Efficiency assessment of thermal radiation utilizing flow of advanced nanocomposites on riga plate

Utilizing nanostructured materials to optimize thermal processes for renewable energy is an important strategy that has been applied in numerous engineering disciplines for diverse interventions such as photovoltaic thermal systems. Ternary nanofluids have demonstrated potential for improving the cooling capabilities of this kind of system. The current research focuses on enhancing the thermal performance of convective flow of a water-based trihybrid nanofluid across a Riga plate incorporating carbon nanotubes in spherical, graphene in cylindrical and Al₂O₃ in platelet shapes. Several mechanisms like non-linear heat production, thermal radiation, velocity and thermal slip conditions have all been investigated regarding the flow describing equations. Due to the high complexity of the problem modeling and numerical methods, conventional techniques to the parametric work that incorporate various model factors can fail to derive accurate solutions. This study assesses the ability of soft computing techniques to determine the behavior of a problem with various connected parameters to resolve this issue. With help from numerical scheme Lobatto IIIa technique reference data, the artificial neural network is trained. Furthermore, a constructive technique using artificial neural networks (Levenberg–Marquardt) is used to quantitatively determine the rate of heat transmission on the surface of Riga plates. With the use of correlation, fitting analysis, regression, mean squared error, absolute error, and error histogram, the prediction performance of the proposed algorithms is examined. The C_fx and Nu_x reach convergence with mean squared errors close to 10⁻⁸ and 10⁻¹⁰ after 626 and 100 epochs. The investigation illustrates the benefits of using soft computing methods to accurately investigate the behavior of complex flow models. The most important discovery is that, in comparison to mono- and binary-hybrid nanofluids, ternary hybrid nanofluids have a greater thermal responsiveness.