MACHINE LEARNING APPARATUS, MACHINE LEARNING METHOD, AND INDUSTRIAL MACHINE

    公开(公告)号:US20210097440A1

    公开(公告)日:2021-04-01

    申请号:US17027480

    申请日:2020-09-21

    申请人: FANUC CORPORATION

    IPC分类号: G06N20/00

    摘要: A machine learning apparatus determines a control parameter of an active vibration isolation apparatus on which an industrial machine is mounted. The industrial machine includes a movable part, a drive source that drives the movable part, and a drive source control section that controls the drive source to position the movable part at a command position. The machine learning apparatus includes: an acquiring section that acquires, as teacher data, a positional deviation, which is a difference between the command position and an actual position of the movable part; a storage section that stores a learning model that outputs the control parameter corresponding to a state quantity concerning the industrial machine; and a learning section that updates the learning model using the teacher data.

    PARAMETER SETTING METHOD AND CONTROL APPARATUS

    公开(公告)号:US20210062890A1

    公开(公告)日:2021-03-04

    申请号:US17008989

    申请日:2020-09-01

    申请人: FANUC CORPORATION

    摘要: A parameter setting method includes a parameter value changing step of, when the magnitude of a deviation that is a difference between a command position and an actual position of a movable portion is greater than or equal to a prescribed value during operation of an active damper, selecting an unselected set of candidate values from among a plurality of sets of candidate values and changing the values of respective types of parameters of the active damper to the selected set of candidate values, and when the magnitude of the deviation is less than the prescribed value, not changing the values of the respective types of the parameters. After the parameter value changing step is finished, the parameter value changing step is repeated until the magnitude of the deviation becomes less than the prescribed value.