Neural network analysis for prediction of heat transfer of aqueous hybrid nanofluid flow in a variable porous space with varying film thickness over a stretched surface

The high thermal conductivity of the nanoparticles in hybrid nanofluids results in enhanced thermal conductivity associated with their base fluids. Enhanced heat transfer is a result of this high thermal conductivity, which has significant applications in heat exchangers and engineering devices. To optimize heat transfer, a liquid film of Cu and TiO₂ hybrid nanofluid behind a stretching sheet in a variable porous medium is being considered due to its importance. The nature of the fluid is considered time-dependent and the thickness of the liquid film is measured variable adjustable with the variable porous space and favorable for the uniform flow of the liquid film. The solution of the problem is acquired using the homotopy analysis method HAM, and the artificial neural network ANN is applied to obtain detailed information in the form of error estimation and validations using the fitting curve analysis. HAM data is utilized to train the ANN in this study, which uses Cu and TiO₂ hybrid nanofluids in a variable porous space for unsteady thin film flow, and it is used to train the ANN. The results indicate that Cu and TiO₂ play a greater role in boosting the rate.