COMPUTER VISION INFERENCING FOR NON-DESTRUCTIVE TESTING

    公开(公告)号:US20220335254A1

    公开(公告)日:2022-10-20

    申请号:US17233404

    申请日:2021-04-16

    Abstract: An inspection system is provided and includes a camera and controller. The controller can include one or more processors in communication with the camera and receive a plurality of images of a target captured by the camera. The controller can also determine, using a first computer vision algorithm, a first prediction and corresponding confidence level for substantially all of the images. The controller can select a subset of the images having the first prediction confidence level greater than or equal to a first prediction threshold value. The controller can additionally determine, using a second computer vision algorithm, a second prediction and corresponding second prediction confidence level for each of the selected images. The at least one second prediction can require more time to determine than the at least one first prediction. The controller can output the second prediction and the second prediction confidence level for each of the selected images.

    Erosion detection and prediction
    2.
    发明授权

    公开(公告)号:US12152998B2

    公开(公告)日:2024-11-26

    申请号:US17716565

    申请日:2022-04-08

    Abstract: An inspection system is provided and includes a camera and controller. The camera can acquire at least one image of a target including opposed first and second surfaces. The controller can be in communication with the camera and receive the at least one image. The controller can also detect, using at least one computer vision algorithm, a geometry of the target including the first target surface and the second target surface of the target within at least one image. The at least one image can be acquired at a respective time under respective operating conditions. The controller can additionally segment erosion within the at least one image using the at least one computer vision algorithm. The controller can also generate an erosion depth profile for the at least one image. The erosion depth profile can characterize a depth of erosion of the target between the first and second surfaces.

    Computer vision inferencing for non-destructive testing

    公开(公告)号:US12153653B2

    公开(公告)日:2024-11-26

    申请号:US17233404

    申请日:2021-04-16

    Abstract: An inspection system is provided and includes a camera and controller. The controller can include one or more processors in communication with the camera and receive a plurality of images of a target captured by the camera. The controller can also determine, using a first computer vision algorithm, a first prediction and corresponding confidence level for substantially all of the images. The controller can select a subset of the images having the first prediction confidence level greater than or equal to a first prediction threshold value. The controller can additionally determine, using a second computer vision algorithm, a second prediction and corresponding second prediction confidence level for each of the selected images. The at least one second prediction can require more time to determine than the at least one first prediction. The controller can output the second prediction and the second prediction confidence level for each of the selected images.

    CONFIGURABLE NON-DESTRUCTIVE TESTING DEVICE
    5.
    发明公开

    公开(公告)号:US20240094878A1

    公开(公告)日:2024-03-21

    申请号:US18456895

    申请日:2023-08-28

    Abstract: A method includes receiving, by a data processor of a non-destructive testing (NDT) device, data characterizing an inspection point identifying an asset to be inspected using the NDT device. The method also includes determining, by the data processor, an inspection procedure associated with the asset based on the inspection point included in the received data. In addition, the method includes determining, by the data processor, a user interface configuration of the NDT device, the user interface configuration including a graphical interface configuration provided via a graphical user interface displayed on a display of the NDT device and a manual interface configuration corresponding to an actuated interface device of the NDT device. The method further includes configuring, by the data processor, the NDT device to perform the inspection procedure by applying the determined user interface configuration.

    AUTOMATED BORESCOPE DATA SYNCHRONIZATION
    6.
    发明公开

    公开(公告)号:US20240039991A1

    公开(公告)日:2024-02-01

    申请号:US18359749

    申请日:2023-07-26

    CPC classification number: H04L67/1095 G01N21/88 H04L67/12

    Abstract: A first set of data is received by a non-destructive testing device (NDT device) from a remote system. A second set of data is received by the NDT device from a sensor on the NDT device. In response to receiving the second set of data, the first set of data and the second set of data are synchronized to create a synchronized set of data by comparing the first set of data and the second set of data, identifying differences between the first set of data and the second set of data, and providing a set of data that include elements of both the first set of data and the second set of data. Synchronizing occurs automatically during an inspection. The synchronizing occurs between the NDT device and the remote system such that the synchronized set of data is present on both the NDT device and the remote system.

    Computer vision predictions for non-destructive testing

    公开(公告)号:US11790508B2

    公开(公告)日:2023-10-17

    申请号:US17236465

    申请日:2021-04-21

    Abstract: Systems and methods for target inspection are provided. The system includes a camera, at least one sensor, and a controller. The camera acquires images of a target over time and the sensor(s) acquire motion data characterizing camera and target movement. The controller generates, using a first computer vision (CV) algorithm, an initial prediction and confidence level regarding an object of interest for a first image acquired at a first time. The controller also determines, using the motion data, a motion parameter characterizing relative motion between the camera and the target at the first time. The controller additionally receives a weighting based upon a second image acquired at a second time prior to the first time. The controller generates, using a second CV algorithm, a final prediction and confidence level for the first image based upon the first image, the initial prediction and confidence level, the motion parameter, and the weighting.

    COMPUTER VISION PREDICTIONS FOR NON-DESTRUCTIVE TESTING

    公开(公告)号:US20220343486A1

    公开(公告)日:2022-10-27

    申请号:US17236465

    申请日:2021-04-21

    Abstract: Systems and methods for target inspection are provided. The system includes a camera, at least one sensor, and a controller. The camera acquires images of a target over time and the sensor(s) acquire motion data characterizing camera and target movement. The controller generates, using a first computer vision (CV) algorithm, an initial prediction and confidence level regarding an object of interest for a first image acquired at a first time. The controller also determines, using the motion data, a motion parameter characterizing relative motion between the camera and the target at the first time. The controller additionally receives a weighting based upon a second image acquired at a second time prior to the first time. The controller generates, using a second CV algorithm, a final prediction and confidence level for the first image based upon the first image, the initial prediction and confidence level, the motion parameter, and the weighting.

    EROSION DETECTION AND PREDICTION
    9.
    发明申请

    公开(公告)号:US20220341854A1

    公开(公告)日:2022-10-27

    申请号:US17716565

    申请日:2022-04-08

    Abstract: An inspection system is provided and includes a camera and controller. The camera can acquire at least one image of a target including opposed first and second surfaces. The controller can be in communication with the camera and receive the at least one image. The controller can also detect, using at least one computer vision algorithm, a geometry of the target including the first target surface and the second target surface of the target within at least one image. The at least one image can be acquired at a respective time under respective operating conditions. The controller can additionally segment erosion within the at least one image using the at least one computer vision algorithm. The controller can also generate an erosion depth profile for the at least one image. The erosion depth profile can characterize a depth of erosion of the target between the first and second surfaces.

Patent Agency Ranking