EXPERIMENTAL ANALYSIS OF THE EFFECT OF NANOFLUID USE ON POWER AND EFFICIENCY ENHANCEMENT IN HEAT PIPE SOLAR COLLECTORS AND MODELING USING ARTIFICIAL NEURAL NETWORKS

Abstract

Solar energy systems have significant advantages over traditional energy production methods, but improvements are needed to improve performance and efficiency. In this study, the effect of the use of nanofluids on power and efficiency values in a heat pipe solar collector was analyzed using experimental and artificial intelligence approaches. A heat pipe solar collector was fabricated and the effects of prepared water-based Al<sub>2</sub>O<sub>3</sub> and TiO<sub>2</sub> nanofluids on power and efficiency values were experimentally investigated. Using the obtained experimental data, an artificial neural network model has been developed to predict power and efficiency values. The values obtained from the network model were compared with the experimental data and the prediction performance of the network model was extensively examined using various performance parameters. The coefficient of performance value for the neural network model was calculated as 0.99332 and the mean squared error value was calculated as 2.77E-03. The study findings revealed that the use of nanofluids in the heat pipe solar collector improves the power and efficiency values. It has also been seen as a result of the study that the developed artificial neural network model can predict power and efficiency values with deviation rates lower than 0.48%.