Apparatus, method, and computer readable medium

Patent metadata

Field	Value
Publication number	US-12530004-B2
Application number	US-202217970556-A
Country	US
Kind code	B2
Filing date	Oct 20, 2022
Priority date	Oct 27, 2021
Publication date	Jan 20, 2026
Grant date	Jan 20, 2026

Abstract

Provided is an apparatus including a supply unit suppling a value of a state parameter to an operation model outputting a recommendation value of a control parameter of a piece of equipment in response to a value of a state parameter relating to the piece of equipment being input; a control parameter acquisition unit acquiring a recommendation value of a control parameter output from the operation model in response to the supply unit supplying a value of a state parameter to the operation model; an acquisition unit acquiring a model evaluation value corresponding to a result of having operated the piece of equipment according to the recommendation value acquired by the control parameter acquisition unit; and an evaluation unit evaluating the operation model, based on the model evaluation value and a reference evaluation value corresponding to a result of having operated the piece of equipment through manipulation by a human.

First claim

What is claimed is:

1 . An apparatus comprising at least one processor, wherein:
the at least one processor supplies a value of a state parameter to an operation model configured to output a recommendation value of a control parameter of a piece of equipment in response to a value of a state parameter relating to the piece of equipment being input; the at least one processor acquires the recommendation value of the control parameter that is output from the operation model in response to the at least one processor supplying a value of a state parameter to the operation model; the at least one processor acquires a model evaluation value corresponding to a result of having operated the piece of equipment according to the recommendation value acquired by the at least one processor; and the at least one processor evaluates the operation model based on the model evaluation value and a reference evaluation value, wherein the reference evaluation value relates to a result of the piece of equipment being operated using the control parameters chosen through a manipulation by a human.

2 . The apparatus according to claim 1 , wherein
the reference evaluation value is calculated based on a result of having input a manipulation by a human to a simulator of the piece of equipment.

3 . The apparatus according to claim 2 , wherein
the model evaluation value is calculated based on a result of having input the recommendation value acquired by the at least one processor to a simulator of the piece of equipment.

4 . The apparatus according to claim 2 , wherein
the model evaluation value is calculated based on whether a parameter relating to the piece of equipment operated according to the recommendation value falls within a target range, and the reference evaluation value is calculated based on whether a parameter relating to the piece of equipment operated through a manipulation by a human falls within the target range.

5 . The apparatus according to claim 2 , wherein the at least one processor executes learning processing of the operation model by using learning data including a value of a state parameter and a value of a control parameter.

6 . The apparatus according to claim 1 , wherein
the model evaluation value is calculated based on a result of having input the recommendation value acquired by the at least one processor to a simulator of the piece of equipment.

7 . The apparatus according to claim 6 , wherein
the model evaluation value is calculated based on whether a parameter relating to the piece of equipment operated according to the recommendation value falls within a target range, and the reference evaluation value is calculated based on whether a parameter relating to the piece of equipment operated through a manipulation by a human falls within the target range.

8 . The apparatus according to claim 6 , wherein the at least one processor executes learning processing of the operation model by using learning data including a value of a state parameter and a value of a control parameter.

9 . The apparatus according to claim 1 , wherein
the model evaluation value is calculated based on whether a parameter relating to the piece of equipment operated according to the recommendation value falls within a target range, and the reference evaluation value is calculated based on whether a parameter relating to the piece of equipment operated through a manipulation by a human falls within the target range.

10 . The apparatus according to claim 9 , wherein the at least one processor acquires the target range set by an operator with respect to a selection parameter selected by the operator among a plurality of types of parameters relating to the piece of equipment.

11 . The apparatus according to claim 10 , wherein the at least one processor causes, in response to the selection parameter being selected from the plurality of types of parameters, a value of the selection parameter in a past operation of the piece of equipment to be displayed.

12 . The apparatus according to claim 11 , wherein
the at least one processor causes a value of each selection parameter in the past operation of the piece of equipment to be displayed in a coordinate space in which each selection parameter is set as a coordinate axis.

13 . The apparatus according to claim 12 , wherein
the piece of equipment is a piece of equipment configured to manufacture an article, and the parameter relating to the piece of equipment is at least one of an index value representing a quality of the article or a production volume of the article.

14 . The apparatus according to claim 11 , wherein
the piece of equipment is a piece of equipment configured to manufacture an article, and the parameter relating to the piece of equipment is at least one of an index value representing a quality of the article or a production volume of the article.

15 . The apparatus according to claim 9 , wherein
the piece of equipment is a piece of equipment configured to manufacture an article, and the parameter relating to the piece of equipment is at least one of an index value representing a quality of the article or a production volume of the article.

16 . The apparatus according to claim 10 , wherein
the piece of equipment is a piece of equipment configured to manufacture an article, and the parameter relating to the piece of equipment is at least one of an index value representing a quality of the article or a production volume of the article.

17 . The apparatus according to claim 1 , wherein the at least one processor executes learning processing of the operation model by using learning data including a value of a state parameter and a value of a control parameter.

18 . The apparatus according to claim 17 , wherein
the at least one processor executes the learning processing of the operation model by using the learning data and a reward value determined by a preset reward function.

19 . A method comprising:
supplying a value of a state parameter to an operation model configured to output a recommendation value of a control parameter of a piece of equipment, in response to a value of a state parameter representing a state relating to the piece of equipment being input; acquiring a control parameter by acquiring the recommendation value of the control parameter that is output from the operation model in response to supplying a value of a state parameter to the operation model by the supplying; acquiring a model evaluation value corresponding to a result of having operated the piece of equipment according to the recommendation value acquired by the acquiring the recommendation value of the control parameter; and evaluating the operation model based on the model evaluation value and a reference evaluation value, wherein the reference evaluation value relates to a result of the piece of equipment being operated using the control parameters chosen through a manipulation by a human.

20 . A non-transitory computer readable storage medium having recorded thereon a program configured to cause a computer to:
supply a value of a state parameter to an operation model configured to output a recommendation value of a control parameter of a piece of equipment in response to a value of a state parameter relating to the piece of equipment being input; acquire the recommendation value of the control parameter that is output from the operation model in response to the computer supplying a value of a state parameter to the operation mode

Assignees

• Yokogawa Electric Corp

Inventors

• Takami Go
• Yamamoto Junji
• Kobuchi Keiichiro
• Kanokogi Hiroaki
• Furukawa Yota

Classifications

• G05B13/042

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• G05B13/048

  using a predictor · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G05B13/04

  involving the use of models or simulators · CPC title

• G05B19/41885

  characterised by modeling, simulation of the manufacturing system · CPC title