Yuting Kong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuting Kong has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Dong Ni
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China
3 shared publications
Latest Publications
- 26 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 35 (1) , 40-49
A One-Shot Learning Approach for Similarity Retrieval of Wafer Bin Maps With Unknown Failure Pattern
Due to the increasing complexity of semiconductor manufacturing, new process failures occur and cause unknown types of defective patterns on wafer bin maps (WBMs). Similar patterns have a high probability of being induced by the identical process failure. The commonality analysis of unknown patterns can help to track down the new faults. To explore the similarity between defective WBMs, a retrieval method based on deep learning is adopted to detect WBMs with unknown failure patterns. Since there are few available WBMs with unknown patterns at the initial troubleshooting stage, more WBMs with unknown patterns are generated by morphology transformation. The deep retrieval model is trained by real and generated WBMs, which has a similar structure to the generative adversarial networks (GANs) and can create more WBMs to provide more information. Experiments on a real-world dataset have demonstrated that the proposed method has a high precision for measuring WBM similarity and retrieving similar unknown pattern wafers.
- 26 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 35 (1) , 40-49
A One-Shot Learning Approach for Similarity Retrieval of Wafer Bin Maps With Unknown Failure Pattern
Due to the increasing complexity of semiconductor manufacturing, new process failures occur and cause unknown types of defective patterns on wafer bin maps (WBMs). Similar patterns have a high probability of being induced by the identical process failure. The commonality analysis of unknown patterns can help to track down the new faults. To explore the similarity between defective WBMs, a retrieval method based on deep learning is adopted to detect WBMs with unknown failure patterns. Since there are few available WBMs with unknown patterns at the initial troubleshooting stage, more WBMs with unknown patterns are generated by morphology transformation. The deep retrieval model is trained by real and generated WBMs, which has a similar structure to the generative adversarial networks (GANs) and can create more WBMs to provide more information. Experiments on a real-world dataset have demonstrated that the proposed method has a high precision for measuring WBM similarity and retrieving similar unknown pattern wafers.
- 8 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 33 (4) , 578-586
Qualitative and Quantitative Analysis of Multi-Pattern Wafer Bin Maps
Wafer map analysis is one of the most critical steps for monitoring wafer quality and tracking failures in the semiconductor manufacturing process. Defective dies on wafer bin maps (WBMs) usually cluster into specific spatial patterns, which contain critical information for cause identification and yield improvement. Failures frequently arise due to the high complexity of production processes. Multiple patterns are likely to appear on one WBM. This paper proposes a qualitative and quantitative analysis approach for multi-pattern WBMs. The boundary detection method is proposed to locate and segment pattern groups at first. Then, the overlapped pattern unwrapping method is proposed to segment overlapped patterns. With two stages of segmentation, multi-pattern WBMs are separated into multiple single pattern WBMs. A convolutional neural network is introduced to determine the classes of patterns. After pattern segmentation and classification, the segmented single pattern WBMs will be remapped to the original multi-pattern WBMs, and the impacts of patterns are calculated. Our approach is validated with the real-world dataset, and the results demonstrate the proposed method has a good performance of qualitative and quantitative analysis for multi-pattern WBMs.
- 8 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 33 (4) , 578-586
Qualitative and Quantitative Analysis of Multi-Pattern Wafer Bin Maps
Wafer map analysis is one of the most critical steps for monitoring wafer quality and tracking failures in the semiconductor manufacturing process. Defective dies on wafer bin maps (WBMs) usually cluster into specific spatial patterns, which contain critical information for cause identification and yield improvement. Failures frequently arise due to the high complexity of production processes. Multiple patterns are likely to appear on one WBM. This paper proposes a qualitative and quantitative analysis approach for multi-pattern WBMs. The boundary detection method is proposed to locate and segment pattern groups at first. Then, the overlapped pattern unwrapping method is proposed to segment overlapped patterns. With two stages of segmentation, multi-pattern WBMs are separated into multiple single pattern WBMs. A convolutional neural network is introduced to determine the classes of patterns. After pattern segmentation and classification, the segmented single pattern WBMs will be remapped to the original multi-pattern WBMs, and the impacts of patterns are calculated. Our approach is validated with the real-world dataset, and the results demonstrate the proposed method has a good performance of qualitative and quantitative analysis for multi-pattern WBMs.
- 7 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 33 (1) , 62-71
A Semi-Supervised and Incremental Modeling Framework for Wafer Map Classification
Wafer map analysis provides critical information for quality control and yield improvement tasks in semiconductor manufacturing. In particular, wafer patterns of gross failing areas (GFA) are important clues to identify the causes of relevant failures during the manufacturing process. In this work, a semi-supervised classification framework is proposed for wafer map analysis, and its application to wafer bin maps with GFA patterns classification is demonstrated. The Ladder network and the semi-supervised variational autoencoder are adopted to classify wafer bin maps in comparison with a standard convolutional neural network (CNN) model on two real-world datasets. The results have illustrated that two semi-supervised models are consistently and substantially better than the CNN model across various training data percentages by effective utilization of the unlabeled data. Active learning and pseudo labeling are also utilized to accelerate the learning curve.
- 7 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Semiconductor Manufacturing
- Vol. 33 (1) , 62-71
A Semi-Supervised and Incremental Modeling Framework for Wafer Map Classification
Wafer map analysis provides critical information for quality control and yield improvement tasks in semiconductor manufacturing. In particular, wafer patterns of gross failing areas (GFA) are important clues to identify the causes of relevant failures during the manufacturing process. In this work, a semi-supervised classification framework is proposed for wafer map analysis, and its application to wafer bin maps with GFA patterns classification is demonstrated. The Ladder network and the semi-supervised variational autoencoder are adopted to classify wafer bin maps in comparison with a standard convolutional neural network (CNN) model on two real-world datasets. The results have illustrated that two semi-supervised models are consistently and substantially better than the CNN model across various training data percentages by effective utilization of the unlabeled data. Active learning and pseudo labeling are also utilized to accelerate the learning curve.