Machine learning-assisted thermal analysis of propylene glycol nanofluid with dual flux and bioconvection over a Riga plate

The current study investigates the behavior of non-Newtonian nanofluids with Cattaneo-Christov dual flux by using various effects of different physical parameters over a Riga plate. Nanoparticles significantly increase the heat transfer rate and serve as powerful tools for improving energy storage devices and solar thermal systems. The novelty of the current research study is the mixing of copper nanoparticles (Cu) in the propylene glycol. (C₃H₈O₂) has highly thermodynamic properties. The main objective of the present analysis is to enhance the rate of heat and mass transfer in the nanofluid. Therefore, the Cattaneo-Christov model was used in the heat and mass equations to increase the heat transfer rate of the fluid model. The PDE system of the problem is converted into an ODE system using suitable transformations. The solution to the mathematical problem was obtained by applying the bvp4c technique of MATLAB. The graphical results represent the physical properties of the nanofluid, including the bioconvection, concentration, temperature, and velocity profiles. Furthermore, tables were used to compute the numerical values of motile microorganisms, Sherwood number, Nusselt number, and skin friction coefficient. Boosting the parameters, such as the modified Hartmann number, buoyancy ratio, and Rayleigh number, of bio-convection increases the velocity profile. The temperature profile increased as the thermophoresis parameter, heat relaxation time parameter, and Eckert number increased. Additionally, this study uses an intelligent numerical computing method known as MLFF, which is based on ANN. These artificial neural networks are used to optimize physical quantities and verify the accuracy of data by training, validation, and testing.