Numerical and hybrid physics-informed neural network study of magnetohydrodynamic blood-based Jeffrey ternary hybrid nanofluid flow over a wedge

Introduction The current study explores the magnetohydrodynamic flow, heat transfer, and entropy generation characteristics of a blood-based Jeffrey ternary hybrid nanofluid containing graphene oxide (GO), titanium dioxide (TiO 2 ), and iron oxide (Fe 3 O 4 ) nanoparticles over an impermeable wedge embedded in a porous medium. The mathematical model accounts for the effects of the magnetic field, porous-medium resistance, thermal radiation, heat generation/absorption, viscous dissipation, and Jeffrey fluid rheology. Methods Through appropriate similarity transformations, the governing partial differential equations are converted into a system of nonlinear ordinary differential equations. The transformed equations are solved numerically using a boundary value problem (BVP) solver and subsequently analyzed through a Hybrid Physics-Informed Neural Network (HPINN) framework. The proposed HPINN combines governing-equation residuals, boundary constraints, and sparse numerical anchor data to obtain physically consistent predictions. The effects of the magnetic parameter, porous-medium resistance parameter, radiation parameter, Brinkman number, heat source/sink parameter, and Jeffrey fluid parameter on the velocity, temperature, entropy generation, skin-friction coefficient, and Nusselt number are examined in detail. Result The results show that the momentum transport characteristics are strongly influenced by the magnetic, porous-medium resistance, and Jeffrey fluid parameters, whereas thermal radiation enhances thermal boundary-layer growth. Entropy generation increases with increasing Brinkman number and Jeffrey fluid parameter, indicating greater thermodynamic irreversibility, particularly near the wedge surface. In addition, the HPINN predictions show close agreement with the benchmark numerical solutions and demonstrate satisfactory predictive capability for the transport quantities studied. Discussion The proposed methodology presents an efficient and reliable computational tool for the analysis of non-Newtonian hybrid nanofluid transport phenomena in biomedical engineering, thermal management systems, and intelligent heat-transfer applications.

Authors

Institutions

Publication Details

Journal
Frontiers in Artificial Intelligence
Published
2026-11-17
DOI
https://doi.org/10.3389/frai.2026.1960993
Primary Topic
Nanofluid Flow and Heat Transfer
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Numerical and hybrid physics-informed neural network study of magnetohydrodynamic blood-based Jeffrey ternary hybrid nanofluid flow over a wedge

Durgaprasad P, Krishnan D
4 links
Frontiers in Artificial Intelligence
Nanofluid Flow and Heat Transfer
article

Numerical and hybrid physics-informed neural network study of magnetohydrodynamic blood-based Jeffrey ternary hybrid nanofluid flow over a wedge

Durgaprasad P, Krishnan D
article en

Abstract

Introduction The current study explores the magnetohydrodynamic flow, heat transfer, and entropy generation characteristics of a blood-based Jeffrey ternary hybrid nanofluid containing graphene oxide (GO), titanium dioxide (TiO 2 ), and iron oxide (Fe 3 O 4 ) nanoparticles over an impermeable wedge embedded in a porous medium. The mathematical model accounts for the effects of the magnetic field, porous-medium resistance, thermal radiation, heat generation/absorption, viscous dissipation, and Jeffrey fluid rheology. Methods Through appropriate similarity transformations, the governing partial differential equations are converted into a system of nonlinear ordinary differential equations. The transformed equations are solved numerically using a boundary value problem (BVP) solver and subsequently analyzed through a Hybrid Physics-Informed Neural Network (HPINN) framework. The proposed HPINN combines governing-equation residuals, boundary constraints, and sparse numerical anchor data to obtain physically consistent predictions. The effects of the magnetic parameter, porous-medium resistance parameter, radiation parameter, Brinkman number, heat source/sink parameter, and Jeffrey fluid parameter on the velocity, temperature, entropy generation, skin-friction coefficient, and Nusselt number are examined in detail. Result The results show that the momentum transport characteristics are strongly influenced by the magnetic, porous-medium resistance, and Jeffrey fluid parameters, whereas thermal radiation enhances thermal boundary-layer growth. Entropy generation increases with increasing Brinkman number and Jeffrey fluid parameter, indicating greater thermodynamic irreversibility, particularly near the wedge surface. In addition, the HPINN predictions show close agreement with the benchmark numerical solutions and demonstrate satisfactory predictive capability for the transport quantities studied. Discussion The proposed methodology presents an efficient and reliable computational tool for the analysis of non-Newtonian hybrid nanofluid transport phenomena in biomedical engineering, thermal management systems, and intelligent heat-transfer applications.

Frontiers in Artificial IntelligenceVol. 9
Vellore Institute of Technology University (IN)
Nanofluid Flow and Heat Transfer
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