Modeling of the effects of length to diameter ratio and nozzle number on the performance of counterflow Ranque-Hilsch vortex tubes using artificial neural networks

In this study, the effect of length to diameter ratio and nozzle number on the performance of a counterflow Ranque-Hilsch vortex tube has been modeled with artificial neural networks (ANN), by using experimental data. In the modeling, experimental data, which were obtained from experimental studies in a laboratory environment have been used. ANN has been designed by MATLAB 6.5 NN toolbox software in a computer environment working with Windows XP operating system and Pentium 4 2.4 GHz hardware. In the developed system outlet parameter ΔT has been determined using inlet parameters P, L/D, N and ξ. When experimental data and results obtained from ANN are compared by statistical independent t-test in SPSS, it was determined that both groups of data are consistent with each other for P > 0.05 confidence interval, and differences were statistically not significant. Hence, ANN can be used as a reliable modeling method for similar studies. © 2008 Elsevier Ltd. All rights reserved.