Neural network modeling of convection heat transfer coefficient for the casson nanofluid

Abstract

This paper presents applications of Artificial Neural Network (ANN) to develop a mathematical model of magnetohydrodynamic (MHD) flow and heat transfer in a Casson nanofluid. The model equations are solved numerically by Runge-Kutta Fehlberg method with shooting technique. In the developing ANN model, the performance of the various configuration were compared with various types of errors such as Mean Square Error (MSE), Mean Absolute Error (MAE) and Sum Square Error (SSE). The best ANN configuration incorporated two hidden layers with twenty five neurons in each hidden layer was able to construct convective heat transfer coefficients with MSE, MAE and SSE of 0.006346, 0.009813 and 1.015423%, respectively, and had R² of 0.741516. A good co-relation has been obtained between the predicted results and the numerical values.