-
公开(公告)号：US20240055208A1
公开(公告)日：2024-02-15
申请号：US18229185
申请日：2023-08-02
Applicant: Keyence Corporation
Inventor： Kenji KOJIMA , Satoru TOMOSHI , Hiroshi KASHIMA , Choryon OH , Manabu TSUBOYAMA
Abstract: A worker is prevented from being hindered. A safety switch includes a switch body including an electromagnet and an actuator attracted to the electromagnet. The switch body includes a drive control unit and a safety control unit which control the safety switch, and the drive control unit and the safety control unit are surrounded by a housing. The housing is arranged on a back surface side of the electromagnet of the switch body, and the housing forms an accommodating portion that accommodates the drive control unit and the safety control unit.
-
公开(公告)号：US20240054252A1
公开(公告)日：2024-02-15
申请号：US18222490
申请日：2023-07-17
Applicant: Keyence Corporation
Inventor： Kazusa AOKI , Masaki FUJIWARA , Jun TABUCHI
IPC: G06F30/10
CPC classification number: G06F30/10
Abstract: CAD data, which can be directly used for a design drawing, can be easily created from geometric element following mesh data. Provided is a reverse engineering support apparatus that converts mesh data obtained by measuring a three-dimensional shape of a workpiece into CAD data and outputs the CAD data. The reverse engineering support apparatus includes: a data acquisition unit that acquires mesh data; an extraction unit that extracts geometric element data from the mesh data; a rounding unit that executes rounding on a characteristic value of the geometric element data extracted by the extraction unit; a conversion unit that converts the geometric element data subjected to the rounding into CAD data; and an output unit that outputs the CAD data.
-
公开(公告)号：US11854163B2
公开(公告)日：2023-12-26
申请号：US17542537
申请日：2021-12-06
Applicant: Keyence Corporation
Inventor： Ikuo Yamada
CPC classification number: G06T5/002 , G06K7/10722 , G06K7/1417 , G06V10/22 , G06T2207/20084
Abstract: To improve reading accuracy by enabling a read image to be restored by machine learning while reducing a calculation load in an optical information reading device. An optical information reading device includes: a storage part that stores a structure and a parameter of a neural network generated in advance by machine learning of a plurality of defective images and a plurality of ideal images; a processor that attempts restoration by inputting a read image to the neural network configured using the structure and parameter stored in the storage part and executes decoding processing on the restored read image; and a housing that accommodates a camera, the storage part, and the processor.
-
公开(公告)号：US20230368362A1
公开(公告)日：2023-11-16
申请号：US18122751
申请日：2023-03-17
Applicant: Keyence Corporation
Inventor： Takashi NARUSE
CPC classification number: G06T7/0006 , G06T7/74 , G06T7/13 , G06T7/60 , G06T2207/30164 , G06T2200/24
Abstract: A first contact target position, a second contact target position, and a characteristic pattern for specifying a position and a posture of the workpiece are set in association with each other. First and second contact target positions for measurement are specified from a workpiece image newly generated during the execution of measurement such that a driving section is controlled to bring the touch probe into contact with the side surface of the workpiece with the specified first contact target position for measurement as a reference, and the driving section is controlled to bring the touch probe into contact with the upper surface of the workpiece with the specified second contact target position for measurement as a reference. Three-dimensional coordinates of a contact point are measured based on a contact signal output when the touch probe comes into contact with the workpiece.
-
公开(公告)号：US11781856B2
公开(公告)日：2023-10-10
申请号：US17241267
申请日：2021-04-27
Applicant: Keyence Corporation
Inventor： Tatsuro Wakai , Atsushi Matsutani
Abstract: Convenience is improved by enabling an imaging section to capture an image of a measurement element without adjustment of a rotation angle of a measurement object performed by a user. A control unit identifies a reference rotation angle during measurement, and calculates a measurement angle to measure a measurement element based on a relative rotation angle with respect to the reference rotation angle stored in advance. The control unit controls a rotation unit such that a rotation angle of the rotation unit becomes the measurement angle. The control unit executes a process of measuring a dimension of the measurement element based on a measurement object image captured by an imaging section when the rotation angle of the rotation unit becomes the measurement angle.
