知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.017 秒)

    Learning Model Generation Method, Non-Transitory Computer Readable Recording Medium, Set Value Determination Device, Molding Machine, and Molding Apparatus System
    4.
    发明申请
    Learning Model Generation Method, Non-Transitory Computer Readable Recording Medium, Set Value Determination Device, Molding Machine, and Molding Apparatus System 有权

    公开(公告)号：US20220402183A1

    公开(公告)日：2022-12-22

    申请号：US17770419

    申请日：2020-10-08

    申请人： The Japan Steel Works, Ltd.

    发明人： Takayuki Hirano

    IPC分类号： B29C45/76 ,  G05B13/02

    摘要： First training data including a set value related to a molding machine, a measured value obtained by measuring a physical quantity related to molding, and a degree of quality of a molded product generated by the molding machine is collected, a first learning model for outputting a degree of quality of a molded product when a set value and a measured value are input is generated by machine learning based on collected first training data, second training data including a defect degree for each defect type of a molded product, a measured value, and a set value capable of reducing the defect degree is collected, and a second learning model for outputting a set value capable of reducing a defect degree when a defect degree and a measured value are input is generated by machine learning based on collected second training data and a degree of quality output from the first learning model.

    Abnormality Detection System, Molding Machine System, Abnormality Detection Apparatus, Abnormality Detection Method and Non-Transitory Computer Readable Recording Medium
    5.
    发明公开
    Abnormality Detection System, Molding Machine System, Abnormality Detection Apparatus, Abnormality Detection Method and Non-Transitory Computer Readable Recording Medium 审中-公开

    公开(公告)号：US20240109237A1

    公开(公告)日：2024-04-04

    申请号：US18273723

    申请日：2021-10-27

    申请人： The Japan Steel Works, Ltd.

    发明人： Mikio Furokawa ,  Jun Suzuki ,  Takayuki Hirano

    IPC分类号： B29C48/92 ,  G01M99/00

    CPC分类号： B29C48/92 ,  G01M99/005 ,  B29C48/40

    摘要： An abnormality detection system includes an abnormality detection apparatus that detects an abnormality of a production device, a control device that performs operation control of the manufacturing device and transmits operating data, a sensor that detects a physical quantity related to operation or a product of the manufacturing device and outputs sensor value data, and a diagnostic apparatus. The abnormality detection apparatus determines a presence or an absence of an abnormality of the manufacturing device based on the operating data transmitted from the control device and the sensor value data output from the sensor and transmits the determination result to the control device. The abnormality detection apparatus further transmits the operating data and the sensor value data to the diagnostic apparatus. The diagnostic apparatus diagnoses the condition of the manufacturing device based on sensor value data accumulated in the past in the database and the received data and transmits the diagnostic result to the abnormality detection apparatus. The abnormality detection apparatus transmits the diagnostic result to the control device.

    Machine Learning Method, Non-Transitory Computer Readable Recording Medium, Machine Learning Device, and Molding Machine
    7.
    发明公开
    Machine Learning Method, Non-Transitory Computer Readable Recording Medium, Machine Learning Device, and Molding Machine 审中-公开

    公开(公告)号：US20230325562A1

    公开(公告)日：2023-10-12

    申请号：US18025255

    申请日：2021-08-03

    申请人： The Japan Steel Works, Ltd.

    发明人： Takayuki Hirano

    IPC分类号： G06F30/27

    CPC分类号： G06F30/27 ,  G06F2119/18

    摘要： Provided is a machine learning method of a learning model that outputs a variable parameter that is configured to reduce the degree of defect of a molded article obtained by actual molding and relates to molding conditions of a molding machine in a case where observation data obtained by observing a physical quantity relating to actual molding using the molding machine is input. The machine learning method includes: a step of simulating a molding process by setting a variable parameter and a fixed parameter to a fluid analysis device; a step of acquiring a defect-related parameter that is obtained by simulation and relates to the degree of defect of the molded article; a step of calculating the degree of defect of the molded article on the basis of the acquired defect-related parameter; and a step of causing the learning model to perform machine learning by using the variable parameter set to the fluid analysis device and reward corresponding to the calculated degree of defect.

    Dataset Creation Method, Learning Model Generation Method, Non-Transitory Computer Readable Recording Medium, and Dataset Creation Device
    8.
    发明公开
    Dataset Creation Method, Learning Model Generation Method, Non-Transitory Computer Readable Recording Medium, and Dataset Creation Device 审中-公开

    公开(公告)号：US20240326306A1

    公开(公告)日：2024-10-03

    申请号：US18291483

    申请日：2022-06-01

    申请人： The Japan Steel Works, Ltd.

    发明人： Akihiko Saeki ,  Takashi Akagi ,  Takayuki Hirano

    IPC分类号： B29C45/76

    CPC分类号： B29C45/768 ,  B29C45/766 ,  B29C2945/76949

    摘要： Physical quantity data indicating the state of a molded product produced by changing a first molding condition parameter set in a molding machine such that the quality of the molded product is degraded or the state of the molding machine is acquired, physical quantity data indicating the state of a molded product produced by changing a second molding condition parameter set in the molding machine or the state of the molding machine is acquired, the second molding condition parameter before change, the physical quantity data obtained at this time, the second molding condition parameter after change, and the physical quantity data obtained when setting the second molding condition parameter after change are stored in association with each other, and a dataset for machine learning is created by repeating the change of the first and second molding condition parameters and the acquisition of the physical quantity data.

    Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine
    9.
    发明公开
    Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine 审中-公开

    公开(公告)号：US20240227266A9

    公开(公告)日：2024-07-11

    申请号：US18279166

    申请日：2022-03-17

    申请人： THE JAPAN STEEL WORKS, LTD.

    发明人： Takayuki Hirano

    IPC分类号： B29C45/76

    CPC分类号： B29C45/76 ,  B29C2945/76979

    摘要： A reinforcement learning method of a learning machine including a first agent adjusting a manufacture condition of a manufacturing device based on observation data obtained by observing a state of the manufacturing device and a second agent having a functional model or a functional approximator representing a relationship between the observation data and the manufacture condition in a different way from the first agent, comprises: adjusting the manufacture condition searched by the first agent that is performing reinforcement learning, using the observation data and the functional model or the functional approximator of the second agent; calculating reward data in accordance with a state of a product manufactured by the manufacturing device under the manufacture condition adjusted; and performing reinforcement learning on the first agent and the second agent based on the observation data and the reward data calculated.

    Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine
    10.
    发明公开
    Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine 审中-公开

    公开(公告)号：US20240131765A1

    公开(公告)日：2024-04-25

    申请号：US18279166

    申请日：2022-03-16

    申请人： THE JAPAN STEEL WORKS, LTD.

    发明人： Takayuki Hirano

    IPC分类号： B29C45/76

    CPC分类号： B29C45/76 ,  B29C2945/76979

    摘要： A reinforcement learning method of a learning machine including a first agent adjusting a manufacture condition of a manufacturing device based on observation data obtained by observing a state of the manufacturing device and a second agent having a functional model or a functional approximator representing a relationship between the observation data and the manufacture condition in a different way from the first agent, comprises: adjusting the manufacture condition searched by the first agent that is performing reinforcement learning, using the observation data and the functional model or the functional approximator of the second agent; calculating reward data in accordance with a state of a product manufactured by the manufacturing device under the manufacture condition adjusted; and performing reinforcement learning on the first agent and the second agent based on the observation data and the reward data calculated.