A voting-based ensemble feature network for semiconductor wafer defect classification
Abstract Semiconductor wafer defects severely affect product development. In order to reduce the occurrence of defects, it is necessary to identify why they occur, and it can be inferred by analyzing the patterns of defects. Automatic defect classification (ADC) is used to analyze large amounts of s...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-09-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-20630-9 |
_version_ | 1797998187439456256 |
---|---|
author | Sampa Misra Donggyu Kim Jongbeom Kim Woncheol Shin Chulhong Kim |
author_facet | Sampa Misra Donggyu Kim Jongbeom Kim Woncheol Shin Chulhong Kim |
author_sort | Sampa Misra |
collection | DOAJ |
description | Abstract Semiconductor wafer defects severely affect product development. In order to reduce the occurrence of defects, it is necessary to identify why they occur, and it can be inferred by analyzing the patterns of defects. Automatic defect classification (ADC) is used to analyze large amounts of samples. ADC can reduce human resource requirements for defect inspection and improve inspection quality. Although several ADC systems have been developed to identify and classify wafer surfaces, the conventional ML-based ADC methods use numerous image recognition features for defect classification and tend to be costly, inefficient, and time-consuming. Here, an ADC technique based on a deep ensemble feature framework (DEFF) is proposed that classifies different kinds of wafer surface damage automatically. DEFF has an ensemble feature network and the final decision network layer. The feature network learns features using multiple pre-trained convolutional neural network (CNN) models representing wafer defects and the ensemble features are computed by concatenating these features. The decision network layer decides the classification labels using the ensemble features. The classification performance is further enhanced by using a voting-based ensemble learning strategy in combination with the deep ensemble features. We show the efficacy of the proposed strategy using the real-world data from SK Hynix. |
first_indexed | 2024-04-11T10:44:42Z |
format | Article |
id | doaj.art-a5d23ec04edf45b6ac420579105fb4b2 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-11T10:44:42Z |
publishDate | 2022-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-a5d23ec04edf45b6ac420579105fb4b22022-12-22T04:29:06ZengNature PortfolioScientific Reports2045-23222022-09-0112111210.1038/s41598-022-20630-9A voting-based ensemble feature network for semiconductor wafer defect classificationSampa Misra0Donggyu Kim1Jongbeom Kim2Woncheol Shin3Chulhong Kim4Department of Convergence IT Engineering, Pohang University of Science and TechnologyDepartment of Convergence IT Engineering, Pohang University of Science and TechnologyDepartment of Convergence IT Engineering, Pohang University of Science and TechnologyNAND Data Science Team, SK HynixDepartment of Convergence IT Engineering, Pohang University of Science and TechnologyAbstract Semiconductor wafer defects severely affect product development. In order to reduce the occurrence of defects, it is necessary to identify why they occur, and it can be inferred by analyzing the patterns of defects. Automatic defect classification (ADC) is used to analyze large amounts of samples. ADC can reduce human resource requirements for defect inspection and improve inspection quality. Although several ADC systems have been developed to identify and classify wafer surfaces, the conventional ML-based ADC methods use numerous image recognition features for defect classification and tend to be costly, inefficient, and time-consuming. Here, an ADC technique based on a deep ensemble feature framework (DEFF) is proposed that classifies different kinds of wafer surface damage automatically. DEFF has an ensemble feature network and the final decision network layer. The feature network learns features using multiple pre-trained convolutional neural network (CNN) models representing wafer defects and the ensemble features are computed by concatenating these features. The decision network layer decides the classification labels using the ensemble features. The classification performance is further enhanced by using a voting-based ensemble learning strategy in combination with the deep ensemble features. We show the efficacy of the proposed strategy using the real-world data from SK Hynix.https://doi.org/10.1038/s41598-022-20630-9 |
spellingShingle | Sampa Misra Donggyu Kim Jongbeom Kim Woncheol Shin Chulhong Kim A voting-based ensemble feature network for semiconductor wafer defect classification Scientific Reports |
title | A voting-based ensemble feature network for semiconductor wafer defect classification |
title_full | A voting-based ensemble feature network for semiconductor wafer defect classification |
title_fullStr | A voting-based ensemble feature network for semiconductor wafer defect classification |
title_full_unstemmed | A voting-based ensemble feature network for semiconductor wafer defect classification |
title_short | A voting-based ensemble feature network for semiconductor wafer defect classification |
title_sort | voting based ensemble feature network for semiconductor wafer defect classification |
url | https://doi.org/10.1038/s41598-022-20630-9 |
work_keys_str_mv | AT sampamisra avotingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT donggyukim avotingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT jongbeomkim avotingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT woncheolshin avotingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT chulhongkim avotingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT sampamisra votingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT donggyukim votingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT jongbeomkim votingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT woncheolshin votingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification AT chulhongkim votingbasedensemblefeaturenetworkforsemiconductorwaferdefectclassification |