Automated Image Measurement for Semiconductor Process Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image measurement systems in semiconductor manufacturing fail to handle variations in images due to changes in manufacturing processes and imaging conditions, leading to erroneous or incomplete measurements, which require manual intervention by engineers, resulting in errors and inefficiencies.
Innovation Solution
An automated system using a trained machine learning model to classify images, select appropriate image processing algorithms, and preprocess images to enhance edge detection, allowing for accurate measurement of attributes without user intervention, and updating manufacturing parameters based on these measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a setup is created based on a first image to measure attributes of remaining images, then measurement automation is achieved, but measurement accuracy deteriorates when images have variations due to process and imaging condition changes
Solution Approach 1:
The system dynamically adapts the measurement setup by detecting variations in images and automatically adjusting measurement parameters and algorithms to match the specific characteristics of each image, transforming a static measurement approach into a dynamic one that maintains accuracy across varying conditions
Solution Approach 2:
The system changes measurement parameters based on detected image variations, including adjusting algorithm selection, preprocessing steps, and measurement thresholds according to the specific process and imaging conditions identified in each image
2Measurement precision
If manual measurement is performed by process engineers to handle image variations, then measurement accuracy is maintained, but time consumption and engineer workload increase significantly
Solution Approach 1:
The measurement system performs self-adjustment by automatically detecting image variations and modifying its own measurement approach without requiring engineer intervention, enabling the system to maintain accuracy while operating autonomously
Solution Approach 2:
The system incorporates feedback mechanisms where measurement results and image characteristics are continuously analyzed to automatically refine and adjust measurement parameters, creating a closed-loop system that maintains accuracy without manual input
3Device complexity
If a fixed measurement setup is used for all images, then device complexity is minimized, but adaptability to different process and imaging conditions deteriorates
Solution Approach 1:
The measurement system achieves multi-functionality by incorporating a library of measurement algorithms and preprocessing techniques that can be automatically selected based on image characteristics, allowing a single system to handle multiple types of variations without requiring separate dedicated setups for each condition
Data Source
AI summary
A method includes providing attributes of a manufacturing process and an image of a product associated with the manufacturing process to a trained machine learning model. The method further includes obtaining, from the trained machine learning model, predictive data. The method further includes determining, based on the predictive data, image measurements of the image of the product associated with the manufacturing process. Manufacturing parameters of the manufacturing process are to be updated based on the image measurements.