Optimization of heat and mass transfer in chemically radiative nanofluids using Cattaneo-Christov fluxes and advanced machine learning techniques

Abstract

This paper investigates the effects of heat radiation and magnetic forces on the motion of a viscous nanofluid across a stretched sheet. Cattaneo-Christov fluxes are utilized in this investigation to clarify thermal and concentration diffusions in heat and mass transport. An innovative Morlet-Wavelet artificial neural network addresses complex mathematical challenges by providing a solution to the complex problem. Utilizing diagrammatic representations, the effects of diverse physical movement conditions on concentration and temperature profiles are clarified. Our investigation demonstrates that radiation, thermophoretic, and Brownian parameters increase as the temperature rises. In contrast, a temperature profile decreases when both the Prandtl number and ratio parameter are increased. The overall AE fall within 10-03-10-07.The MSE values lie within the interval of 1001-10-05.The FIT spread over the range of 100-10-12 while the MAD values lie in the interval 10-01-10-07.The Mean values observed between 10-03 and 10-04 while the Standard deviation values fall within the range 10-02-10-04, demonstrating that the proposed methodology is precise and consistent. The analysis improved comprehension and surpassed conventional methods. This functionality empowers specialists to oversee the progression of optimization, identify convergence patterns, and adjust algorithms to achieve superior results, thereby making a remarkable contribution to heat transfer and fluid dynamics.

Keywords

• Morlet-Wavelet neural networks
• Cattaneo-Christov heat flux model
• MHD
• Thermal radiation
• Cattaneo-Christov dual diffusion