Ion beam irradiation apparatus and program therefor

Patent metadata

Field	Value
Publication number	US-11462385-B2
Application number	US-202016801689-A
Country	US
Kind code	B2
Filing date	Feb 26, 2020
Priority date	Mar 25, 2019
Publication date	Oct 4, 2022
Grant date	Oct 4, 2022

Abstract

An ion beam irradiation apparatus includes modules for generating an ion beam meeting a processing condition, and a machine learning part that generates a learning algorithm using, as an explanatory variable, a processing condition during new processing and a monitored value that indicates a state of a module during a last processing immediately before the new processing, and a basic operation parameter output part that uses the learning algorithm to output an initial value of a basic operation parameter for controlling an operation of the module.

First claim

What is claimed is:

1. An ion beam irradiation apparatus comprising:
a plurality of modules for generating an ion beam meeting a processing condition;
a memory storing program code; and
at least one central processing unit (CPU) which accesses the memory to read the program code and execute the program code to operate as:
a machine learning part that generates a learning algorithm using, as an explanatory variable, a processing condition during new processing and a monitored value that indicates a state of at least one of the modules during a last processing immediately before the new processing; and
a basic operation parameter output part that uses the learning algorithm to output an initial value of a basic operation parameter for controlling an operation of the at least one of the modules.

2. The ion beam irradiation apparatus as recited in claim 1 , wherein the at least one CPU further executes the program code to input an initial value to one of the modules, and the one of the modules is operated based on an adjusted value obtained by adjusting the initial value,
wherein the CPU further executes the program code to operate as:
a learning data storage part that stores learning data obtained from a plurality of previous processings that are prior to the new processing, the learning data including a plurality of data sets, each data set including the processing condition used in the processing, at least one of the initial value or the adjusted value for at least one module in the processing, the monitored value of the at least one module during the last processing immediately before the processing, and an actual value of an objective variable that is measured in the processing associated with each other, and
wherein the learning algorithm is generated through machine learning using the learning data.

3. The ion beam irradiation apparatus as recited in claim 2 , wherein the objective variable comprises a setup time period until the adjusted value is obtained; an index value indicative of whether or not the adjusted value is obtained; a beam current amplitude of the ion beam; a beam angle of the ion beam; or a beam current density of the ion beam.

4. The ion beam irradiation apparatus as recited in claim 2 , wherein the plurality of modules include an ion source system-module, and
wherein the learning data includes the monitored value of at least the ion source system-module.

5. The ion beam irradiation apparatus as recited in claim 4 , wherein the basic operation parameter comprises at least one of a flow rate of a gas to be supplied to a plasma chamber constituting the ion source-system module, or a current to be supplied to a source magnet for generating a magnetic field inside the plasma chamber.

6. The ion beam irradiation apparatus as recited in claim 1 , which further comprises:
a control device comprising a memory storing control program code and at least one central processing unit (CPU) that accesses the memory to execute the control program code to:
based on the processing condition and a setup sequence, select an initial value of the basic operation parameter;
input the selected initial value to one of the modules; and
adjust the input initial value to setup the one of the modules.

7. The ion beam irradiation apparatus as recited in claim 6 , wherein the at least one CPU of the control device further executes the control program code to operate as a recovery part that, when the setup of the one of the modules fails to be completed, acquire an abnormal signal indicative of the failure, and in response to the abnormal signal, input the initial value of the basic operation parameter output from the basic operation parameter output part to the one of the modules.

8. The ion beam irradiation apparatus as recited in claim 6 , wherein the at least one CPU of the control device further executes the control program code to operate as an advance prediction part that, when using the initial value selected based on the processing condition and the setup sequence, predicts whether or not the setup of the one of the modules will be completed, and
in response to the advance prediction part predicting that the setup of the one of the modules will not be completed, input the initial value of the basic operation parameter output from the basic operation parameter output part to the one of the modules.

9. A computer readable storage medium storing program code which, when executed by at least one central processing unit (CPU) of an ion beam irradiation apparatus that includes a plurality of modules for generating an ion beam meeting a processing condition, causes the CPU to operate as:
a machine learning part that generates a learning algorithm using, as an explanatory variable, a processing condition during new processing and a monitored value that indicates a state of at least one of the modules during a last processing immediately before the new processing; and
a basic operation parameter output part that uses the learning algorithm to output an initial value of a basic operation parameter for controlling an operation of at least one of a plurality of modules for generating an ion beam meeting the processing condition.

Assignees

• Nissin Ion Equipment Co Ltd

Inventors

• Takemura Shinya

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• H01J37/3171

  for ion implantation · CPC title

• H01J37/08

  Ion sources; Ion guns · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• H01J2237/30427

  using neural networks or fuzzy logic · CPC title