IP Library › Granted Patent US 12,285,792
Granted Patent B2
US 12,285,792 · App. 17/429,819 · Granted Apr 29, 2025

Setup condition determining method for manufacturing facilities, mill setup value determining method for rolling mill, mill setup value determining device for rolling mill, product manufacturing method, and rolled material manufacturing method

Inventor: Tatsuya Yamazaki (Tokyo, JP)
Assignee: JFE Steel Corporation
B21B37/00G05B19/41885G05B2219/33034
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,285,792
App. No.
17/429,819
Granted
Apr 29, 2025
Kind
B2
Abstract

A set condition determining method for manufacturing facilities includes: inputting, into a trained model, a manufacturing condition for a target product and a setup condition that is for a product manufactured in same manufacturing facilities before manufacture of the target product and that reflects setup condition modification by an operator's manual manipulation; and obtaining a setup condition for the target product. The trained model has been trained with input being: manufacturing conditions for the target product; and setup conditions that are for the product manufactured in the same manufacturing facilities before the manufacture of the target product and that reflect setup condition modification by an operator's manual manipulation, and output being setup conditions for the target product.

Claims (51)

1. A mill setup value determining method for a rolling mill, comprising:

a mill setup value calculating step of:

inputting, into a trained model, a mill setup value for a target rolled material and a mill setup value that is for a rolled material manufactured by the rolling mill before manufacture of the target rolled material and that reflects setup value modification by an operator's manual manipulation; and

obtaining a mill setup value for the target rolled material, wherein

the trained model has been trained with input comprising:

manufacturing conditions for the target rolled material; and

mill setup values that are for the rolled material manufactured by the rolling mill before the manufacture of the target rolled material and that reflect setup value modification by an operator's manual manipulation, and

output being mill setup values for the target rolled material;

wherein

the trained model includes:

a first trained model obtained by training a learning model with input comprising:

manufacturing conditions for the target rolled material; and

mill setup values that are for a rolled material manufactured by the rolling mill before manufacture of the target rolled material and that reflect modification by an operator's manual manipulation, and

output being mill setup values for the target rolled material; and

a second trained model obtained by training a learning model with input being manufacturing conditions for the target rolled material, and

output being mill setup values for the target rolled material, and

the mill setup value calculating step includes:

obtaining, as output, a first mill setup value for the target rolled material by inputting, into the first trained model, a manufacturing condition for the target rolled material and a mill setup value for a rolled material manufactured by the rolling mill before the manufacture of the target rolled material, if it is determined, on the basis of a predetermined determination condition, that using a previous mill setup value is appropriate;

obtaining, as output, a second mill setup value for the target rolled material by inputting, into the second trained model, a manufacturing condition for the target rolled material, if it is determined, on the basis of the predetermined determination condition, that using the previous mill setup value is not appropriate; and

changing a setting of the rolling mill with the obtained first or second mill setup values.

2. The mill setup value determining method for a rolling mill according to claim 1 , wherein

the trained model is obtained by training a learning model with input comprising:

manufacturing conditions for a target rolled material;

manufacturing conditions for a rolled material manufactured by the rolling mill before manufacture of the target rolled material; and

mill setup values that are for the rolled material manufactured by the rolling mill before the manufacture of the target rolled material and that reflect setup value modification by an operator's manual manipulation, and

output being mill setup values for the target rolled material, and

the mill setup value calculating process includes obtaining, as output, a mill setup value for the target rolled material by inputting, into the trained model, a manufacturing condition for the target rolled material, a manufacturing condition for the rolled material manufactured by the rolling mill before the manufacture of the target rolled material, and a mill setup value for the rolled material manufactured by the rolling mill before the manufacture of the target rolled mill.

3. A rolled material manufacturing method comprising:

allocating one or more rolling conditions; and

manufacturing a rolled material with the allocated one or more rolling conditions using the changed setting according to claim 1 .

