Prediction of Liquid and Vapor Enthalpies of Ammonia-water Mixture


Sencan A., Gok S., Dikmen E.

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, vol.33, no.15, pp.1463-1473, 2011 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 33 Issue: 15
  • Publication Date: 2011
  • Doi Number: 10.1080/15567030903397891
  • Title of Journal : ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
  • Page Numbers: pp.1463-1473

Abstract

The ammonia-water mixture may be commonly employed as a working fluid in the absorption chiller, especially because both ammonia and water are natural substances and are harmless. In addition, these substances have excellent thermodynamic properties. In this study, an alternative method using the artificial neural network (ANN) to determine liquid and vapor enthalpies of ammonia-water mixture is presented. The training and validation was performed with good accuracy. The correlation coefficient obtained when unknown data were used to the networks was 0.975 for the liquid enthalpy and 0.887 for the vapor enthalpy. Using the weights obtained from the trained network, a new formulation is presented for the determination of the vapor and liquid enthalpies of ammonia-water mixture. The results of the study show that the ANN is a perfect alternative method for the calculation of thermodynamic properties of ammonia-water mixture. The faster and simpler solutions with equations derived from the ANN can be carried out.