Abstract:

In this paper, we present an Artificial Neural Networks (ANNs) model which is prone to accurately estimate the friction factor and nusselt number of a tube with modified twisted tapes. Numerical analysis were realized using the tapes with six different rates of pitch length of twisted tape to inner diameter of tube (y/D=3, 4, 5) in a range of Reynolds number 8000 to 24000 under uniform heat flux conditions. The ANN model was improved and validated using a databank containing numerical datasets. The back propagation algorithm is recognized to be the most extensive learning method for ANN. This algorithm is used for training and testing of the network. The results of the ANNs were demonstrated superior performance to adapt the numerical datas. Value of the coefficient of multiple determination were obtained. The R2 values were found 0,9994 for nusselt number and 0,9995 for friction factor.

Keywords: