Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.01268 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917117511598080 |
|---|---|
| author | Sohn, Jongwon Moon, Juhyeon Jung, Hyunjoon Nam, Jaewook |
| author_facet | Sohn, Jongwon Moon, Juhyeon Jung, Hyunjoon Nam, Jaewook |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01268 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ViscNet: Vision-Based In-line Viscometry for Fluid Mixing Process Sohn, Jongwon Moon, Juhyeon Jung, Hyunjoon Nam, Jaewook Computer Vision and Pattern Recognition 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. |
| title | ViscNet: Vision-Based In-line Viscometry for Fluid Mixing Process |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.01268 |