This work introduces a practical reinforcement learning (RL) techniques to address the complex scheduling challenges in producing Active Matrix Organic Light Emitting Diode displays. Specifically, we focus on autonomous optimization of the photolithography process, a critical bottleneck in the fabrication. This provides an outperforming scheduling method compared with the existing rule-based approach which requires diverse rules and engineer experience on adapting dynamic environments. Our purposing RL network was designed to make effective schedules aligning with layered structures of the planning and scheduling modules for mass production. In the training phase, historical production data is utilized to create a representative discrete event simulation environment. The RL agent, based on the Deep Q-Network, undergoes episodic training to learn optimal scheduling policies. To ensure safe and reliable scheduling decisions, we further introduce action filters and parallel competing schedulers. The performance of RL-based Scheduler (RLS) is compared to the Rule-Based Scheduler (RBS) over actual fabrication in a year-long period. Based on key performance indicators, we validate the RLS outperforms the RBS, with a remarkable improvement in step target matching, reduced setup times, and enhanced lot assignments. This work also paves a way for the gradual integration of AI-based algorithms into smart manufacturing practices.
{"title":"Practical Reinforcement Learning for Adaptive Photolithography Scheduler in Mass Production","authors":"Eungjin Kim;Taehyung Kim;Dongcheol Lee;Hyeongook Kim;Sehwan Kim;Jaewon Kim;Woosub Kim;Eunzi Kim;Younggil Jin;Tae-Eog Lee","doi":"10.1109/TSM.2023.3336909","DOIUrl":"https://doi.org/10.1109/TSM.2023.3336909","url":null,"abstract":"This work introduces a practical reinforcement learning (RL) techniques to address the complex scheduling challenges in producing Active Matrix Organic Light Emitting Diode displays. Specifically, we focus on autonomous optimization of the photolithography process, a critical bottleneck in the fabrication. This provides an outperforming scheduling method compared with the existing rule-based approach which requires diverse rules and engineer experience on adapting dynamic environments. Our purposing RL network was designed to make effective schedules aligning with layered structures of the planning and scheduling modules for mass production. In the training phase, historical production data is utilized to create a representative discrete event simulation environment. The RL agent, based on the Deep Q-Network, undergoes episodic training to learn optimal scheduling policies. To ensure safe and reliable scheduling decisions, we further introduce action filters and parallel competing schedulers. The performance of RL-based Scheduler (RLS) is compared to the Rule-Based Scheduler (RBS) over actual fabrication in a year-long period. Based on key performance indicators, we validate the RLS outperforms the RBS, with a remarkable improvement in step target matching, reduced setup times, and enhanced lot assignments. This work also paves a way for the gradual integration of AI-based algorithms into smart manufacturing practices.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"37 1","pages":"16-26"},"PeriodicalIF":2.7,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139695117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-15DOI: 10.1109/TSM.2023.3332630
Hsiu-Hui Hsiao;Kung-Jeng Wang
This paper addresses the quality control of the photolithography process in the semiconductor industry. Overlay errors in the process seriously affect the wafer yield, and cause the wafer to be forced to rework and affect the production efficiency of the equipment. We examine the current state of its process control, develop a novel overlay predict model, and verify the prediction results. This study proposes a Global Attention Generative Adversarial Networks (GAGAN) model to precisely predict the overlay error for the feed-forward data of the front layer, which is used as the important information and process parameters for the advanced process control of the current layer. Experiment results on a semiconductor shop-floor confirms that our proposed method achieves high predictive performance while maintaining extensibility and visual quality.
