A novel design of inverse multiquadric radial basis neural networks to analyze MHD nanofluid boundary layer flow past a wedge embedded in a porous medium under the influence of radiation and viscous effects

The current study explores a new direction of research in which the magnetohydrodynamic (MHD) effects on two-dimensional nanofluid boundary layer flow under the influence of radiation are investigated in a porous medium using inverse multiquadric (IMQ) radial basis neural networks (RBNNs) i.e. IMQ-RBNNs. A quite new computational approach is used here in which artificial neural networks (ANNs) acquired IMQ radial basis function as an activation function in an amalgam of globally searching solver named genetic algorithms (GAs) together with an efficient local searching sequential quadratic programming (SQP) solver. The basic equations that represent the fluid flow are first obtained in the form of partial differential equations (PDEs) and then converted into dimensionless ordinary differential equations (ODEs) by applying similarity transformations. The dynamical properties of the nanofluid including velocity, temperature along mass concentration are analyzed by varying physical parameters including radiation parameter, magnetic parameter, constant moving parameter, heat source parameter, Brownian motion parameter and Eckert number. Moreover, the escalation in the value of the constant moving parameter diminishes the fluid velocity but this effect is reversed in the case of magnetic parameter. The increasing values of heat source parameter, Brownian motion parameter and Eckert number inflate the nanofluid temperature but a reversal effect is observed in the case of radiation parameter. It is also observed that larger values of heat Brownian motion parameter and radiation parameter amplify the nanofluid concentration but an opposite effect is obtained in the case of heat source parameter. The numerical results of the proposed model obtained through the IMQ-RBNNs based solver optimized with GASQP algorithm. The efficacy and tendency of rapid convergence of the proposed solver are endorsed through graphical illustrations and tables using well-known statistical operators with various fitness analyses on MATLAB are also part of this research.

Automated summary

This study investigates the magnetohydrodynamic effects and radiation effects on two-dimensional nanofluid boundary layer flow in a porous medium using inverse multiquadric radial basis neural networks (IMQ-RBNNs). A new computational approach combining artificial neural networks (ANNs) with genetic algorithms (GAs) and sequential quadratic programming (SQP) is used. The dynamical properties of the nanofluid, including velocity, temperature, and mass concentration, are analyzed by varying physical parameters. The numerical results obtained through the IMQ-RBNNs based solver optimized with GASQP algorithm are validated through graphical illustrations and tables.