Modelling of a direct evaporative air cooler using artificial neural network

This paper proposes the use of artificial neural networks (ANNs) to predict various performance parameters of a direct evaporative air cooler. For this aim, an experimental evaporative cooler was operated at steady-state conditions, while varying the dry bulb temperature and relative humidity of the entering air along with the flow rates of air and water streams. Using some of the experimental data for training, a three-layer feed-forward ANN model based on back propagation algorithm was developed. This model was used for predicting various performance parameters of the cooler, namely the dry bulb temperature and relative humidity of the leaving air, mass flow rate of the water evaporated into the air stream, sensible cooling rate, and effectiveness of the cooler. Then, the performance of the ANN predictions was tested by applying a set of new experimental data. The predictions usually agreed well with the experimental values with correlation coefficients in the range of 0.969–0.993, mean relative errors in the range of 0.66–4.04%, and very low root mean square errors. This study reveals that, as an alternative to classical modelling techniques, the ANN approach can be used successfully for predicting the performance of direct evaporative air coolers. Copyright © 2007 John Wiley & Sons, Ltd.