Artificial neural network model research on effects of cross-wind to performance parameters of wet cooling tower based on level Froude number

Abstract Based on level Froude number ( Fr l ), an artificial neural network (ANN) model is set up to predict performance parameters of wet cooling tower under cross-wind conditions in this paper, enough data are gathered by a thermal state model experiment to finish ANN training and prediction. Then three-layer back propagation network model which has one hidden layer is developed, and the node number in input layer, hidden layer and output layer are 4, 8 and 6, respectively. This model adopts the improved BP algorithm, that is, the gradient descent method with momentum, and the input parameters are level Froude number, water spraying density, inlet water temperature and relative humidity of inlet air, the output parameters are air gravity wind velocity of inlet tower, temperature difference, cooling efficiency, heat transfer coefficient, mass transfer coefficient and evaporative loss proportion. This BP model demonstrated a good statistical performance with the MRE and R in the range of 0.48%–3.92% and 0.992–0.999, and the RMSE values for the ANN training and predictions were very low relative to the range of the experiments. Thus, the developed BP model can be used to predict successfully the thermal performance of wet cooling tower under cross-wind conditions.