Real time data quality control and determination of formation angles from multicomponent induction measurements using neural networks
US7496451B2 · kind B2 · utility
4Cited by
13References
22Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 6, 2006 |
| Grant date | Feb 24, 2009 |
| Priority date | — |
| Expiry date | Aug 17, 2026 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG01V3/28
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
Neural networks may be used to determine and predict formation dip angles and perform quality assurance assessments from data collected with a multi-component induction tool used for well logging. The neural networks make use of corrected, rotated and normalized data to provide the predictions and assessments. Synthetic data using various models is used to train the neural networks. The teachings herein provide for real-time determinations with a substantial degree of accuracy in the results.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.