Login| Sign Up| Help| Contact|

Patent Searching and Data


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:
JPS5932206[Title of the Invention] A lock on timing deciding method in automatic board thickness control of rolled plates and sheets of steel
JP2008012561APPARATUS FOR CONTROLLING WINDING TEMPERATURE OF STEEL SHEET
JPH0994605COLD ROLLING METHOD FOR STRIP METAL
Inventors:
OJIMA MAYUMI (JP)
FUNAKAWA YOSHIMASA (JP)
Application Number:
PCT/JP2021/029901
Publication Date:
March 17, 2022
Filing Date:
August 16, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
JFE STEEL CORP (JP)
International Classes:
B21B37/00; B21B38/00; G06N20/00
Domestic Patent References:
WO2020152993A12020-07-30
WO2020148917A12020-07-23
WO2003045607A22003-06-05
Foreign References:
JP2010172962A2010-08-12
JP2019087152A2019-06-06
JP2020115258A2020-07-30
JP2005315703A2005-11-10
EP3916651A12021-12-01
EP3912740A12021-11-24
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
Attorney, Agent or Firm:
SUGIMURA Kenji (JP)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: STEEL STRIP AND METHOD FOR PRODUCING SAME

Next Patent: SOLID-STATE IMAGING DEVICE, PRODUCTION METHOD THEREFOR, AND ELECTRONIC DEVICE