<p>Carbon nanotubes (CNTs) are utilized in drug delivery systems due to their minimal toxicity and unique characteristics. Moreover, investigations show the practicality of employing magnetic, CNTs in conjunction with gold nanoparticles for the thermal ablation of tumor cells via photon stimulation. However, the intricate interplay of ternary nanoparticles and base fluid presents challenges for researchers in the field to accurately simulate the characteristics of such flow patterns. We adopt the finite difference technique alongside a multi-layer artificial neural network (ANN) implementing the Levenberg–Marquardt algorithm (LMA) to investigate the transport of Casson-micro-polar ternary nano-fluid between two parallel plates, using blood as the base fluid. Our analysis focuses on the interactions and rotational behavior, particularly concerning red blood cells. The equations that describe blood flow are converted into nonlinear coupled ordinary differential equations through the process of similarity scaling. The ternary embedded nano-fluid demonstrates a significantly enhanced heat transfer rate when compared to both single and hybrid integrated nano-fluids. Higher <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$E_\text{c}$</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>E</mi> <mtext>c</mtext> </msub> </math></EquationSource> </InlineEquation> values signify a more significant transformation of kinetic energy into thermal energy, leading to an increase in the fluid temperature distribution. Enhancing the vortex viscosity variable boosts the angular velocity of the fluid particles. Scores of 1 indicate an outstanding alignment between the numerical data and the predictions. The quantitative comparison indicates that the ANN estimates the solution about nine times quicker than numerical method, while sustaining errors on the order of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$10^{-4}$</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>10</mn> <mrow> <mo>-</mo> <mn>4</mn> </mrow> </msup> </math></EquationSource> </InlineEquation>, hence illustrating a distinct practical benefit for applications necessitating frequent assessments. The current study examines the impact of nano-fluid composition on drug transport efficiency and flow characteristics within arterial systems and can be useful in biomedical engineering.</p>

Artificial neural network–enhanced simulation of bio-magnetic Casson micro-polar ternary nano-fluid flow for cardiovascular drug delivery: Keller-box approach

期刊论文
发表日期：

2026年8月1日

查看全文

Mohib Hussain,
Gunisetty Ramasekhar

摘要

Carbon nanotubes (CNTs) are utilized in drug delivery systems due to their minimal toxicity and unique characteristics. Moreover, investigations show the practicality of employing magnetic, CNTs in conjunction with gold nanoparticles for the thermal ablation of tumor cells via photon stimulation. However, the intricate interplay of ternary nanoparticles and base fluid presents challenges for researchers in the field to accurately simulate the characteristics of such flow patterns. We adopt the finite difference technique alongside a multi-layer artificial neural network (ANN) implementing the Levenberg–Marquardt algorithm (LMA) to investigate the transport of Casson-micro-polar ternary nano-fluid between two parallel plates, using blood as the base fluid. Our analysis focuses on the interactions and rotational behavior, particularly concerning red blood cells. The equations that describe blood flow are converted into nonlinear coupled ordinary differential equations through the process of similarity scaling. The ternary embedded nano-fluid demonstrates a significantly enhanced heat transfer rate when compared to both single and hybrid integrated nano-fluids. Higher $E_\text{c}$ $E_{c}$ values signify a more significant transformation of kinetic energy into thermal energy, leading to an increase in the fluid temperature distribution. Enhancing the vortex viscosity variable boosts the angular velocity of the fluid particles. Scores of 1 indicate an outstanding alignment between the numerical data and the predictions. The quantitative comparison indicates that the ANN estimates the solution about nine times quicker than numerical method, while sustaining errors on the order of $10^{-4}$ $10^{- 4}$ , hence illustrating a distinct practical benefit for applications necessitating frequent assessments. The current study examines the impact of nano-fluid composition on drug transport efficiency and flow characteristics within arterial systems and can be useful in biomedical engineering.