-
Patent Agency Ranking
公开(公告)号：US20230280267A1
公开(公告)日：2023-09-07
申请号：US18144875
申请日：2023-05-09
Applicant: Keyence Corporation
Inventor： Ryosuke IMAI , Kenichiro HIROSE
CPC classification number: G01N21/255 , G02B19/0019 , G02B5/10 , G01N21/31
Abstract: An analysis and observation device includes: an electromagnetic wave emitter that emits a primary electromagnetic wave; a reflective object lens having a primary mirror provided with a primary reflection surface reflecting a secondary electromagnetic wave and a secondary mirror provided with a secondary reflection surface receiving and further reflecting the secondary electromagnetic wave; first and second detectors that receive the secondary electromagnetic wave and generate an intensity distribution spectrum; and a controller that performs component analysis of a sample based on the intensity distribution spectrum. A transmissive region through which the primary electromagnetic wave is transmitted is provided at a center of the secondary mirror. The transmissive region transmits the primary electromagnetic wave, which has been emitted from the electromagnetic wave emitter and passed through an opening of the primary mirror, thereby emitting the primary electromagnetic wave along an analysis optical axis of the reflective object lens.
-
27.发明公开公开(公告)号：US20230229879A1
公开(公告)日：2023-07-20
申请号：US18126501
申请日：2023-03-27
Applicant: Keyence Corporation
Inventor： Hidezumi NAGATA , Taichi TAJIKA , Takashi HIRANO
CPC classification number: G06K7/1417 , G06K7/1413 , G06K7/10722 , G06K7/10831
Abstract: Recommended installation position and posture of a stationary code reader can be proposed to a user to facilitate installation work of the code reader by the user. An installation support device for the stationary code reader acquires camera information including a camera parameter of the code reader, code information to be read, and environment information including a conveying speed of a line, determines required field of view and depth of the code reader required to read a code under an environment specified by the environment information, and determines an installation pattern which is recommended installation position and posture of the code reader that can satisfy the required field of view and depth based on the camera information and the code information.
-
公开(公告)号：US20230162344A1
公开(公告)日：2023-05-25
申请号：US17958474
申请日：2022-10-03
Applicant: Keyence Corporation
Inventor： Xinliang ZHAO
CPC classification number: G06T7/0008 , G06T5/002 , G06V10/751 , G06T2207/10024 , G06T2207/20081 , G06T2207/20182
Abstract: When a machine learning network trained with both a non-defective product image and a defective product image is used, it is possible to stably exhibit high detection capability for the defective product image having an unknown defect while shortening a takt time during the operation time. A processor executes a first learning process of causing a machine learning network to learn a non-defective product image added with a noise, and a second learning process of causing the machine learning network to learn a defective product image, and detects both an unknown defect having a characteristic different from a characteristic of the non-defective product image and a known defect having a characteristic designated as a defective site, by inputting a workpiece image to the machine learning network whose parameter has been adjusted by the first learning process and the second learning process.
-
公开(公告)号：US11590652B2
公开(公告)日：2023-02-28
申请号：US17094839
申请日：2020-11-11
Applicant: Keyence Corporation
Inventor： Kyosuke Tawara , Naoki Takayama
Abstract: A user can easily create a robot program. A measuring device includes a position determination processing part that determines a holding position, held by a robot hand, of a workpiece placed in a work space and determines coordinates of a fixed via point having any single attribute based on a result of measurement made by a measuring part and holding information, the fixed via point being one of an approach position of the robot hand for holding the holding position, the holding position, and a retreat position after holding, and an output part that outputs, to a robot controller, the coordinates of the fixed via point determined by the position determination processing part and attribute information showing the attribute of the fixed via point.
-
公开(公告)号：US20220335588A1
公开(公告)日：2022-10-20
申请号：US17686474
申请日：2022-03-04
Applicant: Keyence Corporation
Inventor： Di HE
Abstract: An image inspection apparatus includes a learned neural network storage storing a neural network that previously learns weighting factors between input, intermediate and output layers, and an inferer determining failure/no-failure of a workpiece and classify the workpiece to classes based on an image of the workpiece. The inferer performs first and second inferences. In the first inference, the inferer determines failure/no-failure of the workpiece based on failure/no-failure feature quantities that are obtained by providing the workpiece image to the neural network and a failure/no-failure determination boundary. In the second inference, the inferer define a classification boundary to be used to classify an inspection workpiece to the classes in a feature quantity space of the neural network based on classification feature quantities that represent the different-type classification workpiece images, and classifies a workpiece to the classes based on classification feature quantities of an image of the workpiece and the classification boundary.
-
-
-
-
-
-
-
-
-
Search Results
650
records
(took 0.025 seconds)
