ANN approach for irreversibility analysis of vapor compression refrigeration system using R134a/LPG blend as replacement of R134a

This paper experimentally evaluated the irreversibility in the components (compressor, condenser, capillary tube, and evaporator) of the vapor compression refrigeration system (VCRS) using R134a/LPG refrigerant as a replacement for R134a. For this aim, different tests were conducted for various evaporator and condenser temperatures under controlled surrounding conditions. The results reported that the irreversibilities in the components of VCRS using R134a/LPG blend were found lesser than irreversibilities in the components of VCRS using R134a under similar experimental conditions. Artificial neural network (ANN) models were developed to predict the second law of efficiency and total irreversibility of the refrigeration system. ANN and ANFIS model predictions were also compared with experimental results and an absolute fraction of variance in range of 0.980–0.994 and 0.951–0.977, root-mean-square error in the range of 0.1636–0.2387 and 0.2501–0.4542 and mean absolute percentage error in the range of 0.159–0.572 and 0.308–0.931%, respectively, were estimated. The outcomes suggested that ANN model shows better statistical prediction than ANFIS model.