Optimal COP prediction of a solar intermittent refrigeration system for ice production by means of direct and inverse artificial neural networks

A direct and inverse artificial neural network (ANN and ANNi) approach were developed to predict the required coefficient of performance (COP) of a solar intermittent refrigeration system for ice production under various experimental conditions. Ammonia/lithium nitrate was used as a working fluid considering different solution concentrations. The configuration 6-6-1 (6 inputs, 6 hidden and 1 output neurons) presented an excellent agreement (R > 0.986) between experimental and simulated values. The used inputs parameters were: the solution concentration, the cooling water temperature, the generation temperature, the ambient temperature, the generation pressure and the solar radiation. The sensitivity analysis showed that all studied input variables have effect on the COP prediction but the generation pressure is the most influential parameter on the COP, while the rest of input parameters were less significant. COP performance was also determined by inverting ANN to calculate the unknown input parameter from a required COP. Because of the high accuracy and short computing time makes this methodology useful to simulate and to optimize the solar refrigerator system.

► More than 650 set of data were used to evaluate the solar refrigeration system.
► A methodology based on artificial neural networks was used to predict the system performance.
► A very good accuracy was obtained on the prediction of the coefficients of performance by means of ANN.
► The good results suggest that ANN could be used to predict the efficiencies of other solar thermal devices.