Micron technology, inc. (20240185406). APPARATUSES AND METHODS FOR DETERMINING WAFER DEFECTS simplified abstract
Contents
APPARATUSES AND METHODS FOR DETERMINING WAFER DEFECTS
Organization Name
Inventor(s)
Dmitry Vengertsev of Boise ID (US)
Seth A. Eichmeyer of Boise ID (US)
APPARATUSES AND METHODS FOR DETERMINING WAFER DEFECTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240185406 titled 'APPARATUSES AND METHODS FOR DETERMINING WAFER DEFECTS
Simplified Explanation: The patent application describes an inspection system for identifying defects in semiconductor wafers using image capturing and deep neural networks.
- The system includes an image capturing device to capture a wafer image.
- A classification convolutional neural network (CNN) is used to determine the type of defect present in the captured image.
- An encoder converts training images into feature vectors, which are then clustered to generate soft labels for the images.
- A decoder re-generates the images from the feature vectors.
- A classification system determines the classification of defects in the training images.
- Both the encoder and decoder are formed from a CNN autoencoder.
- The system utilizes deep neural networks for classification and image reconstruction.
Potential Applications: This technology can be used in semiconductor fabrication facilities to automate the detection and classification of defects in wafers, improving quality control processes.
Problems Solved: The system addresses the challenge of efficiently and accurately identifying defects in semiconductor wafers, which is crucial for ensuring the quality of the final products.
Benefits: - Enhanced defect detection accuracy - Increased efficiency in quality control processes - Automation of defect classification tasks
Commercial Applications: The technology can be applied in semiconductor manufacturing industries for quality control, leading to improved product quality and reduced production costs.
Prior Art: Prior research has explored the use of deep learning techniques for defect detection in semiconductor manufacturing, but this specific combination of image capturing, clustering, and classification systems is a novel approach.
Frequently Updated Research: Ongoing research in the field of deep learning and computer vision may lead to advancements in defect detection systems for semiconductor fabrication.
Questions about Semiconductor Wafer Defect Detection: Question 1: How does the system handle different types of defects in semiconductor wafers? The system uses a classification CNN to determine the type of defect present in the captured image, with each class representing a specific defect.
Question 2: What are the advantages of using a CNN autoencoder for image reconstruction in this system? The CNN autoencoder is utilized for encoding and decoding training images into feature vectors, allowing for efficient clustering and soft label generation for defect classification.
Original Abstract Submitted
an inspection system for determining wafer defects in semiconductor fabrication may include an image capturing device to capture a wafer image and a classification convolutional neural network (cnn) to determine a classification from a plurality of classes for the captured image. each of the plurality of classes indicates a type of a defect in the wafer. the system may also include an encoder to encode to convert a training image into a feature vector; a cluster system to cluster the feature vector to generate soft labels for the training image; and a decoder to decode the feature vector into a re-generated image. the system may also include a classification system to determine a classification from the plurality of classes for the training image. the encoder and decoder may be formed from a cnn autoencoder. the classification cnn and the cnn autoencoder may each be a deep neural network.
