A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition
2021
IEEE Access
Preserved Fulltext
They trained an ensemble of six DBNs for six classes of defects in the real wafer map data and tested it on the wafers having single and mixed type defects. ...
Byun and Baek [45] used a CAE to initialize CNN weights. The model was trained on single-type defect map data and tested on the combination of single and mixed type patterns. ...
doi:10.1109/access.2021.3106171
fatcat:tjpdwnv4wzhi3fbaelpo7ewewy
Efficient Mixed-Type Wafer Defect Pattern Recognition Using Compact Deformable Convolutional Transformers
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2303.13827v1 fatcat:vhjyecw5n5fexo6yxufgiq2sla
Mixed-type DPR is much more complicated compared to single-type DPR due to varied spatial features, the uncertainty of defects, and the number of defects present. ...
Defect Pattern Recognition (DPR) of wafer maps is crucial to find the root cause of the issue and further improving the yield in the wafer foundry. ...
Therefore, we resize all wafer images to 52×52. The wafer maps are classified into 38 categories based on the type and number of defects present in a wafer map. ...
arXiv:2303.13827v2
fatcat:ukisb4yplrb3foyockim7uysiy
Improved U-Net with Residual Attention Block for Mixed-Defect Wafer Maps
2022
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
By using the proposed method, we can extract an improved feature map by suppressing irrelevant features and paying attention to the defect to be found. ...
In particular, because mixed defects have become more likely with the development of technology, finding them has become more complex than can be performed by conventional wafer defect detection. ...
Therefore, accurately classifying the defect patterns on the wafer map allows defect sources from the manufacturing process to be identified. ...
doi:10.3390/app12042209
fatcat:qtompcmagfdevl2gqfnizuck5y
Mixed-Type Wafer Classification For Low Memory Devices Using Knowledge Distillation
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2303.13974v1 fatcat:36jvnbfssfgtjh4imtli3egttu
Identifying multiple defects in a wafer is generally harder compared to identifying a single defect. Recently, deep learning methods have gained significant traction in mixed-type DPR. ...
Defect Pattern Recognition (DPR) of wafer maps is crucial for determining the root cause of production defects, which may further provide insight for yield improvement in wafer foundry. ...
The 13 mixed defect patterns from C10-C22 belong to wafers with 2 single-type defects on them, while the 12 mixed defect patterns identified as C23 through C34 belong to wafers with 3 single-type defects ...
arXiv:2303.13974v2
fatcat:aju7xu2gajgl7h73rumqg5rqxe
Defects Recognition on Wafer Maps Using Multilayer Feed-Forward Neural Network
[chapter]
2020
Frontiers in Artificial Intelligence and Applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The neural network classifies wafer-defect maps into classes. Each class represents certain defect on the map. ...
The neural network was trained, tested and validated using a wafer-defect maps dataset containing real defects inspired from manufacturing process. ...
Single and mixed defects patterns using deep machine learning based approach were studied by [7] . ...
doi:10.3233/faia200828
fatcat:anv4zjunlzg7jgcmlm2n6qn7py
A Fast Postprocessing Algorithm for the Overlapping Problem in Wafer Map Detection
2021
Journal of Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Mixed defects have become increasingly popular in defect detection and one of the hottest research areas in wafer maps. ...
Postprocessing methods used to solve the overlapping problem in mass mixed defects have a poor detection speed, which is insufficient for rapid defect detection. ...
Kyeong and Kim [1] applied CNNs to classify mixed defect patterns of wafer maps and established a separate model for each single defect pattern (whether there is a corresponding model when multiple defect ...
doi:10.1155/2021/2682286
fatcat:bf2mo4jl6va4hampjo3u3tfuou
Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In the early stages, research has been conducted to extract features from wafer maps and classify defective patterns using machine learning techniques. ...
Moreover, Kyeong and Kim [28] proposed a CNN-based classification model to classify mixed-type defect patterns in wafer bin maps separately for each pattern circle, ring, scratch, and zone. ...
doi:10.1109/access.2021.3068378
fatcat:c2ilj27vb5g5dkup6irawlufxa
WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects
2022
Computers in industry (Print)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2207.00960v1 fatcat:2sllx5daajabxe7qsajh2fpvja
WSCN performs simultaneous classification and segmentation of both single and mixed-type wafer defects. ...
For analyzing mixed-type defects, some previous works require separately training one model for each defect type, which is non-scalable. ...
