Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis

This study presents a mathematical model of tissue adhesive based on stretched surfaces with emphasis on flow and thermal characteristics using artificial neural networks with a Levenberg-Marquardt backpropagation scheme (ANN-LMBS). The model investigates Eyring-Powell nanofluids (EP-NF) with ferric...

Full description

Saved in:
Bibliographic Details
Main Authors: Umar Farooq, Ali Alshamrani, M. Mahtab Alam, Khadija Rafique
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Case Studies in Thermal Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214157X25004125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314381869875200
author Umar Farooq
Ali Alshamrani
M. Mahtab Alam
Khadija Rafique
author_facet Umar Farooq
Ali Alshamrani
M. Mahtab Alam
Khadija Rafique
author_sort Umar Farooq
collection DOAJ
description This study presents a mathematical model of tissue adhesive based on stretched surfaces with emphasis on flow and thermal characteristics using artificial neural networks with a Levenberg-Marquardt backpropagation scheme (ANN-LMBS). The model investigates Eyring-Powell nanofluids (EP-NF) with ferric oxide (Fe2O3) and silicon dioxide (SiO2) nanoparticles dispersed in water (H2O), focusing on magnetic strength, Darcy drag, viscous dissipation, joule heating and thermal radiation effects. Validation consists of 70 % training, 15 % testing, and 15 % validation. This dataset covers four scenarios and nine EP-NF cases. The resulting domain is divided into 300 grid points for velocity and temperature profiles. The ANN-LMBS model demonstrated excellent robustness in terms of accuracy, precision, and convergence, as verified by error histograms and regression optimization. The main findings include: as M increases from 1 to 4, the Nusselt number decreases by 2.48 %–2.16 % for Fe2O3 and by 1.71 %–1.54 % for SiO2; as Rd increases from 0.3 to 1.2, the Nusselt number increases by −10.17 % to −6.52 % for Fe2O3 and by −10.19 % to −6.58 % for SiO2; The influence of porosity (ϵ) and Eckert number (Ec) is less pronounced but still noticeable (∼3 % and 1.2 %, respectively). The governing equations, solved numerically via non-similarity transformation and the BVP4C algorithm, align with boundary conditions across all scenarios, with uncertainty analysis confirming solution robustness. Cross-thermal streamline patterns further enhance insights into flow dynamics, underscoring the model's potential in biomedical applications.
format Article
id doaj-art-f9eb51094a9b4b00b9fc55f2e24fe4e2
institution Kabale University
issn 2214-157X
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Case Studies in Thermal Engineering
spelling doaj-art-f9eb51094a9b4b00b9fc55f2e24fe4e22025-08-20T03:52:28ZengElsevierCase Studies in Thermal Engineering2214-157X2025-06-017010615210.1016/j.csite.2025.106152Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysisUmar Farooq0Ali Alshamrani1M. Mahtab Alam2Khadija Rafique3Department of Mathematics, COMSATS University Islamabad, Pakistan; Corresponding author.Department of Mechanical Engineering, College of Engineering, Taif University, P.O. Box 11099, Taif, 21944, Saudi ArabiaDepartment of Basic Medical Sciences, College of Applied Medical Science, King Khalid University, Abha, Saudi ArabiaDepartment of Mathematics and Statistics, Hazara University, Mansehra, PakistanThis study presents a mathematical model of tissue adhesive based on stretched surfaces with emphasis on flow and thermal characteristics using artificial neural networks with a Levenberg-Marquardt backpropagation scheme (ANN-LMBS). The model investigates Eyring-Powell nanofluids (EP-NF) with ferric oxide (Fe2O3) and silicon dioxide (SiO2) nanoparticles dispersed in water (H2O), focusing on magnetic strength, Darcy drag, viscous dissipation, joule heating and thermal radiation effects. Validation consists of 70 % training, 15 % testing, and 15 % validation. This dataset covers four scenarios and nine EP-NF cases. The resulting domain is divided into 300 grid points for velocity and temperature profiles. The ANN-LMBS model demonstrated excellent robustness in terms of accuracy, precision, and convergence, as verified by error histograms and regression optimization. The main findings include: as M increases from 1 to 4, the Nusselt number decreases by 2.48 %–2.16 % for Fe2O3 and by 1.71 %–1.54 % for SiO2; as Rd increases from 0.3 to 1.2, the Nusselt number increases by −10.17 % to −6.52 % for Fe2O3 and by −10.19 % to −6.58 % for SiO2; The influence of porosity (ϵ) and Eckert number (Ec) is less pronounced but still noticeable (∼3 % and 1.2 %, respectively). The governing equations, solved numerically via non-similarity transformation and the BVP4C algorithm, align with boundary conditions across all scenarios, with uncertainty analysis confirming solution robustness. Cross-thermal streamline patterns further enhance insights into flow dynamics, underscoring the model's potential in biomedical applications.http://www.sciencedirect.com/science/article/pii/S2214157X25004125Cross-thermal streamlineEyring-powell nanofluidANNMATLABNon-similar analysis
spellingShingle Umar Farooq
Ali Alshamrani
M. Mahtab Alam
Khadija Rafique
Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
Case Studies in Thermal Engineering
Cross-thermal streamline
Eyring-powell nanofluid
ANN
MATLAB
Non-similar analysis
title Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
title_full Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
title_fullStr Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
title_full_unstemmed Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
title_short Cross-thermal streamline patterns and heat transfer in EP-nanofluids: a neural network approach with uncertainty analysis
title_sort cross thermal streamline patterns and heat transfer in ep nanofluids a neural network approach with uncertainty analysis
topic Cross-thermal streamline
Eyring-powell nanofluid
ANN
MATLAB
Non-similar analysis
url http://www.sciencedirect.com/science/article/pii/S2214157X25004125
work_keys_str_mv AT umarfarooq crossthermalstreamlinepatternsandheattransferinepnanofluidsaneuralnetworkapproachwithuncertaintyanalysis
AT alialshamrani crossthermalstreamlinepatternsandheattransferinepnanofluidsaneuralnetworkapproachwithuncertaintyanalysis
AT mmahtabalam crossthermalstreamlinepatternsandheattransferinepnanofluidsaneuralnetworkapproachwithuncertaintyanalysis
AT khadijarafique crossthermalstreamlinepatternsandheattransferinepnanofluidsaneuralnetworkapproachwithuncertaintyanalysis