Modelling (using artificial neural-networks) the performance parameters of a solar-driven ejector-absorption cycle

Theoretical thermodynamic analysis of the absorption thermal systems is at present too complex because of analytic functions calculating the thermodynamic properties of fluid couples involving the solution of complex differential equations and simulation programs. This paper proposes a new approach to performance analysis of a solar-driven ejector-absorption refrigeration system (EARS) with an aqua/ammonia working fluid. Use of artificial neural-networks (ANNs) has been proposed to determine the performance parameters as functions of only the working temperature, under various working conditions. Thus, this study is considered to be helpful in predicting the performance of an EARS prior to it being set up in an environment where the temperatures are known. The statistical coefficient of multiple determinations (R2 - value) equals to 0.976, 0.9825, 0.9855 for the coefficient of performance (COP), exergetic coefficient of performance (ECOP) and circulation ratio (F), respectively. These accuracies are acceptable for the design of an EARS. The present method greatly reduces the time required by design engineers to find the optimum solution and in many cases reaches a solution that could not be easily obtained from simple modelling programs. The importance of the ANN approach, apart from reducing the time required, is that it is possible to find solutions that make solar-energy applications more viable and thus more attractive to potential users, such as solar engineers. Also, this approach has the advantages of computational speed, low cost for feasibility, rapid turnaround (which is especially important during iterative design-phases), and ease of design by operators with little technical experience