Substrate processing apparatus, article manufacturing method, substrate processing method, substrate processing system, management apparatus, and storage medium

Patent metadata

Field	Value
Publication number	US-10996574-B2
Application number	US-202016830753-A
Country	US
Kind code	B2
Filing date	Mar 26, 2020
Priority date	Apr 18, 2019
Publication date	May 4, 2021
Grant date	May 4, 2021

Abstract

A substrate processing apparatus is provided. The apparatus includes an imaging unit that images a mark on a substrate, and a processor that aligns the substrate based on an image of the mark obtained by the imaging unit. If the alignment has failed, the processor identifies a factor of the failure based on information including the image and executes at least one of a plurality of recovery processes based on the identified factor. The processor includes an output unit that outputs a condition for the at least one of recovery processes in accordance with an inference model, and a learning unit that learns the inference model based on an execution result of the at least one of the recovery processes under the condition output from the output unit.

First claim

What is claimed is:

1. A substrate processing apparatus that processes a substrate, the apparatus comprising:
an imaging unit configured to image a mark provided on the substrate; and
a processor configured to align the substrate based on a position of the mark obtained by processing an image of the mark obtained by the imaging unit,
wherein if the alignment has failed, the processor identifies a factor of the failure based on information including the image and executes at least one of a plurality of recovery processes based on the identified factor of the failure, and
the processor includes an output unit configured to output a condition for the at least one of the recovery processes corresponding to the identified factor of the failure, in accordance with an inference model, and
a learning unit configured to learn the inference model based on an execution result obtained from the at least one of the recovery processes under the condition output from the output unit.

2. The apparatus according to claim 1 , wherein the learning is performed by setting a factor of the alignment failure as a state and a condition for a recovery process corresponding to the state as an action and evaluating a reward obtained by the action.

3. The apparatus according to claim 2 , wherein the learning is performed so as to maximize an expected value of a sum of rewards obtained by actions selected in observed states.

4. The apparatus according to claim 3 , wherein the learning includes giving a positive reward if a recovery process has succeeded under a condition determined as the selected action and giving a negative reward if the recovery process has failed.

5. The apparatus according to claim 1 , wherein the processor determines that the alignment has failed, if an index corresponding to the image is lower than a predetermined threshold.

6. The apparatus according to claim 5 , wherein the index includes at least one of a signal intensity of the image, a contrast, and a degree of correlation of pattern matching.

7. The apparatus according to claim 1 , further comprising a notification unit configured to notify contents of the executed at least one of the recovery processes.

8. The apparatus according to claim 1 , wherein the plurality of recovery processes include expansion of a search range for an image of the mark in the image, a change of an imaging condition in the imaging unit, and a change of a mark, of a plurality of marks provided on the substrate, which is used.

9. The apparatus according to claim 1 , wherein the information includes an offset setting, a type of the mark, and context information in addition to the image.

10. An article manufacturing method comprising:
forming a pattern on a substrate by using a substrate processing apparatus defined in claim 1 ; and
processing the substrate on which the pattern is formed,
wherein an article is manufactured from the processed substrate.

11. A substrate processing method comprising:
imaging a mark provided on a substrate by using an imaging unit:
aligning the substrate based on a position of the mark which is obtained by processing an image of the mark which is obtained in the imaging;
identifying, if the alignment has failed, a factor of the failure based on information including the image:
determining at least one of a plurality of recovery processes, which correspond to the identified factor of the failure;
outputting a condition for the determined at least one of the recovery processes in accordance with an inference model;
executing the determined at least one of the recovery processes under the output condition; and
learning the inference model based on an execution result obtained by the at least one of the recovery processes under the output condition.

12. A substrate processing system comprising a substrate processing apparatus configured to process a substrate and a management apparatus configured to manage the substrate processing apparatus,
the substrate processing apparatus comprising:
an imaging unit configured to image a mark provided on the substrate; and
a transmission unit configured to transmit an image captured by the imaging unit to the management apparatus,

the management apparatus comprising:
a reception unit configured to receive the image transmitted from the transmission unit of the substrate processing apparatus; and
a processor configured to instruct the substrate processing apparatus to align the substrate based on a position of the mark obtained by processing the received image,

wherein the processor instructs, if the alignment has failed, the substrate processing apparatus to identify a factor of the failure based on information including the image and execute at least one of a plurality of recovery processes based on the identified factor of the failure, and
the processor includes:
an output unit configured to output a condition for the at least one of the recovery processes corresponding to the identified factor of the failure, in accordance with an inference model, and
a learning unit configured to learn the inference model based on an execution result obtained from the at least one of the recovery processes under the condition output from the output unit.

13. A management apparatus that manages a substrate processing apparatus configured to process a substrate, the management apparatus comprising:
a reception unit configured to receive an image of a mark provided on the substrate which is imaged by an imaging unit of the substrate processing apparatus; and
a processor configured to instruct the substrate processing apparatus to align the substrate based on a position of the mark which is obtained by processing the received image,
wherein the processor instructs, if the alignment has failed, the substrate processing apparatus to identify a factor of the failure based on information including the image and execute at least one of a plurality of recovery processes based on the identified factor of the failure, and
the processor includes:
an output unit configured to output a condition for the at least one of recovery processes corresponding to the identified factor of the failure, in accordance with an inference model, and
a learning unit configured to learn the inference model based on an execution result obtained from the at least one of the recovery processes under the condition output from the output unit.

14. A non-transitory computer-readable storage medium storing a program for causing a computer to function as each unit of a management apparatus defined in claim 13 .

Assignees

• Canon Kk

Inventors

• Takiguchi Takahiro
• Koga Shinichiro

Classifications

• H10P76/2041

  Photolithographic processes · CPC title

• G03F9/7092

  Signal processing · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G03F9/7088 Primary

  Alignment mark detection, e.g. TTR, TTL, off-axis detection, array detector, video detection · CPC title

• G06T7/30

  Determination of transform parameters for the alignment of images, i.e. image registration · CPC title