Supervised machine learning techniques for optimization of heat transfer rate of Cu-H₂O nanofluid flow over a radial porous fin

Abstract

Purpose

The purpose of this paper is to study the thermal behavior of radial porous fin surrounded by water-base copper nanoparticles under the influence of radiation.

Design/methodology/approach

In order to optimize the response variable, the authors perform sensitivity analysis with the aid of response surface methodology (RSM). Moreover, this study enlightens the applications of artificial neural networks (ANN) for predicting the temperature gradient. The governing modeled equations are firstly non-dimensionalized and then solved with the aid of Runge–Kutta fourth order together with the shooting method in order to guess the initial conditions.

Findings

Numerical results are analyzed and presented in the form of tables and graphs. This study reveals that the temperature of the fin is decreasing as the wet porous parameter increases (m₂) and the temperature for 10% concentration of nanoparticles are higher than 5 and 1%. Physical parameters involved in the study are analyzed and processed through RSM. It is come to know that sensitivity of temperature gradient to radiative parameter (Nr) and convective parameter (Nc) is positive and negative to dimensionless ambient temperature (θ_a). Furthermore, after ANN training it can be argued that the established model can efficiently be used to predict the temperature gradient over a radial porous fin for the copper-water nanofluid flow.

Originality/value

To the best of our knowledge, only a few attempts have been made to analyze the thermal behavior of radial porous fin surrounded by copper-based nanofluid under the influence of radiation and convection.

Citation

Raza, J., Raza, M., Mustaq, T. and Qureshi, M.I. (2023), "Supervised machine learning techniques for optimization of heat transfer rate of Cu-H₂O nanofluid flow over a radial porous fin", Multidiscipline Modeling in Materials and Structures, Vol. 19 No. 4, pp. 680-706. https://doi.org/10.1108/MMMS-08-2022-0153