Answers are grounded in this paper and cite their sources.
The analysis of coupled momentum, heat, and mass transfer in non-Newtonian fluids is important for understanding transport processes involving fluid memory, magnetic effects, porous media, and thermal and concentration variations. This study investigates the transient behavior of an electrically conducting second-grade fluid by developing a fractional mathematical model based on the Atangana–Baleanu (AB) fractional derivative. The main objective is to examine the influence of fractional memory and the governing physical parameters on the velocity, temperature, and concentration distributions and to evaluate the capability of an Artificial Neural Network (ANN) for predicting the corresponding transport characteristics. The governing momentum, energy, and concentration equations are formulated by incorporating the second-grade fluid effects, magnetic field, porous-medium resistance, thermal and solutal buoyancy forces, heat generation/absorption, and chemical reaction. The resulting fractional system is solved analytically using the Laplace-transform technique, and the inverse Laplace transform is evaluated numerically using the Stehfest algorithm. The obtained data are subsequently used to train, validate, and test a feed-forward ANN using the Levenberg–Marquardt algorithm, with 70% of the data used for training and 15% each for validation and testing. The results demonstrate that the fractional order and physical parameters substantially affect the velocity, temperature, and concentration fields, highlighting the importance of nonlocal memory effects in second-grade fluid transport. The ANN predictions show close agreement with the analytical/numerical results and provide accurate approximations with low prediction errors. The proposed fractional second-grade fluid model combined with ANN therefore offers an effective framework for analyzing coupled magnetohydrodynamic heat and mass transfer processes and for efficiently predicting their transport behavior.
No takes yet. Share an insight, caveat, or question.
Garalleh et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: