“Artificial neural network can be used in the modeling of complex physical phenomena, such as in thermal engineering.”

The paper is the result of our group’s efforts and describes an application of artificial neural networks on an absorption refrigeration system, outlining the performance of the system’s speed and its ease of use and the consequent reduction of required engineering effort. This study demonstrates that artificial neural networks (ANNs) can be used instead of the simulation of mathematical models in absorption systems. 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 an ease of design for operators who possess little technical experience.

This paper describes a new method by which a user could carry out a comparative performance study of the system by using both analytic functions and prediction of the ANN, and it is demonstrated that these networks can be used instead of a simulation of mathematical models in these systems.

ANNs can be used in the modeling of complex physical phenomena, such as thermal engineering. This is mainly due to the fact that the networks have very good approximation capabilities and also offer additional advantages such as short development and fast processing times. Our paper is interested in the application of the network to absorption refrigeration systems.

We have been working in the field of absorption refrigeration systems for more than 10 years, developing new solutions and applying them to these systems.