{"title":"GAGAN: Global Attention Generative Adversarial Networks for Semiconductor Advanced Process Control","authors":"Hsiu-Hui Hsiao;Kung-Jeng Wang","doi":"10.1109/TSM.2023.3332630","DOIUrl":"10.1109/TSM.2023.3332630","url":null,"abstract":"This paper addresses the quality control of the photolithography process in the semiconductor industry. Overlay errors in the process seriously affect the wafer yield, and cause the wafer to be forced to rework and affect the production efficiency of the equipment. We examine the current state of its process control, develop a novel overlay predict model, and verify the prediction results. This study proposes a Global Attention Generative Adversarial Networks (GAGAN) model to precisely predict the overlay error for the feed-forward data of the front layer, which is used as the important information and process parameters for the advanced process control of the current layer. Experiment results on a semiconductor shop-floor confirms that our proposed method achieves high predictive performance while maintaining extensibility and visual quality.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"37 1","pages":"115-123"},"PeriodicalIF":2.7,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135709787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-08DOI: 10.1109/TSM.2023.3329863
{"title":"2023 Index IEEE Transactions on Semiconductor Manufacturing Vol. 36","authors":"","doi":"10.1109/TSM.2023.3329863","DOIUrl":"10.1109/TSM.2023.3329863","url":null,"abstract":"","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"36 4","pages":"677-693"},"PeriodicalIF":2.7,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10312824","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135515206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.1109/TSM.2023.3325126
{"title":"IEEE Transactions on Semiconductor Manufacturing Information for Authors","authors":"","doi":"10.1109/TSM.2023.3325126","DOIUrl":"https://doi.org/10.1109/TSM.2023.3325126","url":null,"abstract":"","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"36 4","pages":"C3-C3"},"PeriodicalIF":2.7,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71903136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.1109/TSM.2023.3324270
{"title":"Special Issue on Semiconductor Design for Manufacturing (DFM)","authors":"","doi":"10.1109/TSM.2023.3324270","DOIUrl":"https://doi.org/10.1109/TSM.2023.3324270","url":null,"abstract":"","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"36 4","pages":"676-676"},"PeriodicalIF":2.7,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71903144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.1109/TSM.2023.3323254
Tsuyoshi Moriya
Since its beginning in 1992 in Japan, International Symposium on Semiconductor Manufacturing (ISSM) has provided unique opportunities to share the best practices of semiconductor manufacturing technologies for professionals. At the symposiums, semiconductor manufacturing professionals discussed the technologies developed to meet the worldwide requirements for advanced manufacturing. It is becoming crucial to re-examine semiconductor manufacturing in terms of fundamental principles to improve the performance of semiconductor devices. Moreover, utilizing artificial intelligence and machine learning technologies to improve semiconductor manufacturing have become a new challenge. These manufacturing technology challenges are showing the need for drastic revolutionary concept and stronger collaborative efforts to find solutions to the precompetitive challenges.
{"title":"Guest Editorial Special section on the 2022 International Symposium on Semiconductor Manufacturing","authors":"Tsuyoshi Moriya","doi":"10.1109/TSM.2023.3323254","DOIUrl":"https://doi.org/10.1109/TSM.2023.3323254","url":null,"abstract":"Since its beginning in 1992 in Japan, International Symposium on Semiconductor Manufacturing (ISSM) has provided unique opportunities to share the best practices of semiconductor manufacturing technologies for professionals. At the symposiums, semiconductor manufacturing professionals discussed the technologies developed to meet the worldwide requirements for advanced manufacturing. It is becoming crucial to re-examine semiconductor manufacturing in terms of fundamental principles to improve the performance of semiconductor devices. Moreover, utilizing artificial intelligence and machine learning technologies to improve semiconductor manufacturing have become a new challenge. These manufacturing technology challenges are showing the need for drastic revolutionary concept and stronger collaborative efforts to find solutions to the precompetitive challenges.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"36 4","pages":"499-500"},"PeriodicalIF":2.7,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71903143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.1109/TSM.2023.3324469
John W. Fowler;Karl Kempf;Lars Mönch
The increasing availability of data, advances in computational and storage capacities of IT systems, and algorithmic advances in Artificial Intelligence (AI), especially Machine Learning (ML) combine to enable significant improvements in the efficiency, operations and throughput of manufacturing systems at the production level. The semiconductor industry is one of the most data-intensive industries and has seen increased use of AI-based technologies over the last few years. In order to develop effective AI-based technologies in the semiconductor manufacturing industry several issues have to be taken into account, including scalability, heterogeneity of data, and the need for interpretability.
