Convective heat transfer prediction of evaporative processes is more complicatedudthan the heat transfer prediction of single-phase convective processes. This is due to the fact that physical phenomena involved in evaporative processes are very complex and vary with the vapor quality that increases gradually as more fluid is evaporated. Power-law correlations used for prediction of evaporative convection have proved little accuracy when used in practical cases. In this investigation, neural-network-based models have been used as a tool for prediction of the thermal performance of evaporative units. For this purpose, experimental data were obtained in a facility that includes a counter-flow concentric pipes heat exchanger with R134a refrigerant flowing inside the circularudsection and temperature controlled warm water moving through the annularudsection. This work also included the construction of an inverse Rankine refrigerationudcycle that was equipped with measurement devices, sensors and a dataudacquisition system to collect the experimental measurements under differentudoperating conditions. Part of the data were used to train several neural-networkudconfigurations. The best neural-network model was then used for predictionudpurposes and the results obtained were compared with experimental data notudused for training purposes. The results obtained in this investigation reveal theudconvenience of using artificial neural networks as accurate predictive tools foruddetermining convective heat transfer rates of evaporative processes.
展开▼
