Alignment Mark Imaging with AI Parameter Adjustment

Solution Overview

Problem

Existing methods for detecting alignment marks in exposure apparatuses require manual parameter adjustment by operators, which is time-consuming and knowledge-intensive, and automated adjustment methods are inefficient, prolonging the parameter determination process.

Innovation Solution

A mark detecting apparatus and method that utilize a learning model to automatically adjust imaging parameters using machine learning, specifically a convolutional neural network, to quickly and accurately acquire a good alignment mark image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual parameter adjustment is used, then detection accuracy can be achieved, but time consumption increases significantly

Engineering Contradiction:

Improvealignment mark detection accuracyVSAvoidparameter adjustment time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary learning by collecting alignment mark images under various imaging conditions and pre-processing them into training datasets. This preliminary action enables the machine learning model to be trained in advance, so that during actual operation, parameter adjustment can be performed quickly without manual intervention, thus resolving the contradiction between detection accuracy and time consumption.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual mechanical adjustment process with an automated machine learning-based system. The machine learning model automatically determines optimal imaging parameters by learning from training data, substituting the manual operator's mechanical adjustment process. This substitution maintains high detection accuracy while dramatically reducing the time required for parameter adjustment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If automated parameter adjustment is used, then operation efficiency improves, but adjustment time increases due to sequential testing

Engineering Contradiction:

Improveautomatic parameter adjustmentVSAvoidparameter determination time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary learning by collecting alignment mark images under various imaging conditions and pre-processing them into training datasets. This preliminary action enables the machine learning model to be trained in advance, so that during actual operation, parameter adjustment can be performed quickly without manual intervention, thus resolving the contradiction between detection accuracy and time consumption.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual mechanical adjustment process with an automated machine learning-based system. The machine learning model automatically determines optimal imaging parameters by learning from training data, substituting the manual operator's mechanical adjustment process. This substitution maintains high detection accuracy while dramatically reducing the time required for parameter adjustment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Manufacturing precision

If operator knowledge is required, then parameter optimization can be achieved, but operation complexity increases

Engineering Contradiction:

Improveparameter optimization qualityVSAvoidoperator knowledge requirement

Core Design Contradiction:

Manufacturing precisionVSEase of operation

Solution Approach 1:

The system enables self-service by allowing the machine learning model to automatically determine optimal imaging parameters without requiring operator expertise. The model learns from training data and autonomously selects the best parameters for detecting alignment marks under various conditions, eliminating the need for operators to possess specialized knowledge while maintaining high parameter optimization quality.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical adjustment process with an automated machine learning-based system. The machine learning model automatically determines optimal imaging parameters by learning from training data, substituting the manual operator's mechanical adjustment process. This substitution maintains high detection accuracy while dramatically reducing the time required for parameter adjustment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12481229B2Mark detecting apparatus, mark learning apparatus, substrate processing apparatus, mark detecting method, and manufacturing method of article

Publication Date: 2025.11.25 CANON KK

AI summary

A mark detecting apparatus includes an imaging unit configured to generate an alignment mark image by imaging of an alignment mark on an object, a detecting unit configured to detect the alignment mark in the alignment mark image, and an adjusting unit configured to adjust a parameter relating to the imaging, based on a learning model generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected. The adjusting unit acquires a second parameter as a result of inference processing based on the learning model. The imaging unit performs the imaging in a state where the parameter is adjusted to the second parameter.