An artificial neural network analysis of the thermal distribution of a fractional-order radial porous fin influenced by an inclined magnetic field

Abstract

Fins and radial fins are essential elements in engineering applications, serving as critical components to optimize heat transfer and improve thermal management in a wide range of sectors. The thermal distribution within a radial porous fin was investigated in this study under steady-state conditions, with an emphasis on the impact of different factors. The introduction of an inclined magnetic field was investigated to assess the effects of convection and internal heat generation on the thermal behavior of the fin. The dimensionless form of the governing temperature equation was utilized to facilitate analysis. Numerical solutions were obtained through the implementation of the Hybrid Cuckoo Search Algorithm-based Artificial Neural Network (HCS-ANN). The Hartmann number (M) and the Convection-Conduction parameter (Nc) were utilized in the evaluation of heat transfer efficiency. Enhanced efficiency, as evidenced by decreased temperature and enhanced heat removal, was correlated with higher values of these parameters. Residual errors for both M and Nc were contained within a specified range of $ 10^{-6} $ to $ 10^{-14} $, thereby offering a quantitative assessment of the model's accuracy. As a crucial instrument for assessing the performance and dependability of predictive models, the residual analysis highlighted the impact of fractional orders on temperature fluctuations. As the Hartmann number increased, the rate of heat transfer accelerated, demonstrating the magnetic field's inhibitory effect on convection heat transport, according to the study. The complex relationship among Nc, fractional order (BETA), and temperature was underscored, which motivated additional research to improve our comprehension of the intricate physical mechanisms involved. This study enhanced the overall understanding of thermal dynamics in radial porous fins, providing significant implications for a wide array of applications, including aerospace systems and heat exchangers.

Keywords

• shear rate dependent viscosity
• thermal enhancement
• sisko fluid
• numerical solution
• artificial neural network
• hybrid cuckoo search