Heat transfer analysis of a fully wetted inclined moving fin with temperature-dependent internal heat generation using DTM-Pade approximant and machine learning algorithms

Abstract

This study investigates the thermal properties of a longitudinally inclined moving porous fin with varying internal heat generation. The approach takes into account the combined influence of natural convection, radiation, and the wet condition while modelling the fin’s energy equation. Using dimensionless terms, the governing energy balance equation is converted into an ordinary differential equation (ODE), which is then solved using the Differential transform method (DTM) and Pade approximant. The machine learning (ML) algorithms is also implemented for detecting temperature fluctuations in wetted fins. The ability of stacking ensemble ML model is employed to strengthen the reliability and accuracy of forecasts, which demonstratrates the improved regression predictions with absolute error rates ranging at 10⁻⁶. The coefficient of regression of 1 indicates the best fit for the data signifying efficient ML prediction. The graphical representations demonstrate how thermal factors influence temperature dispersion. The analysis reveals that the fin’s temperature rises with increasing ambient temperature, nondimensional internal heat generation, generation number, power exponent, and Peclet number. However, under these conditions the temperature gradient reduces. Furthermore, greater values of the convective, radiative, wet porous, and inclination angle parameters result in lower fin temperatures, which aids in cooling while increasing the temperature gradient.