公开(公告)号：US11835674B1

公开(公告)日：2023-12-05

申请号：US18053143

申请日：2022-11-07

Applicant: Schlumberger Technology Corporation

Inventor： Bo Fan ,  Maja Skataric ,  Sandip Bose ,  Shuchin Aeron ,  Smaine Zeroug

IPC: G01V1/50 ,  E21B47/005

CPC classification number: G01V1/50 ,  E21B47/005 ,  E21B2200/22 ,  G01V2210/324 ,  G01V2210/60

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

公开(公告)号：US11493659B2

公开(公告)日：2022-11-08

申请号：US16759667

申请日：2018-10-25

Applicant: SCHLUMBERGER TECHNOLOGY CORPORATION

Inventor： Bo Fan ,  Maja Skataric ,  Sandip Bose ,  Shuchin Aeron ,  Smaine Zeroug

IPC: G01V1/50 ,  G06N20/10 ,  E21B47/005 ,  G01V1/46 ,  G06N3/04 ,  G06N3/08

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

公开(公告)号：US20210181366A1

公开(公告)日：2021-06-17

申请号：US16759667

申请日：2018-10-25

Applicant: SCHLUMBERGER TECHNOLOGY CORPORATION

Inventor： Bo Fan ,  Maja Skataric ,  Sandip Bose ,  Shuchin Aeron ,  Smaine Zeroug

IPC: G01V1/50 ,  G01V1/46 ,  E21B47/005 ,  G06N3/08 ,  G06N3/04 ,  G06N20/10

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.