View in EDS

TensorFlow-based data-driven analysis of Johnson–Segalman nanofluid flow with microbial species in a slippery dissipative peristaltic microchannel.

Saved in:
Bibliographic Details
Title: TensorFlow-based data-driven analysis of Johnson–Segalman nanofluid flow with microbial species in a slippery dissipative peristaltic microchannel.
Authors: Liu, Xinwang1 (AUTHOR) liuxinwang@hrbeu.edu.cn, Ishaq, Muhammad2 (AUTHOR) rashidishaq938@gmail.com, Ashraf, Muhammad Bilal2 (AUTHOR) bilalashraf_qau@yahoo.com, Badawi, Maria Altaib3 (AUTHOR) m.badawi@mu.edu.sa, Thaljaoui, Adel3 (AUTHOR) adel.t@mu.edu.sa, Farooq, Umer1 (AUTHOR) umer_farooq@hrbeu.edu.cn
Source: International Journal of Numerical Methods for Heat & Fluid Flow. 2026, Vol. 36 Issue 8, p3373-3394. 22p.
Subjects: Artificial neural networks, Nanofluids, Heat radiation & absorption, Microchannel flow, Magnetic field effects, Energy dissipation, Biological fluid dynamics
Abstract: Purpose: The purpose of this study is to develop an intelligent artificial neural network-based framework for predicting the flow, heat, mass and bioconvection characteristics of Johnson–Segalman nanoliquid transport in a symmetric peristaltic channel. The model incorporates viscous dissipation, wavy boundaries, magnetic field effects, thermal radiation, thermophoresis, Brownian motion and chemical reaction. Numerical solutions obtained via lubrication theory are used to train the neural network, enabling accurate prediction of velocity, temperature, concentration and bioconvection profiles under varying physical parameters. Design/methodology/approach: The governing partial differential equations describing Johnson–Segalman nanoliquid flow in a symmetric peristaltic channel are reduced to a system of dimensionless ordinary differential equations using the lubrication approximation. These equations, incorporating viscous dissipation, magnetic field, thermal radiation, thermophoresis, Brownian motion, chemical reaction and bioconvection effects, are solved numerically using NDSolve in Mathematica. The resulting data sets are used to train an artificial neural network implemented in Python using TensorFlow, with optimized architecture and performance assessed through multiple statistical error metrics. Findings: The results demonstrate that the artificial neural network accurately predicts the velocity, temperature, concentration and bioconvection characteristics of Johnson–Segalman nanoliquid flow in a peristaltic channel. Excellent agreement is observed between numerical and predicted results, confirmed by low error metrics. The magnetic field strength and thermal radiation significantly enhance the thermal distribution, while the Weissenberg number and velocity slip parameter strongly influence the velocity field. The trained model effectively captures the complex nonlinear interactions among physical parameters, confirming the reliability of the proposed intelligent framework for analyzing peristaltic nanofluid transport phenomena. Originality/value: This study presents a novel integration of peristaltic Johnson–Segalman nanoliquid modeling with an intelligent artificial neural network framework. Unlike conventional numerical or semi-analytical approaches, the proposed methodology combines lubrication theory-based solutions with data-driven learning to efficiently predict flow, thermal, mass and bioconvection behaviors under complex physical effects. The incorporation of viscous dissipation, slip conditions, magnetic field, thermal radiation, thermophoresis, chemical reaction and microbial dynamics within a unified intelligent framework offers new insights and provides a computationally efficient tool for analyzing complex microfluidic transport systems. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Numerical Methods for Heat & Fluid Flow is the property of Emerald Publishing Limited and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Purpose: The purpose of this study is to develop an intelligent artificial neural network-based framework for predicting the flow, heat, mass and bioconvection characteristics of Johnson–Segalman nanoliquid transport in a symmetric peristaltic channel. The model incorporates viscous dissipation, wavy boundaries, magnetic field effects, thermal radiation, thermophoresis, Brownian motion and chemical reaction. Numerical solutions obtained via lubrication theory are used to train the neural network, enabling accurate prediction of velocity, temperature, concentration and bioconvection profiles under varying physical parameters. Design/methodology/approach: The governing partial differential equations describing Johnson–Segalman nanoliquid flow in a symmetric peristaltic channel are reduced to a system of dimensionless ordinary differential equations using the lubrication approximation. These equations, incorporating viscous dissipation, magnetic field, thermal radiation, thermophoresis, Brownian motion, chemical reaction and bioconvection effects, are solved numerically using NDSolve in Mathematica. The resulting data sets are used to train an artificial neural network implemented in Python using TensorFlow, with optimized architecture and performance assessed through multiple statistical error metrics. Findings: The results demonstrate that the artificial neural network accurately predicts the velocity, temperature, concentration and bioconvection characteristics of Johnson–Segalman nanoliquid flow in a peristaltic channel. Excellent agreement is observed between numerical and predicted results, confirmed by low error metrics. The magnetic field strength and thermal radiation significantly enhance the thermal distribution, while the Weissenberg number and velocity slip parameter strongly influence the velocity field. The trained model effectively captures the complex nonlinear interactions among physical parameters, confirming the reliability of the proposed intelligent framework for analyzing peristaltic nanofluid transport phenomena. Originality/value: This study presents a novel integration of peristaltic Johnson–Segalman nanoliquid modeling with an intelligent artificial neural network framework. Unlike conventional numerical or semi-analytical approaches, the proposed methodology combines lubrication theory-based solutions with data-driven learning to efficiently predict flow, thermal, mass and bioconvection behaviors under complex physical effects. The incorporation of viscous dissipation, slip conditions, magnetic field, thermal radiation, thermophoresis, chemical reaction and microbial dynamics within a unified intelligent framework offers new insights and provides a computationally efficient tool for analyzing complex microfluidic transport systems. [ABSTRACT FROM AUTHOR]
ISSN:09615539