Performance enhancement and ANN prediction of R600a vapour compression refrigeration system using CuO/Sio2 hybrid nanolubricants: an energy conservation approach

In this study improvement in performance of vapour compression refrigeration using R600a as refrigerant is enhanced by using CuO/Sio2 hybrid nanolubricants. The experiment was performed with four various nanolubricants concentration of 0.2, 0.4, 0.6 and 0.8 g/L and refrigerant mass charges of 60, 70 and 80 g. Three significant variables like coefficient of performance, cooling effect and compressor work was determined. Artificial neural network (ANN) techniques are applied to predict the R600a refrigerator performance dispersed with hybrid nanolubricants by training the input parameters like nanolubricants concentrations, refrigerant mass flow rate, evaporator and condenser temperatures. MATLAB tool box is used to predict the experimental data’s. In the network, the back propagation algorithm was utilized. The ANN predicted outputs in comparison to experimental output of refrigeration effect, compressor and COP were significantly enhanced. The ANN predicted coefficient of performance is enhanced from 2.4 to 3.8 with 36% increase in COP, refrigeration effect from 112 to 253 W with 55% increase in refrigeration effect and reduction in compressor work from 147 to 108 W with 27% reduction in power utilized by the compressor in comparison with the system without dispersion of nanolubricant. The ANN model predicted output is accepted with the experimental and the values of mean square error and percentage error are also provided. The predicted data are useful and significant for substituting CuO/Sio2 hybrid nanolubricants with vapour compression refrigeration without addition of nanoparticles and this trained output provide the optimization of CuO/Sio2 hybrid nanolubricants in household refrigerator.