Analysis of fractional operator and neural network on the flow of nanofluid with slip effect

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.

Authors

Institutions

Publication Details

Journal
Discover Mechanical Engineering
Published
2026-11-19
DOI
https://doi.org/10.1007/s44245-026-00383-9
Primary Topic
Fractional Differential Equations Solutions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Analysis of fractional operator and neural network on the flow of nanofluid with slip effect

Imran Siddique, Kamolova Nargiza Ibragimovna, Muhammad Ramzan, Shajar Abbas et al.
Discover Mechanical Engineering
Fractional Differential Equations Solutions
article

Analysis of fractional operator and neural network on the flow of nanofluid with slip effect

Imran Siddique, Kamolova Nargiza Ibragimovna, Muhammad Ramzan, Shajar Abbas, Emad Ahmad Az-Zo’bi, Afnan Al Agha, Abdul Raqib Muslimyar, Hakim A. L. Garalleh, Ibrahim Mahariq
article en

Abstract

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.

Discover Mechanical EngineeringVol. 5(1)
Bahauddin Zakariya University (PK), Korea University (KR), Thi Qar University (IQ), Mutah University (JO), Al-Quds University (PS), İstanbul Gelişim Üniversitesi (TR), Kabul Education University (AF), Biruni University (TR), Islamic University of Madinah (SA), National Pedagogical University of Uzbekistan named after Nizami (UZ), University of Business and Technology (SA)
Fractional Differential Equations Solutions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon