Invention Grant
- Patent Title: Method for predicting cased wellbore characteristics using machine learning
-
Application No.: US17409420Application Date: 2021-08-23
-
Publication No.: US11892591B2Publication Date: 2024-02-06
- Inventor: Payel Ghosh , Melissa Spannuth
- Applicant: Visuray Intech Ltd (BVI)
- Applicant Address: VG Tortola
- Assignee: Visuray Intech Ltd (BVI)
- Current Assignee: Visuray Intech Ltd (BVI)
- Current Assignee Address: VG Road Town
- Agency: Adams and Reese LLP
- Agent Ray R. Ferrera
- Main IPC: G01V5/12
- IPC: G01V5/12 ; E21B47/085 ; G01V1/50 ; G01V5/00 ; G06N20/00

Abstract:
A method for well integrity assessment using machine-trained prediction of physical characteristics related to well integrity across a depth interval of a cased wellbore having one or more casing strings. The method includes collecting scattered X-ray signals from a plurality of X-ray detectors arranged within a well logging tool, learning trained weights to predict wellbore characteristics from the scattered X-ray signals, collecting further scattered X-ray signals from the X-ray detectors, using the trained weights to quantitatively predict the wellbore characteristics from the further X-ray signals, and using the predicted wellbore characteristics to assess well integrity.
Information query