Paralel Bağlı Vorteks Tüplerinin Performansı için Yapay Sinir Ağları Analizi

Abstract

Bu çalışmada iki adet aynı özelliklere sahip karşıt akışlı Ranque-Hilsch Vorteks Tüpü (RHVT) paralel bağlanarak performansı deneysel olarak incelenmiş ve vorteks tüpünün performans göstergesi olan sıcak akışkan çıkışı ile soğuk akışkan çıkışı arasındaki sıcaklık farkı (ΔT) değerleri elde edilmiştir. Oksijen ve hava ile yapılan deneylerde polyamid ve pirinç malzemeden imal edilmiş 3,4 ve 5 orifisli nozullar kullanılmıştır. Farklı akışkanlar, nozul malzemeleri ve nozul sayıları için elde edilen ΔT değerlerinin modellenmesi için bir yapay sinir ağları (YSA) çalışması yapılmış ve paralel bağlı iki vorteks tüpü sistemi için genelleştirilebilir modelleme elde edilmiştir. Nozullar için ısıl iletkenlik ve orifis sayısı, çalışma akışkanları için özgül ısı ve yoğunluk parametreleri ile RHVT giriş basıncı ( 5 girdi) girdi parametreleri olarak kullanılmıştır. YSA için veriler eğitim ve test grubu olarak ayrılmış ve eğitilen model test grubu ile test edilmiştir. Regresyon analizinde eğitim gurubu için R2 değeri %99.8, test grubu için %99.6 olarak hesaplanıştır

Keywords

• Vorteks tüpü
• Modelleme
• YSA

Artificial Neural Network Analysis for Performance of Parallel Connected Vortex Tubes

Abstract

In this study, two counter-flow Ranque-Hilsch Vortex Tubes (RHVTs) were connected in parallel, and their performance was investigated experimentally, and the temperature difference (ΔT) values the vortex tube's performance indicator between hot and the cold fluid outlet were obtained. In experiments with oxygen and air, 3,4 and 5 orifice nozzles made of polyamide and brass are used. An artificial neural network (ANN) study was conducted to model the ΔT values obtained for different fluids, nozzle materials and nozzle numbers, and generalizable modeling was obtained for two parallel vortex tube systems. Thermal conductivity and orifice number for nozzles, specific heat and density parameters for working fluids and RHVT inlet pressure (5 input) are used as input parameters. Data for ANN was separated as a training and test group and the trained model was tested with the test group. In regression analysis, R2 value was calculated as 99.8% for the education group and 99.6% for the test group.

Keywords

• Vortex tube
• Modelling
• ANN

References

1. [1]. Kirmaci, V., Kaya, H., “Effects of working fluid, nozzle number, nozzle material and connection type on thermal performance of a Ranque–Hilsch vortex tube: A review”, International Journal of Refrigeration, 2018, 91: 254–266.
2. [2]. Guo, X., Zhang, B., Liu, B., Xu, X. “A critical review on the flow structure studies of Ranque – Hilsch vortex tubes”, International Journal of Refrigeration, 2019, 104: 51–64.
3. [3]. Altinkaynak, M., Olgun, E, Şencan Şahin, A., “Comparative Evaluation of Energy and Exergy Performances of R22 and its Alternative R407C, R410A and R448A Refrigerants in Vapor Compression Refrigeration Systems”, El-Cezerî Journal of Science and Engineering, 2019, 6(3); 659-667.
4. [4]. Li, N., Jiang, G., Fu, L., “Experimental study of the impacts of cold mass fraction on internal parameters of a vortex tube”, International Journal of Refrigeration, 2019, 104: 151–160.
5. [5]. Uluer, O., Kirmaci, V., Ataş, Ş. “Using the artificial neural network model for modeling the performance of the counter flow vortex tube”, Expert Systems with Applications, 2009, 36: 12256–12263.
6. [6]. Kaya, H., Günver, F., Kirmaci, V., “Experimental investigation of thermal performance of parallel connected vortex tubes with various nozzle materials”, Applied Thermal Engineering, 2018, 136, 287-292.
7. [7]. Attalla, M., Ahmed, H., Salem Ahmed, M., Abo El- Wafa, A., “An experimental study of nozzle number on Ranque Hilsch counter-flow vortex tube”, Experimental Thermal and Fluid Science, 2017, 82: 381–389.
8. [8]. Kaya, H., Uluer, O., Kocaoğlu, E., Kirmaci, V., “Experimental analysis of cooling and heating performance of serial and parallel connected counter-flow Ranquee–Hilsch vortex tube systems using carbon dioxide as a working fluid”, International Journal of Refrigeration, 2019, 106: 297–307.

9. [9]. Pinar, A, M., Uluer, O., Kirmaci, V. “Optimization of counter flow Ranque-Hilsch vortex tube performance using Taguchi method”, International Journal of Refrigeration, 2009, 32: 1487–1494.
10. [10]. Pinar, A, M., Uluer, O., Kırmacı, V., “Statistical assessment of counter-flow vortex tube performance for different nozzle numbers, cold mass fractions, and inlet pressures via taguchi method”, Experimental Heat Transfer, 2009, 22: 271–282.
11. [11]. Korkmaz, M. E., Gümüşel, L., Markal, B., “Using artificial neural network for predicting performance of the Ranque-Hilsch vortex tube”, International Journal of Refrigeration, 2012, 35: 1690–1696.
12. [12]. Polat, K., Kirmaci, V., “Application of the output dependent feature scaling in modeling and prediction of performance of counter flow vortex tube having various nozzles numbers at different inlet pressures of air, oxygen, nitrogen and argon”, International Journal of Refrigeration, 2012, 34: 1387–1397.
13. [13]. Lagrandeur, J., Poncet, S, Sorin, M., Khennich, M., “Thermodynamic modeling and artificial neural network of air counterflow vortex tubes”, International Journal of Thermal Sciences, 2019, 146: 106097.
14. [14]. Suresh Kumar, G., Veerabhadra, Reddy B., Sankaraiah, G., Venkateshwar Reddy, P., “Modeling the Performance of Vortex Tube using Response Surface Methodology and Artificial Neural Networks”, IOP Conference Series Materials Science and Engineering, 2018, 390: 012010.
15. [15]. Nouri-Borujerdi, A., Bovand, M., Rashidi, S., Dincer, K., “Geometric parameters and response surface methodology on cooling performance of vortex tubes”, International Journal of Sustainable Energy, 2017, 36 (9): 872–886.
16. [16]. Bovand, M., Valipour, M S., Dincer, K., Eiamsa-Ard, S., “Application of response surface methodology to optimization of a standard Ranque-Hilsch vortex tube refrigerator”, 2014, Applied Thermal Engineering, 67: 545–553.