Related Experiment Video
Updated: Aug 5, 2026

A Computational Modeling Approach to Investigate the Influence of Hyperthermia on the Tumor Microenvironment
Published on: December 1, 2023
Artificial intelligence analysis of thermo-physical transport in modified Eyring-Powell nanofluids with bioconvective
Pan Zhang1, Zahoor Shah2, Sidra Akram2
1School of Intelligent Manufacturing, Sichuan University Jinjiang College, Meishan, Sichuan, 620860, China.
Abstract:
Thermal flow in advanced engineering and biomedical organizations depends on the complex correlation of heat, mass, and bioconvective transport in non-Newtonian nanofluids. This work examines the stochastic thermo-physical performance of a modified Eyring-Powell nanofluid flow under various parametric influences like thermal radiation, Brownian motion, thermophoresis, stratification, and bioconvective via a computational neural-network based model. The evaluation assumes incompressible laminar flow over a stretching surface and incorporates basis non-Newtonian effects. A deep learning-based technique utilizing Bayesian regularization artificial neural network (BR-ANN) is used to estimate the influential parameters of the model under various conditions. Reference datasets are created by using the Adams numerical method in Mathematica software, and a supervised AI model is used with 80% of the data used for training and while remaining 20% is held back for testing and validation purposes. Model performance is validated using mean square error (MSE), fitness curves, regression plots, and absolute error histograms. Parametric study shows that the temperature of the fluid decreases with an increase in the Prandtl number (Pr), while Brownian motion (Nb) and thermophoresis (Nt) parameters raise the temperature distribution. The thermophoretic parameter (Nt) has an inverse relationship with the concentration distribution, while increasing bioconvective stratification (S3) shows drops in microorganism motility. Moreover, higher values of the Eyring-Powell parameter (δ) are shown to increase the velocity of the nanofluid. The BR-ANN framework produced exceptional predictive accuracy, with the mean square error(MSE) values reaching low levels of 3.25E-13, confirming its remarkable reliability in modeling complex thermo-physical dynamics. The application of AI-based modeling is significant for the investigation of coupled heat, mass, and bioconvective transport mechanisms with the purpose of providing insights that are useful in thermal system optimization and engineering design.
Related Concept Videos
Mechanisms of Heat Transfer II
Mechanisms of Heat Transfer
Conduction, accounting for approximately 3% of body heat loss at rest, is the process of exchanging heat between molecules of two materials in direct contact. This can result in both heat loss and gain. For instance, when the body is submerged in water, which conducts heat 20 times more effectively than air, it can either lose or gain significant heat.
Mechanisms of Heat Transfer I
Joule-Thomson Effect
This experiment forces high-pressure gas through a throttle valve or a porous plug to a lower-pressure region. The gas expands as it passes through to...
Mechanism of heat transfer
Heat Flow and Specific Heat