{"title":"Guest Editorial Special Section on Production-Level Artificial Intelligence Applications in Semiconductor Manufacturing","authors":"John W. Fowler;Karl Kempf;Lars Mönch","doi":"10.1109/TSM.2023.3324469","DOIUrl":"https://doi.org/10.1109/TSM.2023.3324469","url":null,"abstract":"The increasing availability of data, advances in computational and storage capacities of IT systems, and algorithmic advances in Artificial Intelligence (AI), especially Machine Learning (ML) combine to enable significant improvements in the efficiency, operations and throughput of manufacturing systems at the production level. The semiconductor industry is one of the most data-intensive industries and has seen increased use of AI-based technologies over the last few years. In order to develop effective AI-based technologies in the semiconductor manufacturing industry several issues have to be taken into account, including scalability, heterogeneity of data, and the need for interpretability.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"36 4","pages":"558-559"},"PeriodicalIF":2.7,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71903137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-26DOI: 10.1109/TSM.2023.3327767
Yang Liu;Lilei Hu;Bin Sun;Can Ma;Jingxuan Shen;Chang Chen
Single-image super-resolution (SISR) techniques have found wide applications in semiconductor defect inspection. Enhancing image resolution to improve inspection sensitivity and accuracy holds great significance. A novel SISR algorithm, called cross-convolutional residual network (CCRN), is proposed in this study. CCRN comprises a cross-convolutional module (CCM), which incorporates a cross-sharing mechanism that facilitates the fusion of features from different stages, enabling the extraction of more information from the image. Moreover, a global residual aggregation structure (GRA) is introduced. GRA captures and transfers different levels of residual features acquired from learning each CCM to the reconstruction layer. Experimental results demonstrate that the proposed SR algorithm outperforms existing state-of-the-art SR algorithms in terms of both visual and quantitative metrics when applied to optical, SEM, and TEM images of microfluidic chips, CMOS image sensors, and quantum dots, respectively. Additionally, CCRN significantly improves the accuracy of defect classification and inspection of unpatterned wafers, as evaluated using the WM-811K dataset. Notably, an increase in local defection testing accuracy from 79.00% to 89.00% and an improvement in classification accuracy from 93.69% to 96.06% are achieved. These findings underscore the potential applications of the proposed algorithm in improving semiconductor defect inspection and classification accuracies.
单图像超分辨率(SISR)技术已在半导体缺陷检测领域得到广泛应用。增强图像分辨率对提高检测灵敏度和准确性具有重要意义。本研究提出了一种名为交叉卷积残差网络(CCRN)的新型 SISR 算法。CCRN 包括一个交叉卷积模块(CCM),其中包含一个交叉共享机制,可促进不同阶段特征的融合,从而从图像中提取更多信息。此外,还引入了全局残差聚合结构(GRA)。GRA 可捕捉并将从学习每个 CCM 中获取的不同层次的残差特征传输到重建层。实验结果表明,当应用于微流控芯片、CMOS 图像传感器和量子点的光学、扫描电镜和 TEM 图像时,所提出的 SR 算法在视觉和定量指标方面都优于现有的一流 SR 算法。此外,在使用 WM-811K 数据集进行评估时,CCRN 显著提高了缺陷分类和无图案晶片检测的准确性。值得注意的是,局部缺陷检测准确率从 79.00% 提高到 89.00%,分类准确率从 93.69% 提高到 96.06%。这些发现强调了拟议算法在提高半导体缺陷检测和分类准确性方面的潜在应用。
{"title":"A Novel Multiscale Residual Aggregation Network-Based Image Super-Resolution Algorithm for Semiconductor Defect Inspection","authors":"Yang Liu;Lilei Hu;Bin Sun;Can Ma;Jingxuan Shen;Chang Chen","doi":"10.1109/TSM.2023.3327767","DOIUrl":"10.1109/TSM.2023.3327767","url":null,"abstract":"Single-image super-resolution (SISR) techniques have found wide applications in semiconductor defect inspection. Enhancing image resolution to improve inspection sensitivity and accuracy holds great significance. A novel SISR algorithm, called cross-convolutional residual network (CCRN), is proposed in this study. CCRN comprises a cross-convolutional module (CCM), which incorporates a cross-sharing mechanism that facilitates the fusion of features from different stages, enabling the extraction of more information from the image. Moreover, a global residual aggregation structure (GRA) is introduced. GRA captures and transfers different levels of residual features acquired from learning each CCM to the reconstruction layer. Experimental results demonstrate that the proposed SR algorithm outperforms existing state-of-the-art SR algorithms in terms of both visual and quantitative metrics when applied to optical, SEM, and TEM images of microfluidic chips, CMOS image sensors, and quantum dots, respectively. Additionally, CCRN significantly improves the accuracy of defect classification and inspection of unpatterned wafers, as evaluated using the WM-811K dataset. Notably, an increase in local defection testing accuracy from 79.00% to 89.00% and an improvement in classification accuracy from 93.69% to 96.06% are achieved. These findings underscore the potential applications of the proposed algorithm in improving semiconductor defect inspection and classification accuracies.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"37 1","pages":"93-102"},"PeriodicalIF":2.7,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134884005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}