Documents disponibles écrits par cet auteur

Modeling of heating and cooling performance of counter flow type vortex tube by using artificial neural network / Fikret Kocabas in International journal of refrigeration, Vol. 33 N° 5 (Août 2010) 

Public ISBD [article]  in International journal of refrigeration > Vol. 33 N° 5 (Août 2010) . - pp. 963-972 Titre : Modeling of heating and cooling performance of counter flow type vortex tube by using artificial neural network Titre original : Modélisation de la performance en mode chauffage et refroidissement d'un tube vortex à contre-courant à l'aide d'un réseau neuronal artificiel Type de document : texte imprimé Auteurs : Fikret Kocabas, Auteur ; Murat Korkmaz, Auteur ; Ugur Sorgucu, Auteur Année de publication : 2010 Article en page(s) : pp. 963-972 Note générale : Génie Mécanique Langues : Anglais (eng) Mots-clés : Refrigeration  system  Vortex  tube  Modelling  Neural  network  Performance  Heating  Cooling Index. décimale : 621.5 Energie pneumatique. Machinerie et outils. Réfrigération Résumé : In this study, the effect of the nozzle number and the inlet pressures, which vary from 150 to 700 kPa with 50 kPa increments, on the heating and cooling performance of the counter flow type vortex tube has been modeled with an artificial neural network (ANN) and multi-linear regression (MLR) models by using the experimentally obtained data. In the developed system output parameter temperature gradiant between the cold and hot outlets (ΔT) has been determined using inlet parameters such as the inlet pressure (Pinlet), nozzle number (N), cold mass fraction (μc) and inlet mass flow rate View the MathML source. The back-propagation learning algorithm with variant which is Levenberg–Marquardt (LM) and Sigmoid transfer function have been used in the network. In addition, the statistical validity of the developed model has been determined by using the coefficient of determination (R2), the root means square error (RMSE), and the relative absolute errors (RAE). R2, RMSE and RAE have been determined for ΔT as 0.9989, 0.5016, 0.0540 respectively. DEWEY : 621.5 ISSN : 0140-7007 En ligne : http://www.sciencedirect.com/science/article/pii/S0140700710000423 [article] Modeling of heating and cooling performance of counter flow type vortex tube by using artificial neural network = Modélisation de la performance en mode chauffage et refroidissement d'un tube vortex à contre-courant à l'aide d'un réseau neuronal artificiel [texte imprimé] / Fikret Kocabas, Auteur ; Murat Korkmaz, Auteur ; Ugur Sorgucu, Auteur . - 2010 . - pp. 963-972. Génie Mécanique Langues : Anglais (eng) in International journal of refrigeration > Vol. 33 N° 5 (Août 2010) . - pp. 963-972 Mots-clés : Refrigeration  system  Vortex  tube  Modelling  Neural  network  Performance  Heating  Cooling Index. décimale : 621.5 Energie pneumatique. Machinerie et outils. Réfrigération Résumé : In this study, the effect of the nozzle number and the inlet pressures, which vary from 150 to 700 kPa with 50 kPa increments, on the heating and cooling performance of the counter flow type vortex tube has been modeled with an artificial neural network (ANN) and multi-linear regression (MLR) models by using the experimentally obtained data. In the developed system output parameter temperature gradiant between the cold and hot outlets (ΔT) has been determined using inlet parameters such as the inlet pressure (Pinlet), nozzle number (N), cold mass fraction (μc) and inlet mass flow rate View the MathML source. The back-propagation learning algorithm with variant which is Levenberg–Marquardt (LM) and Sigmoid transfer function have been used in the network. In addition, the statistical validity of the developed model has been determined by using the coefficient of determination (R2), the root means square error (RMSE), and the relative absolute errors (RAE). R2, RMSE and RAE have been determined for ΔT as 0.9989, 0.5016, 0.0540 respectively. DEWEY : 621.5 ISSN : 0140-7007 En ligne : http://www.sciencedirect.com/science/article/pii/S0140700710000423