Machine learning model for identifying surfaces in a tubular
US11983860B2 · kind B2 · utility
0Cited by
1References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 2, 2021 |
| Grant date | May 14, 2024 |
| Priority date | — |
| Expiry date | Dec 21, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and instruction memory for processing acoustic images of a tubular to determine the surface of the tubular. The images may be acquired by an acoustic logging tool deployed into a pipe or well. A Machine Learning model is trained to recognize regions of the acoustic images that are internal to the tubular or not, in order to determine surface pixels. The surface pixels may be rendered to create visualizations of the tubular where noise and non-surface features are filtered out automatically.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.