From experimental data to predictions: Artificial intelligence supported new mathematical approaches for estimating thermal conductivity, viscosity and zeta potential in Fe3O4-water magnetic nanofluids
Magnetic nanofluids (MNs) are considered advanced heat transfer fluids of the future due to their ability to function as intelligent fluids, with the applied external magnetic field effect being readily manageable. In this study, firstly, the stabilities of Fe3O4-water MNs prepared at 0.1, 0.25, 0.5...
Saved in:
Published in | Powder technology Vol. 430; p. 118974 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Magnetic nanofluids (MNs) are considered advanced heat transfer fluids of the future due to their ability to function as intelligent fluids, with the applied external magnetic field effect being readily manageable. In this study, firstly, the stabilities of Fe3O4-water MNs prepared at 0.1, 0.25, 0.5, 0.75 and 1 mass ratios were determined by zeta potential measurement. The thermal conductivity and viscosities of MNs with appropriate stability were measured at 20–60 °C for all mass ratios. Secondly, using experimental data, two different artificial neural network (ANN) models were developed: one for thermal conductivity and viscosity depending on the temperature (20–60 °C) and mass ratio values and one for zeta potential depending on pH and mass ratio. Finally, using the obtained ANN data, two new mathematical correlations are proposed to predict thermal conductivity and viscosity. The study's results revealed that the developed ANN model has MSE and R values of 4.51E-06 and 0.99968, respectively, for thermal conductivity and viscosity of Fe3O4-water MNs can be accurately predicted by novel mathematical correlations.
[Display omitted]
•Fe3O4-water nanofluid in 5 different concentrations in suitable stability.•Thermal properties and stability were experimentally measured.•Two high-performance ANN model was developed.•Two new correlations were proposed.•Thermal performance analysis (PER) was employed. |
---|---|
ISSN: | 0032-5910 1873-328X |
DOI: | 10.1016/j.powtec.2023.118974 |