Modeling of thermodynamic properties of refrigerant R410A with artificial neural networks R410A soǧutucu akişkaninin termodi̇nami̇k özelli̇kleri̇ni̇n yapay si̇ni̇r aǧlari metoduyla modellenmesi̇

KIZILKAN Ö., ŞENCAN ŞAHİN A., YAKUT A. K.

Journal of the Faculty of Engineering and Architecture of Gazi University, vol.21, no.2, pp.395-400, 2006 (Scopus, TRDizin) identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 2
  • Publication Date: 2006
  • Journal Name: Journal of the Faculty of Engineering and Architecture of Gazi University
  • Journal Indexes: Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.395-400
  • Keywords: Artificial neural network, R410a, Thermodynamic properties, Vapor compression systems
  • Isparta University of Applied Sciences Affiliated: No

Abstract

In this study, thermodynamic properties as saturation pressure, saturated liquid enthalpy and entropy, superheated vapor enthalpy and temperature of R410a refrigerant, which are harmful to the ozone layer, used in the vapor compression refrigeration systems were determined with Artificial Neural Network (ANN) model. Data of thermodynamic properties used in the study were obtained from empirical and experimental data that is available in the literature. In order to determine thermodynamic properties of refrigerant for all spans, new formulations were derived by ANN model which was very well trained. These formulations were derived with using weights and bias values of network. With these formulations, faster and simple solutions can be obtained.