Experimental Measurement and Machine Learning Modelling for the Density of Hybrid Nanofluids
Bibliographic record
Abstract
Accurate prediction of nanofluid density is crucial for enhancing heat transfer efficiency in energy systems, such as solar thermal and geo-thermal systems.However, existing nanofluid models often fail to capture the interactions of hybrid nanoparticles in hybrid base fluid.This study experimentally investigates the density behavior of single, bi-hybrid, and ternary-hybrid nanofluids and applies machine learning models to improve predictive accuracy.The nanofluids composed of Al₂O₃, Fe₃O₄, and MWCNT nanoparticles synthesized in deionized water (DIW), ethylene glycol (EG), and DIW-EG mixtures.Density measurements were conducted at temperature (10°C < T < 50°C) and nanoparticle volume fractions (0 vol% < ϕ < 6.0 vol%) using a simple glass pycnometer.Linear Regression was employed for density prediction, while Random Forest, Support Vector Machine (SVM), and Gradient Boosting were selected for classification due to their robustness to non-linear relationships and high interpretability.These models were assessed using accuracy and F1-score, with Gradient Boosting and Random Forest achieving the best performance (>94% accuracy).Results showed that single nanofluids (Al₂O₃-based) exhibited density variations influenced by temperature and volume fraction.Bi-hybrid nanofluids (Al₂O₃-MWCNT) had higher densities due to MWCNT reinforcement.Ternary-hybrid nanofluids (Al₂O₃-MWCNT-Fe₃O₄) displayed the highest densities, particularly in EG-based mixtures, attributed to high density Fe₃O₄ nanoparticle and that of EG.Feature importance analysis confirmed volume fraction and base fluid composition as dominant factors influencing the density of the nanofluids.By integrating experimental data into machine learning algorithms, this study improves nanofluid density prediction, offering insights for optimizing thermal management in energy and industrial systems.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".