Application of artificial neural networks for prediction modeling and analysis of the thermophysical properties of Fe₃O₄/water ferrofluid using experimental measurement
Scientific Reports, Published online: 23 August 2026; doi:10.1038/s41598-026-66623-w Application of artificial neural networks for prediction modeling and analysis of the thermophysical properties of Fe₃O₄/water ferrofluid using experimental measurement
The research focuses on the application of artificial neural networks to predict the thermophysical properties of Fe₃O₄/water ferrofluid, specifically thermal conductivity and dynamic viscosity. Nanofluids, such as ferrofluid containing Fe3O4 nanoparticles, exhibit improved thermal performance due to their unique properties like magnetic characteristics and environmental friendliness.
The study investigates the effect of volume fraction (0.05% to 4.0%) and temperature (24 °C to 50 °C) on these properties. As the volume fraction increases from 0.05% to 4.0%, the dynamic viscosity increases from 0 cP to 0.77 cP. Meanwhile, the thermal conductivity shows a positive correlation with increasing nanoparticle concentration, while it decreases with increasing temperature.
The ANN models demonstrate a strong performance in estimating the thermal conductivity, with high correlation coefficients of 0.98 and minimal errors of 1.56 × 10−5.
Written by urgent.news from Scientific Reports's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