This has also led to mixed-type defects, where two or more defect patterns exist in a single wafer. ...
doi:10.1016/j.compind.2022.103720
fatcat:yb4qyxc5pvcgrg2b4us5l3l7my
A Unified Defect Pattern Analysis of Wafer Maps Using Density-Based Clustering
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Wafer maps with global defects are generated through Bernoulli trials. We assume that a single wafer map contains 400 chips and the distance between two adjacent chips is set to 1. ...
., an ability to identify simultaneously occurred several defect patterns on a single wafer map and arbitrary shaped clustered patterns such as a ring. ...
doi:10.1109/access.2021.3084221
fatcat:elc46ymk2rbmzdeyuxktmp2ekm
Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
By tuning parameters implemented on it, quantum circuit driven by our framework learns a given DLDR task, include of wafer defect map classification, defect pattern classification, and hotspot detection ...
These results can be used to build a future roadmap to develop circuit-based quantum deep learning for semiconductor defect detection. ...
The wafer maps with a single pattern or nonoverlapping mixed-type pattern were segmented into single pattern maps and then classified by a CNN. ...
arXiv:2208.03514v1
fatcat:ljhlmamirzg45efqvyeoxr2xxe
Efficient Convolutional Neural Networks for Semiconductor Wafer Bin Map Classification
2023
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
The defect patterns shown on the wafer map provide information about the process and equipment in which the defect occurred, but automating pattern classification is difficult to apply to actual manufacturing ...
The purpose of this study was to classify these defect patterns with a small amount of resources and time. ...
That way, even images of mixed types will be classified. Figure 1 . 1 Figure 1. Wafer bin map defect patterns. Green areas are normal chips and yellow areas are defective chips. ...
doi:10.3390/s23041926
pmid:36850523
pmcid:PMC9960339
fatcat:aq3jc36bw5bdzhttsa4tyabbaa
Deep Learning-Based Defect Classification and Detection in SEM Images
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
2022
Metrology, Inspection, and Process Control XXXVI
unpublished
doi:10.1117/12.2622550 fatcat:iaiaibybabgq3pvdphnnv33nlm
doi:10.1117/12.2622550 fatcat:iaiaibybabgq3pvdphnnv33nlm
This proposes a novel ensemble deep learning-based model to accurately classify, detect and localize different defect categories for aggressive pitches and thin resists (High NA applications).In particular ...
In this work we have developed a novel robust supervised deep learning training scheme to accurately classify as well as localize different defect types in SEM images with high degree of accuracy. ...
In this paper, the authors proposed CNN and XGBoost techniques to retrieve wafer maps and to classify the defect patterns. ...
arXiv:2206.13505v1
fatcat:fhihnbaizbaznlvssb3uvvblji
Inspection and Classification of Semiconductor Wafer Surface Defects Using CNN Deep Learning Networks
2020
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper presents a vision-based machine-learning-based method to classify visible surface defects on semiconductor wafers. ...
Its performance in wafer-defect classification shows superior performance compared to other machine-learning methods investigated in the experiments. ...
Type-C defects vary from wafer to wafer. This type of defect is the most common occurrence in semiconductor manufacturing. ...
doi:10.3390/app10155340
fatcat:xbbyqrlb5ngl3hduyiiqm66wva
A Wafer Bin Map "Relaxed" Clustering Algorithm for Improving Semiconductor Production Yield
2020
Open Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In particular, Wafer Bin Maps (WBMs) presenting specific fault models provide crucial information to keep track of process problems in semiconductor manufacturing. ...
This study proposes a network-based data mining approach, which integrates correlation graphs with clustering analysis to quickly extract patterns from WBMs and then bind them to manufacturing defects. ...
Mixed defects: they are made of random and systematic defects [21] (last pattern in Figure 4 ): most wafers have maps of this type. ...
doi:10.1515/comp-2020-0175
fatcat:o4htqzb2rvb2rlsmbgzuqswxsm
2019 Index IEEE Transactions on Semiconductor Manufacturing Vol. 32
2019
IEEE transactions on semiconductor manufacturing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Voting Ensemble Classifier for Wafer Map Defect Patterns Identification in Semiconductor Manufacturing. ...
., +, TSM Feb. 2019 39-47
A Voting Ensemble Classifier for Wafer Map Defect Patterns Identification
in Semiconductor Manufacturing. ...
Profitability A Productivity-Oriented Wafer Map Optimization Using Yield Model Based on Machine Learning. ...
doi:10.1109/tsm.2019.2958442
fatcat:e276xgw6gbbdlc4fy2ldbrd4py
« Previous
Showing results 1 — 15 out of 1,379 results