A Review of Artificial Intelligence Methods in Predicting Thermophysical Properties of Nanofluids for Heat Transfer Applications

Energies, Journal Year: 2024, Volume and Issue: 17(6), P. 1351 - 1351

Published: March 12, 2024

This present review explores the application of artificial intelligence (AI) methods in analysing prediction thermophysical properties nanofluids. Nanofluids, colloidal solutions comprising nanoparticles dispersed various base fluids, have received significant attention for their enhanced thermal and broad industries ranging from electronics cooling to renewable energy systems. In particular, nanofluids’ complexity non-linear behaviour necessitate advanced predictive models heat transfer applications. The AI techniques, which include genetic algorithms (GAs) machine learning (ML) methods, emerged as powerful tools address these challenges offer novel alternatives traditional mathematical physical models. Artificial Neural Networks (ANNs) other are highlighted capacity process large datasets identify intricate patterns, thereby proving effective predicting nanofluid (e.g., conductivity specific capacity). paper presents a comprehensive overview published studies devoted nanofluids, where (like ANNs, support vector regression (SVR), algorithms) employed enhance accuracy predictions properties. reviewed works conclusively demonstrate superiority over classical approaches, emphasizing role advancing research nanofluids used

Language: Английский

---

Exploring novel heat transfer correlations: Machine learning insights for molten salt heat exchangers

Numerical Heat Transfer Part A Applications, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 18

Published: Feb. 27, 2024

The utilization of molten salts in heat transfer applications, specifically within shell-and-tube exchangers, has garnered significant attention for its potential sustainable energy solutions. this study employs advanced machine learning algorithms, including decision tree regressor, support vector extreme gradient boosting, and random forest, to not only predict the behavior but also unravel complex mechanisms underlying process. Achieving a remarkable accuracy score 0.985, Support Vector Regressor leads predictive models, closely followed by forest (0.982), Decision Tree (0.974), Extreme Gradient Boosting (0.965). incorporation Shapley Additive exPlanations values accentuates Reynolds number's pivotal role, elucidating robust correlation with Nusselt value. These insights transcend mere prediction, offering profound understanding that can significantly impact design optimization salt exchangers. applications extend across various sectors, concentrated solar thermal storage, solidifying their position as versatile effective solution pursuit efficient systems.

Language: Английский

---

Optimizing building energy performance predictions: A comparative study of artificial intelligence models

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 88, P. 109247 - 109247

Published: April 4, 2024

Language: Английский

---

Estimating the density of hybrid nanofluids for thermal energy application: Application of non-parametric and evolutionary polynomial regression data-intelligent techniques

Measurement, Journal Year: 2021, Volume and Issue: 189, P. 110524 - 110524

Published: Nov. 30, 2021

Language: Английский

---

Experimental study on the thermal properties of Al ₂ O ₃ ‐CuO /water hybrid nanofluids: Development of an artificial intelligence model

International Journal of Energy Research, Journal Year: 2022, Volume and Issue: 46(15), P. 21066 - 21083

Published: Nov. 6, 2022

In this work, Al2O3 and CuO nanoparticles were synthesized by a novel sol-gel method. Then, water-based Al2O3-CuO (50:50) nanofluids produced the two-step The viscosity thermal conductivity of determined for concentration temperature range 0-1.0 vol.% 30-60°C, respectively. Sodium dodecylbenzene sulfonate surfactant was used to enhance nanofluid stability. Field emission scanning electron microscopy, transmission x-ray diffraction techniques morphological characterization nanoparticles. pH zeta potential determine stability nanofluid. outcomes show that maximum augmentation in hybrid is 14.6 6.5% higher than 1.0 at 60 30°C, enhancement 14.9 21.4% noticed 30°C 1 vol. % relative base liquid. equations proposed estimate based on experimental results with R2 values 0.99 0.98, A cascaded forward neural network model developed predict properties using datasets. performance ratio indicated its solar energy applications.

Language: Английский

---