ViscNet: Vision-Based In-line Viscometry for Fluid Mixing Process

TL;DR

VisNet introduces a vision-based, non-invasive in-line viscometer that estimates fluid viscosity by analyzing optical distortions caused by light refraction through a mixing process, enabling real-time monitoring under diverse conditions.

Contribution

This work presents a novel computer-vision approach for in-line viscosity measurement, incorporating uncertainty quantification and multi-pattern strategies to enhance robustness and practicality.

Findings

Achieves 0.113 mean absolute error in log viscosity units

Reaches up to 81% accuracy in viscosity-class prediction

Improves robustness with multi-pattern visual cues

Abstract

Viscosity measurement is essential for process monitoring and autonomous laboratory operation, yet conventional viscometers remain invasive and require controlled laboratory environments that differ substantially from real process conditions. We present a computer-vision-based viscometer that infers viscosity by exploiting how a fixed background pattern becomes optically distorted as light refracts through the mixing-driven, continuously deforming free surface. Under diverse lighting conditions, the system achieves a mean absolute error of 0.113 in log m2 s^-1 units for regression and reaches up to 81% accuracy in viscosity-class prediction. Although performance declines for classes with closely clustered viscosity values, a multi-pattern strategy improves robustness by providing enriched visual cues. To ensure sensor reliability, we incorporate uncertainty quantification, enabling viscosity predictions with confidence estimates. This stand-off viscometer offers a practical, automation-ready alternative to existing viscometry methods.