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
- 沙優 橋本
- Mehak Jain (ORCID: https://orcid.org/0009-0008-8315-959X)
- Kazuhiro ITOH (ORCID: https://orcid.org/0000-0001-9301-2841)
- Masakazu Morimoto
Institutions
- University of Hyogo (JP)
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