VISUAL INSPECTION TRAINING BOARD FOR ARTIFICIAL INTELLIGENCE DEEP LEARNING

    公开(公告)号:US20240242328A1

    公开(公告)日:2024-07-18

    申请号:US18155245

    申请日:2023-01-17

    IPC分类号: G06T7/00

    摘要: A computing system includes an automatic optical inspection (AOI) and a database that stores images of a plurality of visual inspection (VI) training boards. Each of the visual inspection (VI) training boards includes at least one intended defect. The AOI system includes an artificial intelligence (AI) algorithm implemented in an automatic optical inspection (AOI) system. The AOI system trains the AI algorithm to learn at least one target defect based on the at least one intended defect including in the plurality of VI training boards, analyzes a production printed circuit board (PCB), and determines either a non-defective PCB in response to the AI algorithm determining the production PCB excludes the at least one target defect, or a defective PCB in response to the AI algorithm determining the production PCB includes at least one target defect.

    CLEAVING FIBERS OF DIFFERING COMPOSITION
    4.
    发明申请

    公开(公告)号:US20200026004A1

    公开(公告)日:2020-01-23

    申请号:US16038755

    申请日:2018-07-18

    摘要: A method for cleaving a fiber comprises rotating an actuator to apply a positioning force to a blade in a scoring assembly. The positioning force produces a score in the surface of a fiber, and the method further comprise applying a cleaving force to the fiber to cleave the fiber. The method can further include measuring the magnitude of the positioning force and rotating the actuator until the magnitude corresponds to a pre-determined magnitude. A cleaver comprises a scoring assembly, drive assembly, and a cleaving assembly. The scoring assembly includes a holder having one or more blades, and an actuator. The cleaving assembly secures a fiber in the scoring assembly. The drive assembly rotates the actuator to position one or more blades to score the surface of the fiber. The cleaving assembly applies a cleaving force to the fiber to cleave the fiber at the location of the score.

    Object cognitive identification solution

    公开(公告)号:US10679054B2

    公开(公告)日:2020-06-09

    申请号:US16120737

    申请日:2018-09-04

    摘要: Embodiments of the present invention provide a computer-implemented method for identifying a specified object. The method includes collecting attributes of a physical object within a physical space, in which the attributes include an object temperature obtained via an (IR) sensor and an object shape obtained via an image sensor. A machine learning algorithm is executed to allocate a coordinate to the object based on the attributes. In response to a request from a user to locate the object, the physical space is scanned via the IR sensor and the image sensor to identify the object and to detect a present location. An indication of a location of the object is then displayed to the user, in which the indication is at least one of the present location of the object or a predicted location of the object.

    Cleaving fibers of differing composition

    公开(公告)号:US10656335B2

    公开(公告)日:2020-05-19

    申请号:US16038755

    申请日:2018-07-18

    摘要: A method for cleaving a fiber comprises rotating an actuator to apply a positioning force to a blade in a scoring assembly. The positioning force produces a score in the surface of a fiber, and the method further comprise applying a cleaving force to the fiber to cleave the fiber. The method can further include measuring the magnitude of the positioning force and rotating the actuator until the magnitude corresponds to a pre-determined magnitude. A cleaver comprises a scoring assembly, drive assembly, and a cleaving assembly. The scoring assembly includes a holder having one or more blades, and an actuator. The cleaving assembly secures a fiber in the scoring assembly. The drive assembly rotates the actuator to position one or more blades to score the surface of the fiber. The cleaving assembly applies a cleaving force to the fiber to cleave the fiber at the location of the score.

    Flux residue detection
    7.
    发明授权

    公开(公告)号:US10939600B2

    公开(公告)日:2021-03-02

    申请号:US16202241

    申请日:2018-11-28

    摘要: A system for flux residue detection is provided. The system includes a flux heater, where the flux heater controls a temperature of a flux spray applied to a printed circuit board, and an infrared camera, wherein the infrared camera provides a thermal image of the flux on the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, and capturing an infrared image of the flux applied to the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, capturing an infrared image of the flux applied to the printed circuit board, and determining there is excess flux residue on the printed circuit board.

    FLUX RESIDUE DETECTION
    8.
    发明申请

    公开(公告)号:US20200170155A1

    公开(公告)日:2020-05-28

    申请号:US16202241

    申请日:2018-11-28

    摘要: A system for flux residue detection is provided. The system includes a flux heater, where the flux heater controls a temperature of a flux spray applied to a printed circuit board, and an infrared camera, wherein the infrared camera provides a thermal image of the flux on the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, and capturing an infrared image of the flux applied to the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, capturing an infrared image of the flux applied to the printed circuit board, and determining there is excess flux residue on the printed circuit board.

    OBJECT COGNITIVE IDENTIFICATION SOLUTION
    9.
    发明申请

    公开(公告)号:US20200074175A1

    公开(公告)日:2020-03-05

    申请号:US16120737

    申请日:2018-09-04

    摘要: Embodiments of the present invention provide a computer-implemented method for identifying a specified object. The method includes collecting attributes of a physical object within a physical space, in which the attributes include an object temperature obtained via an (IR) sensor and an object shape obtained via an image sensor. A machine learning algorithm is executed to allocate a coordinate to the object based on the attributes. In response to a request from a user to locate the object, the physical space is scanned via the IR sensor and the image sensor to identify the object and to detect a present location. An indication of a location of the object is then displayed to the user, in which the indication is at least one of the present location of the object or a predicted location of the object.