Process estimation method and process estimation device

Patent metadata

Field	Value
Publication number	US-12468267-B2
Application number	US-202318113970-A
Country	US
Kind code	B2
Filing date	Feb 24, 2023
Priority date	Mar 2, 2022
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

A computer-performed process estimation method and a process estimation method using the computer are provided for estimating, based on a first process data including a process information of a predetermined target step performed in a first manufacturing device that manufactures a material through at least one step including the target step, a second process data including a process information of the target step performed in a second manufacturing device that is a different device from the first manufacturing device and manufactures the material through at least one step including the target step. This method includes machine-learning a relationship between the first process data and a first structure data obtained from a sample after the target step in the first manufacturing device, and creating a first regression model representing a correlation between the first process data and the first structure data, machine-learning a relationship between the second process data and a second structure data obtained from a sample after the target step in the second manufacturing device, and creating a second regression model representing a correlation between the second process data and the second structure data, creating a third regression model representing a correlation between the first process data and the second process data based on the first regression model and the second regression model, and by using the third regression model, estimating an estimated second process data that includes the second process data corresponding to an estimation source-first process data including the first process data that is an arbitrary estimation source.

First claim

The invention claimed is:

1 . A computer-performed process estimation method for estimating, based on a first process data comprising a process information of a predetermined target step performed in a first manufacturing device configured to manufacture a material through at least one step including the target step, a second process data comprising a process information of the target step performed in a second manufacturing device that is a different device from the first manufacturing device and configured to manufacture the material through at least one step including the target step, the method comprising:
machine-learning a relationship between the first process data and a first structure data obtained from a sample after the target step in the first manufacturing device, and creating a first regression model representing a correlation between the first process data and the first structure data; machine-learning a relationship between the second process data and a second structure data obtained from a sample after the target step in the second manufacturing device, and creating a second regression model representing a correlation between the second process data and the second structure data; creating a third regression model representing a correlation between the first process data and the second process data based on the first regression model and the second regression model; by using the third regression model, estimating an estimated second process data that comprises the second process data corresponding to an estimation source-first process data comprising the first process data that is an arbitrary estimation source; and controlling the second manufacturing device based on the estimated second process data.

2 . The computer-performed process estimation method according to claim 1 , wherein the first regression model is created by machine-learning a relationship between the first process data, the first structure data and also a composition data comprising a composition information of the material so as to represent a correlation between the first process data, the first structure data and the composition data, and wherein the second regression model is created by machine-learning a relationship between the second process data, the second structure data and also the composition data comprising the composition information of the material so as to represent a correlation between the second process data, the second structure data and the composition data.

3 . The computer-performed process estimation method according to claim 1 , wherein the material comprises a ceramic material.

4 . The computer-performed process estimation method according to claim 3 , wherein the material comprises a magnetic material.

5 . The computer-performed process estimation method according to claim 3 , wherein each of the first structure data and the second structure data comprises a feature amount based on temperature dependence of magnetization.

6 . The computer-performed process estimation method according to claim 3 , wherein the target step comprises at least one of a mixing step, a calcination step, a fine grinding step, a molding step, and a sintering step.

7 . The computer-performed process estimation method according to claim 1 , wherein the first manufacturing device comprises a research equipment and the second manufacturing device comprises a mass production equipment, and wherein to reproduce the material, which is manufactured by the research equipment, by the mass production equipment, the third regression model is used and the second process data for manufacturing the material to be reproduced by the mass production equipment is estimated from the first process data from when the research equipment manufactured the material to be reproduced.

8 . The computer-performed process estimation method according to claim 1 , wherein the first manufacturing device comprises a mass production equipment and the second manufacturing device comprises a research equipment, and wherein the third regression model is used and the second process data, which is to be experimental conditions in the research equipment and corresponds to the first process data representing conditions allowing for mass production by the mass production equipment, is estimated from the first process data.

9 . A process estimation device using a computer configured to estimate, based on a first process data comprising a process information of a predetermined target step performed in a first manufacturing device configured to manufacture a material through at least one step including the target step, a second process data comprising a process information of the target step performed in a second manufacturing device that is a different device from the first manufacturing device and configured to manufacture the material through at least one step including the target step, the device comprising:
a first regression model creation processing unit that machine-learns a relationship between the first process data and a first structure data obtained from a sample after the target step in the first manufacturing device, and creates a first regression model representing a correlation between the first process data and the first structure data; a second regression model creation processing unit that machine-learns a relationship between the second process data and a second structure data obtained from a sample after the target step in the second manufacturing device, and creates a second regression model representing a correlation between the second process data and the second structure data; a third regression model creation processing unit that creates a third regression model representing a correlation between the first process data and the second process data based on the first regression model and the second regression model; and a process estimation processing unit that, by using the third regression model, estimates an estimated second process data that comprises the second process data corresponding to an estimation source-first process data comprising the first process data that is an arbitrary estimation source, the device controlling the second manufacturing device based on the estimated second process data.

10 . The process estimation device according to claim 9 , wherein the first regression model is created by machine-learning a relationship between the first process data, the first structure data and also a composition data comprising a composition information of the material so as to represent a correlation between the first process data, the first structure data and the composition data, and wherein the second regression model is created by machine-learning a relationship between the second process data, the second structure data and also the composition data comprising the composition information of the material so as to represent a correlation between the second process data, the second structure data and the composition data.

11 . The process estimation device according to claim 9 , wherein the material comprises a ceramic material.

12 . The process estimation device according to claim 11 , wherein the material comprises a magnetic material.

13 . The process estimation device according to claim 11 , wherein each of the first structure data and the second structure data comprises a feature amount based on temperature dependence of magnetization.

14 . The computer-performed process estimation method according to claim 11 , wherein the target step comprises at least one of a mixing step, a calcination step, a fine grinding step, a molding step, and a sint

Assignees

• Proterial Ltd

Inventors

• Nishiuchi Takeshi
• TANIOKU Yasuaki

Classifications

• G05B19/4155

  characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program · CPC title

• G05B2219/31372

  Mes manufacturing execution system · CPC title

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title

• G06Q50/04

  Manufacturing · CPC title

• G06N20/00

  Machine learning · CPC title