.1016/j.jss.2021.111 062
• V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas, Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines, Ore Geol. Rev., vol. 71, pp. 804–818, 2015. https://doi.org/ 10.1016/j.oregeorev.2015.01.001.
• T.-S. Lee, C.-C. Chiu, Y.-C. Chou, and C.-J. Lu, Mining the customer credit using classification and regression tree and multivariate adaptive regression splines, Comput. Stat. Data Anal., vol. 50, no. 4, pp. 1113–1130, 2006. https://doi.org/10.1016/j.csda.2004 .11.006.