Ingot Crack Detection via Reflected Light Imaging

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for detecting cracks in semiconductor ingots and wafers are labor-intensive and costly, as they require visual inspection and struggle to distinguish internal cracks from the modified layer, especially when the crack shape is irregular.

Innovation Solution

An inspecting apparatus and method using a learned model based on machine learning to analyze images of the ingot's polished surface, employing a light source and imaging unit to capture reflected light, and a determining section to identify cracks through comparison with preset conditions, utilizing a cascade classifier or neural network to determine the presence of cracks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual inspection by operator is used to detect cracks, then detection accuracy can be maintained, but labor cost and inspection time increase significantly

Engineering Contradiction:

Improvecrack detection accuracyVSAvoidinspection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical visual inspection system (operator viewing) with an optical imaging system (camera photographing) combined with image processing. The imaging unit captures images of the ingot surface, and the determining section processes these images to detect cracks, thereby eliminating the need for manual visual inspection while maintaining detection capability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary image processing system between the light reflection and crack detection. The imaging unit captures reflected light patterns, and the determining section uses image processing algorithms to analyze these patterns and identify cracks, serving as an intermediary that translates optical information into detectable crack signatures.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Difficulty of detecting and measuring

If special camera is used to photograph internal cracks, then crack detection capability is improved, but device complexity and cost increase

Engineering Contradiction:

Improveinternal crack detection capabilityVSAvoidcamera system complexity

Core Design Contradiction:

Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

Instead of trying to directly image internal cracks from the front surface (which would require complex special cameras), the patent inverts the approach by using reflected light from the polished surface to indirectly detect cracks. The imaging unit photographs the reflected light pattern on the surface, and crack information is extracted from these reflection patterns, effectively detecting internal cracks through surface optical signatures.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The patent creates an optical copy or signature of the internal crack structure on the surface through reflected light. The imaging unit captures this optical signature (reflected light pattern), and the determining section analyzes it to infer the presence and characteristics of internal cracks, thereby detecting internal defects without directly imaging them.

Inventive Principle:

Principle #26Copying

3Device complexity

If threshold-based method is used to determine cracks from images, then processing simplicity is maintained, but detection accuracy decreases for irregular crack shapes

Engineering Contradiction:

Improveprocessing method simplicityVSAvoidirregular crack detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent transitions from a static threshold-based determination method to a dynamic image processing approach. The determining section uses adaptive image processing algorithms that can dynamically adjust to different crack patterns and shapes, rather than relying on fixed threshold values. This allows the system to accurately detect irregular crack shapes by analyzing image features and patterns rather than simple intensity thresholds.

Inventive Principle:

Principle #15Dynamics

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution enables efficient detection of cracks in ingots and wafers, reducing labor and costs by automating the inspection process and accurately identifying irregular crack shapes.

Implementation Method 1

an imaging unit configured to condense and photograph reflected light reflected by the polished surface of the semiconductor ingot

Methodology Applied

Scientific EffectReflection: Reflection

Data Source

PatentUS20230075359A1Inspecting apparatus, peeling apparatus, and learned model generating method

Publication Date: 2023.03.09 DISCO CORP

AI summary

An inspecting apparatus for inspecting an ingot having a polished surface includes a holding table configured to hold the ingot with the polished surface of the ingot exposed, a light source configured to irradiate the polished surface of the ingot held by the holding table with light at a predetermined incidence angle, an imaging unit configured to condense and photograph reflected light reflected by the polished surface of the ingot, and form a photographed image emphasizing unevenness produced on the polished surface by a crack extending in the ingot, and a control unit including a determining section configured to determine the state of the ingot by comparing the formed photographed image with a preset condition.