Heat rate predictions in humid air-water heat exchangers using correlations and neural networks

We consider the flow of humid air over fin-tube multi-row, multi-column com pact heat exchangers with possible condensation. Previously published exper imental data are used to show that a regression analysis for the best-fit c orrelation of a prescribed form does not provide an unique answer, and that there are small but significant differences between the predictions of the different correlations thus obtained. Ir is also shown that it is more acc urate to predict the heat rate directly rather than through intermediate qu antities like the j-factors. The artificial neural network technique is off ered as an alternative technique. It is trained with experimental values of the humid-air flow rates, dry-bulb and wet-bulb inlet temperatures, fin sp acing, and heat transfer rates. The trained network is then used to make pr edictions of the heat transfer. Comparison of the results demonstrates that the neural network is more accurate than conventional correlations.