Predicting the efficiency of CuO/water nanofluid in heat pipe heat exchanger using neural network

In this study, the CuO/water nanofluid was used to increase the performance of heat pipe heat exchanger. The results showed that the rise in the input power of the heat pipe leads to increase the wall temperature of the pipe, whereas augmenting the concentration of nanoparticles leads to reduce the wall temperature and decrease the temperature difference between the evaporator and the condenser. Using the nanoparticles increases the thermal conductivity of the base fluid and minimizes the temperature gradient within it. Therefore, the thermal power of the heat pipe increases and its resistance decreases. Also, the results showed that with increasing evaporation filling ratio, the resistance reduces (by Fr = 0.45) and then increases. Additionally, experimental data was compared with published data for the heat pipe in order to accurately evaluate the results obtained in this study. The results showed that the measured data are highly accurate. Also, the heat conductivity resistance equation was calculated based on the experimental data. In the next step, the model of neural networks was used to predict thermal performance, FR, the concentration of nanofluid and input power. The results showed that the network with an accuracy of 0.9938 is able to predict the heat transfer coefficient. A review of the predicted and experimental results for the verification part indicated that the residuals are scattered around the zero axis.