Title:
SYSTEM FOR PREDICTING MATERIAL CHARACTERISTIC VALUE, AND METHOD FOR PRODUCING METAL SHEET
Document Type and Number:
WIPO Patent Application WO/2022/054500
Kind Code:
A1
Abstract:
Provided is a system for predicting a characteristic value of a material, said system being capable of predicting the characteristic value of a material with high precision. Also provided is a method for producing a metal sheet with which the yield of a product can be improved by appropriately changing a production condition in a subsequent step on the basis of a characteristic value of a material as predicted by this system for predicting a characteristic value of a material. This system (100) for predicting a characteristic value of a material is provided with a material characteristic value prediction unit that acquires input data, which includes an equipment output factor for equipment for producing the metal sheet, a disturbance factor, and component values for the metal sheet during production, and uses a prediction model to which the input data is input to predict a material characteristic value of a produced metal sheet. The prediction model includes a machine learning model generated by machine learning, wherein the input data is input and a production condition factor is output, and a metallurgy model that receives the production condition factor as an input, and outputs a material characteristic value.
More Like This:
Inventors:
OJIMA MAYUMI (JP)
FUNAKAWA YOSHIMASA (JP)
FUNAKAWA YOSHIMASA (JP)
Application Number:
PCT/JP2021/029901
Publication Date:
March 17, 2022
Filing Date:
August 16, 2021
Export Citation:
Assignee:
JFE STEEL CORP (JP)
International Classes:
B21B37/00; B21B38/00; G06N20/00
Domestic Patent References:
WO2020152993A1 | 2020-07-30 | |||
WO2020148917A1 | 2020-07-23 | |||
WO2003045607A2 | 2003-06-05 |
Foreign References:
JP2010172962A | 2010-08-12 | |||
JP2019087152A | 2019-06-06 | |||
JP2020115258A | 2020-07-30 | |||
JP2005315703A | 2005-11-10 | |||
EP3916651A1 | 2021-12-01 | |||
EP3912740A1 | 2021-11-24 |
Other References:
LI, F. ET AL.: "Ensemble Machine Learning Systems for the Estimation of Steel Quality", IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA, 2018, pages 2245 - 2252, XP033508549, DOI: 10.1109/BigData.2018.8622583
KUEGEL M.: "Five use case ideas to inspire data driven innovation", WHITE PAPER, 1 June 2020 (2020-06-01), pages 1 - 11, XP093115724
See also references of EP 4183495A4
KUEGEL M.: "Five use case ideas to inspire data driven innovation", WHITE PAPER, 1 June 2020 (2020-06-01), pages 1 - 11, XP093115724
See also references of EP 4183495A4
Attorney, Agent or Firm:
SUGIMURA Kenji (JP)
Download PDF:
Previous Patent: STEEL STRIP AND METHOD FOR PRODUCING SAME
Next Patent: SOLID-STATE IMAGING DEVICE, PRODUCTION METHOD THEREFOR, AND ELECTRONIC DEVICE
Next Patent: SOLID-STATE IMAGING DEVICE, PRODUCTION METHOD THEREFOR, AND ELECTRONIC DEVICE