4. A mill setup value determining device for a mill setup process for a rolling mill, the mill setup value determining device comprising:

a mill setup value calculating device configured to obtain, as output, a mill setup value for a target rolled material by inputting, into a trained model, a manufacturing condition for the target rolled material and a mill setup value for a rolled material manufactured by the rolling mill before manufacture of the target rolled material, wherein

the trained model is obtained by training a learning model with input comprising:

manufacturing condition for the target rolled material; and

mill setup values that are for the rolled material manufactured by the rolling mill before the manufacture of the target rolled material and that reflect setup value modification by an operator's manual manipulation, and

output being mill setup values for the target rolled material;

wherein

the trained model includes:

a first trained model obtained by training a learning model with input comprising:

manufacturing conditions for the target rolled material; and

mill setup values that are for a rolled material manufactured by the rolling mill before manufacture of the target rolled material and that reflect modification by an operator's manual manipulation, and

output being mill setup values for the target rolled material; and

a second trained model obtained by training a learning model with input being manufacturing conditions for the target rolled material, and

output being mill setup values for the target rolled material, and

the mill setup value calculating process includes:

obtaining, as output, a first mill setup value for the target rolled material by inputting, into the first trained model, a manufacturing condition for the target rolled material and a mill setup value for a rolled material manufactured by the rolling mill before the manufacture of the target rolled material, if it is determined, on the basis of a predetermined determination condition, that using a previous mill setup value is appropriate; and

obtaining, as output, a second mill setup value for the target rolled material by inputting, into the second trained model, a manufacturing condition for the target rolled material, if it is determined, on the basis of the predetermined determination condition, that using the previous mill setup value is not appropriate; and

a control device configured to change a setting of the rolling mill with the obtained first or second mill setup value.

5. A rolled material manufacturing method comprising:

allocating one or more rolling conditions; and

manufacturing a rolled material with the allocated one or more rolling conditions using the changed setting according to claim 4 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 10, 2021
From: YAMAZAKI, TATSUYA
To: JFE STEEL CORPORATION
Reel/Frame 057136/0188 →
Priority Claims (1)
JP 2019-022839 · Feb 12, 2019 · national
Continuity (1)
Related Publication 20220126339A1 · Apr 28, 2022
References Cited (27)
US 5414619A · Katayama et al. · 1995 [cited by applicant]
US 5586221A · Isik · 1996 [cited by examiner]
US 5930136A · Nakajima et al. · 1999 [cited by applicant]
US 6745169B1 · Schlang et al. · 2004 [cited by applicant]
US 20180341248A1 · Mehr et al. · 2018 [cited by applicant]
CN 101683659A · 2010 [cited by applicant]
CN 107486475A · 2017 [cited by applicant]
CN 107908836A · 2018 [cited by applicant]
EP 0460892A2 · 1991 [cited by applicant]
JP S59215205A · 1984 [cited by applicant]
JP H0538511A · 1993 [cited by applicant]
JP H07204718A · 1995 [cited by applicant]
JP H0890020A · 1996 [cited by applicant]
JP H08117827A · 1996 [cited by applicant]
JP H09155420A · 1997 [cited by applicant]
JP H1034216A · 1998 [cited by applicant]
JP H10198402A · 1998 [cited by applicant]
JP 3223856B2 · 2001 [cited by applicant]
JP 2004255436A · 2004 [cited by applicant]
JP 2010120047A · 2010 [cited by applicant]
Hong, W. K., et al. “Flatness control of strip in continuous hot rolling processes.” 2003 European Control Conference (ECC). IEEE, 2003. (Year: 2003). [cited by examiner]
Akira Murakami et al., “Optimization of Pass Schedules for a Tandem Cold Mill,” Tetsu-to-Hagané, The Iron and Steel Institute of Japan, 2004, vol. 90, No. 11, pp. 95-99 (Abstract). [cited by applicant]
K. Nakai et al., “Support System of Mill Set-up Model Adjustment,” Hitachi Review, vol. 67, No. 4, 1985, pp. 75-78, along with an English Abstract. [cited by applicant]
Kozo Nakai et al., “Support System of Mill Set-up Model Adjustment,” Hitachi Review, 1985, vol. 67, No. 4. [cited by applicant]
The Extended European Search Report dated Mar. 10, 2022, of counterpart European Patent Application No. 19915005.3. [cited by applicant]
Office Action dated Dec. 12, 2023, of counterpart Korean Patent Application No. 10-2021-7025534, along with a Concise Statement of Relevance of Office Action in English. [cited by applicant]
First Office Action dated Feb. 3, 2024, of counterpart Chinese Patent Application No. 201980091804.8, along with an English translation. [cited by applicant]