Artificial neural network modeling of magnetic nanoparticle-enhanced Sisko blood nanofluid flow over an inclined stretching surface with non-uniform heating and thermophoretic effects
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In the evolving field of fluid power and thermal systems, artificial neural networks (ANNs) are increasingly recognized for their robust ability to address nonlinear, coupled, and high-dimensional fluid dynamics problems. This study presents a neural network-assisted investigation of magneto-hydrodynamic Sisko nanofluid flow modelled as a blood-based magnetic suspension over an inclined stretching surface influenced by non-uniform heat generation and thermophoretic effects. The governing partial differential equations derived from mass, momentum, and energy conservation laws with complex boundary conditions are reduced to nonlinear ordinary differential equations through similarity transformations. The resulting system is first solved using MATLAB’s bvp4c solver, and the generated data is then used to train, validate, and test an ANN framework based on the Levenberg Marquardt backpropagation algorithm (BPLMA). The ANN model exhibits high predictive accuracy, with relative absolute errors ranging from 10⁻³ to 10⁻⁷ compared to the reference solution. The thermo-fluidic behaviour of shear-thinning and shear-thickening regimes is analysed under different concentrations of magnetic nanoparticles such as iron oxide and cobalt ferrite. For a 10 percent volume fraction increase, enhancements in heat transfer and reductions in mass transfer are observed, reaching up to 10 percent and 18.9 percent for iron oxide and 9.8 percent and 12 percent for cobalt ferrite, respectively, depending on the fluid rheology. Visualizations of streamlines, temperature fields, and concentration contours reveal intricate flow structures and nanoparticle distributions, offering valuable physical insights. Statistical evaluations including regression analysis, error histograms, and model fitness further support the reliability of the ANN approach. This work introduces a powerful hybrid computational methodology that integrates numerical simulation with machine learning to analyse non-Newtonian nanofluid behaviour and contributes to advancements in biomedical engineering, heat exchanger design, smart cooling systems, and microfluidic devices in fluid power applications. This work presents a novel computational framework that combines traditional numerical simulation with artificial intelligence to analyse complex non-Newtonian nanofluid behaviour. Unlike traditional methods that are often computationally intensive, the ANN model offers fast, accurate predictions and strong generalization across varying conditions. The novelty of this hybrid approach lies in its ability to enhance traditional techniques with AI driven efficiency, making it well suited for applications in biomedical engineering, heat exchanger design, smart cooling systems, and microfluidic devices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it