会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 10. 发明公开
    • LEARNING DEVICE, LEARNING METHOD, AND PROGRAM THEREFOR
    • EP3767401A1
    • 2021-01-20
    • EP19768295.8
    • 2019-03-05
    • Omron Corporation
    • FUJII, TakashiUEYAMA, YukiABE, YasuakiSAKATANI, NobuyukiIMATAKE, Kazuhiko
    • G05B13/02G06N20/00
    • Provided is a technology for efficiently learning an appropriate compensation amount for generating a command value to be imparted to a control object in predictive control of a control system which performs processing and assembly of an object to be processed. This learning device provides a learned model to an adjuster which includes a learned model learned in such a manner that a predetermined adjustment amount with respect to a controller on the basis of parameters of an object to be processed, in a system equipped with a controller that outputs a command value obtained by compensating a target value on the basis of a compensation amount; and an object to be controlled, which is controlled so as to perform a predetermined process with respect to an object to be processed, the object to be controlled having command values input from the controller, and a control variable output as a response to said command value. The learning device comprises: a learning unit which generates candidate compensation amounts on the basis of operation data including a target value, command value and control variable, performs learning of the generated candidate compensation amounts and the parameters of the object to be processed as teacher data, and generates or updates the learned model; and a setting unit which provides, to the adjuster, the learned model which has been generated or updated.