ANN modelling on heat and mass transfer in MHD chemically reactive and radiative flow of hybrid ferrofluid over a non-linear stretching porous surface

被引:0
作者
S. Manjunatha [1 ]
J. Santhosh Kumar [1 ]
M. Veera Krishna [2 ]
S. V. K. Varma [3 ]
机构
[1] REVA University,Department of Mathematics, School of Applied Sciences
[2] Saveetha School of Engineering,Department of Mathematics
[3] Rayalaseema University,Department of Mathematics
关键词
Porous medium; Magnetic field; Ferro fluid; Heat generation/absorption; Darcy–Forchheimer; Suction parameter; Thermal radiation;
D O I
10.1007/s41939-025-00879-z
中图分类号
学科分类号
摘要
This study presents a novel application of an intelligent numerical computing solver using an ANN modelling that employs the Levenberg–Marquardts algorithm. The endeavour of current work is to investigates the heat transport analysis of the non-linear streching sheet in the presence of Brownian motion, Eckert number, and porous medium. The non-linear partial differential equations are derived for the mathematical model, and they are reduced to non-linear ordinary differential equations by utilizing similarity transformations. The resultant governing equations are solved by making use of the bvp4c programme solver package with the help of MATLAB. The impacts of significant parameters are analysed by graphical profiles and tables, and analyse the derived quantities of velocity, temperature and concentration. In addition, the coefficient of skin friction, Nusselt number, and Sherwood number in terms of shear stress, rate of heat transport, and the rate of mass transport. To analyse the rate of heat transport, the ANN modelling is utilized. The 246 number of data points are generated, and they are divided into 70% training, 15% testing, and 15% validating data. As the magnetic parameter growing, fluid flow decreases, and the reversal trend shows in the temperature profile due to Lorentz force. The porous and Darcy–Forchheimer parameters increase the fluid flow velocity, causing it to decrease. The ANN model yielded a regression coefficient value of R = 0.98314, indicating a strong correlation between the input and output data.
引用
收藏
相关论文
empty
未找到相关数据