PREDICTION OF NATURAL CONVECTION HEAT TRANSFER AND FLUID FLOW IN AN ANNULUS USING ARTIFICIAL NEURAL NETWORKS

In the present work Artificial Neural Network (ANN) is used to predict the temperature and flow fields for natural convection in a concentric annulus having constant surfaces temperatures. Governing equations of natural convection are solved using FLUENT to generate databases for ANN in the range of Rayleigh numbers from 102 to 107. Then a multilayer perceptron network with different training algorithm is used and it is found that the Levenberg-Marquardt training algorithm is the best algorithm for this analysis because of its faster training procedure. Results obtained CFD are used for training and testing the ANN approach. A comparison is performed among the soft programming ANN and CFD results and it is observed that ANN soft programming code can be used more efficiently to determine stream function and temperature fields generated in an annulus

کلیدواژه ها:

Annulus ، Artificial neural networks ، Natural convection