Premium
Neural networks—a new approach to model vapour‐compression heat pumps
Author(s) -
Bechtler H.,
Browne M. W.,
Bansal P. K.,
Kecman V.
Publication year - 2001
Publication title -
international journal of energy research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.808
H-Index - 95
eISSN - 1099-114X
pISSN - 0363-907X
DOI - 10.1002/er.705
Subject(s) - refrigerant , coefficient of performance , evaporator , condenser (optics) , heat pump , vapor compression refrigeration , artificial neural network , thermodynamics , compression (physics) , air source heat pumps , chilled water , mechanics , computer science , water cooling , gas compressor , physics , artificial intelligence , heat exchanger , light source , optics
Abstract The aim of this paper is to model the steady‐state performance of a vapour‐compression liquid heat pump with the use of neural networks. The model uses a generalized radial basis function (GRBF) neural network. Its input vector consists only of parameters that are easily measurable, i.e. the chilled water outlet temperature from the evaporator, the cooling water inlet temperature to the condenser and the evaporator capacity. The model then predicts relevant performance parameters of the heat pump, especially the coefficient of performance (COP). Models are developed for three different refrigerants, namely LPG, R22 and R290. It is found that not every model achieves the same accuracy. Predicted COP values, when LPG or R22 are used as refrigerant, are usually accurate to within 2 per cent, whereas many predictions for R290 deviate more than ±10 per cent. Copyright © 2001 John Wiley & Sons, Ltd.