Measurement of multiple rheological properties of oil–water emulsions using a rotating device and machine learning

Abstract Rapid and non-intrusive measurement of the rheological properties of non-Newtonian fluids is crucial for applications such as the development of autonomous experimental systems. Herein, we propose a technique that utilizes machine learning to sequentially predict surface tension, contact angle, and viscosity characteristics based on flow images. Flow images were obtained by rotating oil–water emulsion samples in a cuvette by 90°. The extracted interface positions were used as features to train a random forest algorithm. The 1 mL emulsion sample remained entirely unconsumed, and the measurement was completed in 6 s. We demonstrated that the surface tension and contact angles of eight emulsion samples could be predicted with a NRMSE = 27.7% or less using training data from only two samples.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-12
DOI
https://doi.org/10.21203/rs.3.rs-11423935/v1
Primary Topic
Rheology and Fluid Dynamics Studies
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Measurement of multiple rheological properties of oil–water emulsions using a rotating device and machine learning

沙優 橋本, Mehak Jain, Kazuhiro ITOH, Masakazu Morimoto
Research Square
Rheology and Fluid Dynamics Studies
preprint

Measurement of multiple rheological properties of oil–water emulsions using a rotating device and machine learning

沙優 橋本, Mehak Jain, Kazuhiro ITOH, Masakazu Morimoto
preprint en

Abstract

Abstract Rapid and non-intrusive measurement of the rheological properties of non-Newtonian fluids is crucial for applications such as the development of autonomous experimental systems. Herein, we propose a technique that utilizes machine learning to sequentially predict surface tension, contact angle, and viscosity characteristics based on flow images. Flow images were obtained by rotating oil–water emulsion samples in a cuvette by 90°. The extracted interface positions were used as features to train a random forest algorithm. The 1 mL emulsion sample remained entirely unconsumed, and the measurement was completed in 6 s. We demonstrated that the surface tension and contact angles of eight emulsion samples could be predicted with a NRMSE = 27.7% or less using training data from only two samples.

Research Square
University of Hyogo (JP)
Rheology and Fluid Dynamics Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon