An estimation of the performance of a passive cooling system incorporating a ground heat exchanger using a multilayer artificial neural network

Abstract

Abstract Objective: This paper examines the cooling of an office building without a heat pump, using only ground heat exchangers (GHE) and implementing artificial neural network (ANN) to train it on experimental data. Methods: The office building is situated at 38° 40? 57?? N latitude and 39° 10? 29?? E longitude in the province of Elazig. Each minute, the installed system was monitoring the office’s external meteorological data, the office’s indoor meteorological data, the GHE inlet and outlet temperatures, and the amount of heat load developed during the cooling process. In this study, the passive cooling system’s cooling load and coefficient of performance (COP) were experimentally examined. A second important contribution of this paper is the multilayer ANN model that was created using data selected from the experimental setup, which was measured and recorded. Results: During the summer months of 2018, the COP of the system was measured to be 1.67 on average. The accuracy rates of the multilayer ANN model proposed for cooling systems were calculated to be over 99% and 95% in the training and test datasets, respectively. It was observed that the performance value estimated by ANN converges to the true value by 99%. Conclusion: Having performed this study, it has been demonstrated that passive cooling can be achieved with GHE, and by conducting this study without utilizing a heat pump system, we intend to contribute significantly to the relevant scientific literature.