Effectiveness prediction of CuO nanofluid heat pipe system using fuzzy neuro approach

Heat pipes are used in electronic equipment to protect multiple components from overheating. This article focusses on the development of heat pipe heat exchanger system which uses nanofluid as the working fluid. Copper oxide nanoparticles are suspended in an acetone base and this mixture acts as the working fluid. The different working parameters considered are inclination angle, mass flow rate and temperature. Multiple experiments were conducted at various levels and various combinations of the parameters and the results are analysed. It was observed that temperature had the most significant impact of 67% followed by the angle of inclination which had a 24% contribution on the effectiveness of the process. 3D Pareto plots are represented for each of the factor combinations and the patterns have been reported. The results from the experiments are further modelled using an adaptive neuro fuzzy inference system in order to develop a predictive model. The neuro-fuzzy model converged with a least error of 0.3383. The predicted values from the neural network showed a deviation of less than 5% when compared to the experimental values. The results indicate an acceptable amount of error and the creation of a robust model.