Performance analysis of single-stage refrigeration system with internal heat exchanger using neural network and neuro-fuzzy

In this study, artificial neural networks (ANNs) and adaptive neuro-fuzzy (ANFIS) have been used for performance analysis of single-stage vapour compression refrigeration system with internal heat exchanger using refrigerants R134a, R404a, R407c which do not damage to ozone layer. It is well known that the evaporator temperature, condenser temperature, subcooling temperature, superheating temperature and cooling capacity affect the coefficient of performance (COP) of single-stage vapour compression refrigeration system with internal heat exchanger. In this study, COP is estimated depending on the above temperatures and cooling capacity values. The results of ANN are compared with ANFIS in which the same data sets are used. ANN model is slightly better than ANFIS for R134a whereas ANFIS model is slightly better than ANN for R404a and R407c. In addition, new formulations obtained from ANN for three refrigerants are presented for the calculation of the COP. The R² values obtained when unknown data were used to the networks were 1, 0.999998 and 0.999998 for the R134a, R404a and R407c respectively which is very satisfactory.