Investigation on heat transfer characteristics of roughened solar air heater using ANN technique

Abstract

In present work, Artificial Neural Network (ANN) model has been developed to predict the heat transfer from roughened absorber plate to air passing through the ducts of solar air heater and compared with actual experimental data. Two different types of SAH ducts with roughened absorber plate at single side in one and three sides absorber plates in the other, have been taken up for the analysis of heat transfer. The data for analysis have been collected by conducting actual experiments on the SAHs. ANN model has been structured with five input parameters such as number of rough surface sides, relative roughness height, relative roughness pitch, roughness size and Reynolds Number in input layer, and Nusselt number in output layer. Levenberg-Marquardt (LM) algorithm with feed-forward back propagation is used in present model. The LM learning algorithms with 10 neurons in hidden layer has been found as optimal on the basis of statistical error analysis. The predicted value of heat transfer of solar air heater with highest R2 value gives satisfactory results. The values of RMSE, MAE and R2 were found 0.892025, 0.66261 and 0.99532 respectively during training stage. Similarly, for testing stage these values were 0.55094, 0.3168 and 0.9979 respectively. The statistical results show that the proposed MLP ANN model successfully predicts the heat transfer analysis of roughened solar air heater.