Thermal analysis of a wetted fin of wavy pattern under convective-radiative heat transfer using artificial neural network

The wavy wet fin with internal heat generation is widely used in heat exchangers, refrigeration systems, and cooling devices where condensation and latent heat transfer play a crucial role. In view of this, the current study investigates the influence of internal heat generation on the temperature dispersion and heat transport in a wavy profiled wet fin in the presence of radiation and convection. The wavy fin is wetted with aluminium oxide, titanium dioxide, and copper nanoparticles suspended in water. The heat equation of the wavy profile fin is modeled and converted to the dimensionless equation using appropriate dimensionless terms. The resultant dimensionless temperature equation is solved using Runge Kutta Fehlberg’s fourth-fifth order (RKF-45) approach. Further, the Levenberg-Marquardt artificial neural network (LM-ANN) is considered to assess the thermal dispersion in a wavy fin for various parameters. The LM-ANN is trained using numerical simulation data to predict the heat transfer attributes, including temperature distribution and thermal features. The graphical depiction shows the significance of several parameters on the temperature of the wavy profiled wet fin. The increase in convection-conduction, radiation-conduction, and wet parameters decreases the thermal profile of the fin. The temperature profile intensifies as the values of heat generation number and dimensionless ambient temperature increase.