HAM-Guided Physics-Informed Neural Operator for Stratified Oldroyd-B and Maxwell Nanofluid Flow with Radiation and Gyrotactic Microorganisms
| International Journal of Mechanical Engineering |
| © 2026 by SSRG - IJME Journal |
| Volume 13 Issue 3 |
| Year of Publication : 2026 |
| Authors : D. Vidhya, P. Uma Devi |
10.14445/23488360/IJME-V13I3P105
How to Cite?
D. Vidhya, P. Uma Devi, "HAM-Guided Physics-Informed Neural Operator for Stratified Oldroyd-B and Maxwell Nanofluid Flow with Radiation and Gyrotactic Microorganisms," SSRG International Journal of Mechanical Engineering, vol. 13, no. 3, pp. 54-67, 2026. Crossref, https://doi.org/10.14445/23488360/IJME-V13I3P105
Abstract:
Stratified Oldroyd-B and Maxwell nanofluid flows over a stretching sheet with radiation and gyrotactic microorganisms are addressed in this work by creating a HAM-guided physics-informed neural operator, in accordance with the components and aims outlined in the cited study. A Homotopy Analysis Method (HAM) is used to transform the coupled PDE system into a nonlinear ODE boundary-value problem in the baseline formulation, which employs similarity reduction. Data-driven prediction and regression-based error analysis are provided by an Artificial Neural Network (ANN) trained with Levenberg-Marquardt. In order to enhance generalisability, to keep this physics but train an operator that maps (η, “parameters”)→(f ^’,θ,ϕ,χ) in both fluids, with the Maxwell case included by the documented switch De_2=0. The results display that, in a radiation+stratification scenario (C3), the suggested approach produces wall metrics f ^” (0)=1.245, -^’ (0)=0.612, -ϕ^’ (0)=0.428, and -χ^’ (0)=0.317, which are comparable to physics solvers and an improvement over an ANN baseline that is solely based on data. The prediction accuracy is high across all fields (R^2≥0.9983) and RMSE ≈0.003-0.005 across all C1–C8 observations. Sweeps are efficient because, following training (which takes about 18 minutes), inference takes about 3.2 milliseconds per case, which allows for quick sensitivity studies while maintaining the stratification trend that decreases mass and heat transfer.
Keywords:
Homotopy Analysis Method, Artificial Neural Network, Levenberg–Marquardt, Maxwell nanofluid flow, Gyrotactic microorganisms.
References:
[1] Shuguang Li et al., “Modelling and Analysis of Heat Transfer in MHD Stagnation Point Flow of Maxwell Nanofluid Over a Porous Rotating Disk,” Alexandria Engineering Journal, vol. 91, pp. 237-248, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Muhammad Imran et al., “A Proceeding to Numerical Study of Mathematical Model of Bioconvective Maxwell Nanofluid Flow Through a Porous Stretching Surface with Nield/Convective Boundary Constraints,” Scientific Reports, vol. 14, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Muhammad Abdul Basit et al., “Numerical Analysis of Mathematical Model for Heat and Mass Transfer Through Bioconvective Maxwell Nanofluid Flow Subject to Darcy-Forcheimer and Lorentz forces,” International Journal of Heat and Fluid Flow, vol. 106, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Kashif Ali Khan et al., “Exploring the Numerical Simulation of Maxwell Nanofluid Flow over a Stretching Sheet with the Influence of Chemical Reactions and Thermal Radiation,” Results in Physics, vol. 60, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Muhammad Shoaib Arif, Kamaleldin Abodayeh, and Yasir Nawaz, “Explicit Computational Analysis of Unsteady Maxwell Nanofluid Flow on Moving Plates with Stochastic Variations,” International Journal of Thermofluids, vol. 23, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Taghreed A. Assiri et al., “Artificial Neural Networks Strategy to Analyze the Magnetohydrodynamics Casson-Maxwell Nanofluid Flow through the Cone and Disc System Space,” International Journal of Heat and Fluid Flow, vol. 107, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Fariha