MACHINE LEARNING FOR AUTOMATIC CASING ANOMALY CLASSIFICATION FROM ELECTROMAGNETIC DATA

    公开(公告)号:US20240412044A1

    公开(公告)日:2024-12-12

    申请号:US18330507

    申请日:2023-06-07

    Abstract: Implementations provide a computer-implemented method that includes: accessing a first database holding results of interpreting casing integrity, wherein each result provides a first or a second label for a detected anomaly at a depth location of an inspection log that records electromagnetic (EM) survey data of an underground metal casing; accessing a second database holding inspection logs, each recording EM survey data of a corresponding underground metal casing; training a deep learning model configured to classify an input inspection log into the first or the second label; applying the deep learning model to one or more unclassified inspection logs of the second database, wherein the one or more unclassified inspection logs of the second database comprising anomalies; and subsequently classifying the one or more unclassified inspection logs of the second database into either the first label or the second label.

    Geomodel-Driven Dynamic Well Path Optimization

    公开(公告)号:US20210095557A1

    公开(公告)日:2021-04-01

    申请号:US17004692

    申请日:2020-08-27

    Abstract: Systems and methods of optimizing a new well path using a minimum curvature method are disclosed. An arc of the new well path may include a change in curvature at a point along the length of the arc. The arc of the new well path may be determined by iteratively: selecting a length of a first arc portion of the arc; determining a length of a second arc portion of the arc according to a minimum curvature method; combining the first arc portion and the second arc portion to form an arc; determining a deviation of the arc relative to a planned well trajectory; and selecting the arc with the lowest deviation from the planned well trajectory.

Patent Agency Ranking