Single-Crystal Wafer Cutting Paths Using Image Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual cutting of semiconductor wafers results in material waste, cutting errors, and health hazards due to manual instability and exposure to heavy metals, necessitating an automated and precise cutting path planning method.

Innovation Solution

A cutting path planning algorithm using image processing to identify single crystal regions, plan the largest inscribed rectangle, and determine optimal cutting lines to automate the cutting process, ensuring maximum retention of single crystal areas while minimizing heterocrystal removal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual cutting method is used to remove heterocrystal regions, then the single crystal part can be retained, but material waste increases and cutting precision decreases

Engineering Contradiction:

Improvecutting precisionVSAvoidmaterial waste

Core Design Contradiction:

Manufacturing precisionVSLoss of substance

Solution Approach 1:

The patent replaces manual mechanical cutting with an automated image processing system that uses computer vision to identify crystal regions and algorithms to plan optimal cutting paths, eliminating manual instability and improving both precision and material utilization

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the cutting process from manual operation to automated control by changing the operational parameters from human judgment to algorithmic decision-making based on image analysis, enabling precise identification of heterocrystal boundaries and optimization of cutting paths to maximize single crystal retention

Inventive Principle:

Principle #35Parameter changes

2Productivity

If manual cutting operation is performed, then the cutting process can be completed, but operator health is harmed due to heavy metal inhalation

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidhealth hazards

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent replaces manual cutting operations with an automated system that performs image acquisition, processing, and cutting path planning through computer algorithms, completely eliminating operator exposure to heavy metal particles and health hazards while maintaining high processing efficiency

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the image processing algorithm independently identifies crystal regions, plans cutting paths, and guides the cutting process without human intervention, thereby protecting operators from health risks while improving productivity

Inventive Principle:

Principle #25Self-service

3Reliability

If manual boundary identification is used, then the single crystal regions can be identified, but human resources are wasted and operational stability decreases

Engineering Contradiction:

Improveoperational stabilityVSAvoidprocessing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces manual boundary identification with an automated image processing system that uses deep learning models and contour detection algorithms to accurately identify single crystal regions, eliminating human resource consumption and operational instability while managing processing complexity through systematic algorithm design

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12373933B2Cutting path planning algorithm for semiconductor workpiece based on image processing

Publication Date: 2025.07.29 TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

AI summary

A cutting path planning algorithm for semiconductor workpiece based on image processing is provided, including the following steps: 1, obtaining a semantic boundary of an image; 2, finding a largest inscribed rectangle MRect in the single crystal image X1; 3. dividing the contour region in the single crystal region to find the corresponding cutting line; and 4. determining the final cutting line.