Ahmed et al., “Numerical Modeling of a MHD Non-Linear Radiative Maxwell Nano Fluid with Activation Energy,” Heliyon, vol. 10, no. 2, pp. 1-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Muhammad Shoaib Kamran et al., “Significance of Cattaneo–Christov Heat Flux Theory and Convective Heat Transport on Maxwell Nanofluid Flow,” ZAMM‐Journal of Applied Mathematics and Mechanics, vol. 104, no. 10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Sami Ullah Khan et al., “Evaluation of Thermal Bioconvective Phenomenon for Periodically Accelerating Nonlinear Radiated Flow of Maxwell Nanofluid with Triple Diffusion Effects,” Alexandria Engineering Journal, vol. 93, pp. 22-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Fatimah S. Bayones, A.M. Abd-Alla, and Esraa N. Thabet, “Magnetized Dissipative Soret Effect on Nonlinear Radiative Maxwell Nanofluid Flow with Porosity, Chemical Reaction and Joule Heating,” Waves in Random and Complex Media, vol. 34, no. 6, pp. 6270-6288, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Nisha Chouhan et al., “Heat and Mass Transmission in Maxwell Nanofluid Flow over an Exponential Stretchable Surface with Swimming of Motile Gyrotactic Microorganisms,” International Journal of Thermofluids, vol. 30, pp. 1-12, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Shami A. M. Alsallami et al., “Numerical Simulation of Marangoni Maxwell Nanofluid Flow with Arrhenius Activation Energy and Entropy Anatomization over a Rotating Disk,” Waves in Random and Complex Media, vol. 35, no. 2, pp. 2645-2663, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] T. Salahuddin et al., “Effect of Varying the Temperature Dependent Viscosity of Maxwell Nanofluid Flow Near a Sensor Surface with Activation Enthalpy,” Chaos, Solitons & Fractals, vol. 194, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Danial Habib et al., “Significance of Bioconvection and Mass Transpiration for MHD Micropolar Maxwell Nanofluid Flow Over an Extending Sheet,” Waves in Random and Complex Media, vol. 35, no. 4, pp. 7568-7582, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Thirupathi Thumma et al., “Exploring MHD Radiative Maxwell Nanofluid Flow on an Expanding Surface for the Impact of Activation Energy Associated with Velocity Slip and Convective Boundary Conditions,” Journal of Thermal Analysis and Calorimetry, vol. 150, pp. 3661-3681, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Muhammad Idrees Afridi et al., “Artificial Neural Network Analysis of MHD Maxwell Nanofluid Flow Over a Porous Medium in Presence of Joule Heating and Nonlinear Radiation Effects,” Chaos, Solitons & Fractals, vol. 192, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Chawit Kaewnuratchadasorn, Jiaji Wang, and Chul-Woo Kim, “Physics‐Informed Neural Operator Solver and Super‐Resolution for Solid Mechanics,” Computer‐Aided Civil and Infrastructure Engineering, vol. 39, no. 22, pp. 3435-3451, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Zongyi Li et al., “Fourier Neural Operator for Parametric Partial Differential Equations,” arXiv preprint, pp. 1-16, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] George Em Karniadakis et al., “Physics-Informed Machine Learning,” Nature Reviews Physics, vol. 3, pp. 422-440, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Swathi Baswaraju, Arunadevi Thirumalraj, and B. Manjunatha, Unlocking the Potential of Deep Learning in Knee Bone Cancer Diagnosis using MSCSA-Net Segmentation and MLGC-LTNet Classification, 1st ed., Sustainable Development Using Private AI, CRC Press, pp. 190-213, 2024.
[Google Scholar] [Publisher Link]
[21] S. Stephe et al., “Transformer based Attention Guided Network for Segmentation and Hybrid Network for Classification of Liver Tumor from CT Scan Images,” Eastern Ukrainian Medical Journal, vol. 12, no. 3, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]