Performance prediction of a shower cooling tower using wavelet neural network

Abstract

This paper develops an application of a wavelet neural network (WNN) based model to predict the performance of a shower cooling tower (SCT). In order to gather data to train and test the proposed WNN model, an experimental shower cooling tower was operated at some steady state conditions. Some of the experimental data are utilized for training. The model was used to predict various performance parameters of the system, namely the temperature difference of the outlet and inlet water stream and the dry bulb temperature, relative humidity of the outlet air stream, the water evaporative ratio and the cooling efficiency of the system. The performances of the WNN predictions were tested using experimental data not employed in the training process. The predictions yielded good agreement with the experimental values with correlation coefficients in the range of 0.9906–0.9986, mean relative errors in the range of 1.39–2.28% and very low root mean square errors. The results show that the WNN technique can be used effectively for predicting the performance characteristics of SCT under various operating conditions, then providing the theoretical basis on the research of heat and mass transfer inside SCT under any conditions, which is important for design and running control of the SCT system.