Intelligent networks knacks for numerical treatment of three-dimensional Darcy–Forchheimer Williamson nanofluid model past a stretching surface

Abstract

Due to its resilience, accurate prediction, simulation and effective evaluation, artificial-intelligence-based applications have gained the attention of researchers. Here, in our study, an Intelligent Backpropagated neural network with the Levenberg–Marquardt method (IBNN-LMM) is used to analyze the Darcy–Forchheimer Williamson Nanofluid model (DFW-NFM) over a stretching surface with the convective conditions. System of PDEs representing IBNN-LMM is transformed into ODEs via suitable conversions. Later on, dataset is acquired from the ODEs applying Homotopy analysis technique (HAT) by the variation of influential parameters. Solution is approximated through training, testing and validation procedure in MATLAB, and comparison is made with standard results. The validation of results is also verified by different plots, for example, MSE performance, absolute error, error via histogram and regression relations. Further, the detailed comparative outcomes of IBNN-LMM for velocity profile in both x- and y-directions, temperature profile and concentration profile with reference HAT for DFW-NFM are represented in terms of numerical and graphical simulations.

KEYWORDS:

• Numerical treatment
• intelligent backpropagated neural network
• Levenberg–Marquardt method
• Williamson nano fluid
• homotopy analysis technique
• Darcy–Forchheimer
• stretching surface

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.