The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 09, 2025

Filed:

Feb. 04, 2021
Applicant:

Daicel Corporation, Osaka, JP;

Inventors:

Masahiro Haitsuka, Tokyo, JP;

Hidetoshi Kozono, Tokyo, JP;

Fumihiro Miyoshi, Tokyo, JP;

Assignee:

DAICEL CORPORATION, Osaka, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G05B 19/418 (2006.01);
U.S. Cl.
CPC ...
G05B 19/41875 (2013.01); G05B 19/4183 (2013.01); G05B 19/41885 (2013.01);
Abstract

To accurately obtain operating conditions of a production facility that satisfies desired criteria. A control apparatus includes a process data acquisition unit that reads process data from a storage device that stores the process data obtained from a production facility, and a control unit that obtains an optimum solution for a predetermined adjustment target of the process data and controls the production facility on the basis of the optimum solution. The optimum solution satisfies constraint conditions and optimizes an objective function. The constraint conditions are defined by using at least some of the process data. The objective function is defined by using at least some of the process data. A learned model having learned features of the process data obtained from the production facility is further stored in a storage device on the basis of causality information that defines a combination of first process data and second process data. The first process data is used as an explanatory variable. The second process data is used as a response variable. The constraint conditions include a condition that the second process data or a value corresponding to the second process data is a value calculated by using the first process data and the learned model, and an upper limit or a lower limit for at least some of the process data.


Find Patent Forward Citations

Loading…