Artificial neural network approach to simulate the impact of concentration in optimizing heat transfer rate on water-based hybrid nanofluid under slip conditions: A regression analysis

Abstract

The recent era of science depends upon the efficient performance of the heat transfer rate in several engineering applications for which the role of nanofluids have a greater impact. Therefore, the impact of particle concentration in optimizing heat transfer analysis of water-based hybrid nanofluid is conducted via an artificial neural network. The combined effect of oxide nanoparticles such as MgO and TiO2 in water performs their effective role with various factors involved in the flow phenomena. The magnetized hybrid nanofluid flow over an expanding surface filled with porous material shows its noble behavior on the flow properties. Further, it is not usual to omit the effectiveness of the dissipative heat impact. Therefore, the role of viscous, Joule, and Darcy dissipation is incorporated in the energy profile for which the profiles became coupled. The designed nonlinear model invokes suitable similarity rules that give rise to a system of nonlinear ordinary equations in non-dimensional form. Afterwards, the traditional numerical approach is beneficial to conduct the simulation of the flow profiles. The optimization of the heat transfer rate analysis is obtained by the implementation of an artificial neural network (ANN) for the response of Nusselt number using various factors. The regression analysis for the embedding data shows the effectiveness of the proposed approach in this discussion. The proposed study describes the important outcomes as; an increasing slip produces a thinning in the bounding surface thickness for the case of pure fluid comparing to the nanofluid and hybrid nanofluid. Further, the data set used for the hybrid nanofluid shows an efficient fitting than the case of nanofluid.