Performance of ammonia–water refrigeration systems using artificial neural networks

In this paper, a new formulation, based on artificial neural network (ANN) model, is presented for the analysis of ammonia–water absorption refrigeration systems (AWRS). Performance analysis of the AWRS is very complex because of analytic functions used for calculating the properties of fluid couples and simulation programs. Therefore, it is extremely difficult to perform analysis of this system. It is well known that the generator temperature, evaporator temperature, condenser temperature, absorber temperature, poor and rich solution concentration affect the AWRS's coefficient of performance (COP) and circulation ratio (f). In this study, COP and f are estimated depending on the above temperatures and concentration values. Using the weights obtained from the trained network a new formulation is presented for the calculation of the COP and f; the use of ANN is proliferating with high speed in simulation. The R²-values obtained when unknown data were used to the networks was 0.9996 and 0.9873 for the circulation ratio and COP, respectively which is very satisfactory. The use of this new formulation, which can be employed with any programming language or spreadsheet program for the estimation of the circulation ratio and COP of AWRS, as described in this paper, may make the use of dedicated ANN software unnecessary.