Analyzing magnetic dipole impact in fluid flow with endothermic/exothermic reactions: neural network simulation

Abstract

The consequence of exothermic/endothermic chemical reactions and Arrhenius activation on the heat and mass transport of the liquid flow past a cylinder in the incidence of a magnetic dipole is considered in the current investigation. Magnetic dipoles are used in medical applications such as magnotherapy and spectroscopy, to produce static magnetic fields. Scientists and engineers can improve the effectiveness of chemical reactions or heat transfer operations by analyzing the impact of reactions on flow and building systems with optimized flows. The modelled equations are converted into non-dimensional ordinary differential equations (ODEs) by using similarity variables. The resultant equations are solved by employing the physics-informed neural network (PINN) technique. Additionally, the comparison of PINN with the numerical method Runge–Kutta Fehlberg’s fourth-fifth order (RKF-45) is studied. The effects of different parameters on the temperature, concentration, and velocity profiles for endothermic/exothermic instances are shown graphically. The thermal, velocity, and concentration profiles get stronger as the curvature parameter values increase for both endothermic and exothermic cases. The influence of activation energy parameters, chemical reaction parameters, and endothermic/exothermic reaction parameters on the thermal and concentration is also depicted.