Tailor-layered tube with thickness deviations and method of manufacturing the same

    公开(公告)号:US10801647B2

    公开(公告)日:2020-10-13

    申请号:US16243324

    申请日:2019-01-09

    Abstract: A tailor-layered tube, includes an inner tube, an outer tube having a greater diameter than the inner tube and disposed outside the inner tube, and at least one intermediate tube disposed between the inner tube and the outer tube and having a length different from the inner tube and the outer tube to be locally disposed between the inner tube and the outer tube. The inner tube, the intermediate tube, and the outer tube are hydroformed in a state of being laminated so that the inner tube, the intermediate tube, and the outer tube are sequentially brought into close contact with each other in a region where the intermediate tube is disposed and the inner tube is brought into direct contact with the outer tube in a region where the intermediate tube does not exist, and accordingly regions having locally different thicknesses are successively arranged.

    Forging method
    25.
    发明授权

    公开(公告)号:US10676802B2

    公开(公告)日:2020-06-09

    申请号:US16228383

    申请日:2018-12-20

    Inventor: Kwang Ryel Ryu

    Abstract: A forging method is provided. The forging comprises determining plans of second and third processes for each of a plurality of ingots, categorizing the plurality of ingots into first and second ingot sets, based on the plans of the second and third processes, evaluating the first and second ingot sets using a scoring function, determining an ingot set to be provided to a first heating furnace, based on the evaluating of the first and second ingot sets, and performing a first process, different from the second and third processes, on the ingot set provided to the first heating furnace.

    METHOD AND APPARATUS FOR AUTOMATICALLY SCHEDULING JOBS IN COMPUTER NUMERICAL CONTROL MACHINES USING MACHINE LEARNING APPROACHES

    公开(公告)号:US20190303196A1

    公开(公告)日:2019-10-03

    申请号:US16218195

    申请日:2018-12-12

    Abstract: Disclosed are a method and apparatus for automatically scheduling jobs in computer numerical control machines using machine learning. The method includes collecting a schedule job list from a database, generating a plurality of schedules for a schedule job to be processed with respect to the schedule job list, calculating an evaluation index for the plurality of generated schedules, determining whether the calculated evaluation index for the plurality of schedules has reached a target evaluation index, selecting a schedule corresponding to two evaluation indices when the calculated evaluation index does not reach the target evaluation index and generating two new schedules using a genetic algorithm, and setting a selection probability so that a schedule having the highest evaluation index is selected and returning the selection probability to a user when the calculated evaluation index reaches the target evaluation index.

Patent Agency Ranking