請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85168完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 藍俊宏 | zh_TW |
| dc.contributor.advisor | Jakey Blue | en |
| dc.contributor.author | 李冠德 | zh_TW |
| dc.contributor.author | Kuan-Te Lee | en |
| dc.date.accessioned | 2023-03-19T22:47:51Z | - |
| dc.date.available | 2023-11-10 | - |
| dc.date.copyright | 2022-08-12 | - |
| dc.date.issued | 2022 | - |
| dc.date.submitted | 2002-01-01 | - |
| dc.identifier.citation | Baek, J. Y. and Spanos, C. J. (2013). Performance evaluation of blended metrology schemes incorporating virtual metrology. IEEE transactions on semiconductor manufacturing, 26(4):506–515.
Bai, S., Kolter, J. Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2013). Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203. Butler, S. W. and Stefani, J. A. (1994). Supervisory run-to-run control of polysilicon gate etch using in situ ellipsometry. IEEE Transactions on Semiconductor Manufacturing, 7(2):193–201. Cai, H., Feng, J., Yang, Q., Li, W., Li, X., and Lee, J. (2020). A virtual metrology method with prediction uncertainty based on gaussian process for chemical mechanical planarization. Computers in Industry, 119:103228. Chen, C.-H., Zhao, W.-D., Pang, T., and Lin, Y.-Z. (2020). Virtual metrology of semiconductor pvd process based on combination of tree-based ensemble model. Isa Transactions, 103:192–202. Chen, P., Wu, S., Lin, J., Ko, F., Lo, H., Wang, J., Yu, C., and Liang, M. (2005). Virtual metrology: A solution for wafer to wafer advanced process control. In ISSM 2005, IEEE International Symposium on Semiconductor Manufacturing, 2005., pages 155–157. IEEE. Chen, Y.-T., Yang, H.-C., and Cheng, F.-T. (2006). Multivariate simulation assessment for virtual metrology. In Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., pages 1048–1053. IEEE. Chien, C.-F., Wang, W.-C., and Cheng, J.-C. (2007). Data mining for yield enhancement in semiconductor manufacturing and an empirical study. Expert Systems with Applications, 33(1):192–198. Defferrard, M., Bresson, X., and Vandergheynst, P. (2016). Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29. Del Castillo, E. and Hurwitz, A. M. (1997). Run-to-run process control: Literature review and extensions. Journal of Quality Technology, 29(2):184–196. Dreyfus, P.-A., Psarommatis, F., May, G., and Kiritsis, D. (2022). Virtual metrology as an approach for product quality estimation in industry 4.0: a systematic review and integrative conceptual framework. International Journal of Production Research, 60(2):742–765. Evans, C., Paul, E., Dornfeld, D., Lucca, D., Byrne, G., Tricard, M., Klocke, F., Dambon, O., and Mullany, B. (2003). Material removal mechanisms in lapping and polishing. CIRP annals, 52(2):611–633. Fan, S.-K. S., Hsu, C.-Y., Tsai, D.-M., He, F., and Cheng, C.-C. (2020). Data-driven approach for fault detection and diagnostic in semiconductor manufacturing. IEEE Transactions on Automation Science and Engineering, 17(4):1925–1936. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. Hirai, T., Hazama, K., and Kano, M. (2014). Application of locally weighted partial least squares to design of semiconductor virtual metrology. In 2014 IEEE Conference on Control Applications (CCA), pages 1771–1776. IEEE. Hirai, T. and Kano, M. (2015). Adaptive virtual metrology design for semiconductor dry etching process through locally weighted partial least squares. IEEE Transactions on Semiconductor Manufacturing, 28(2):137–144. Jia, X., Di, Y., Feng, J., Yang, Q., Dai, H., and Lee, J. (2018). Adaptive virtual metrology for semiconductor chemical mechanical planarization process using gmdh-type polynomial neural networks. Journal of Process Control, 62:44–54. Joe Qin, S. (2003). Statistical process monitoring: basics and beyond. Journal of Chemometrics: A Journal of the Chemometrics Society, 17(8-9):480–502. Kang, P., Lee, H.-j., Cho, S., Kim, D., Park, J., Park, C.-K., and Doh, S. (2009). A virtual metrology system for semiconductor manufacturing. Expert Systems with Applications, 36(10):12554–12561. Kim, E., Cho, S., Lee, B., and Cho, M. (2019). Fault detection and diagnosis using self-attentive convolutional neural networks for variable-length sensor data in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 32(3):302–309. Kipf, T. N. and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25. LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324. Lenz, B., Barak, B., Mührwald, J., and Leicht, C. (2013). Virtual metrology in semiconductor manufacturing by means of predictive machine learning models. In 2013 12th International Conference on Machine Learning and Applications, volume 2, pages 174–177. IEEE. Leuven (2010). Classification analysis on metallic contamination in semi-conductor manufacturing industry. https://blog.associatie.kuleuven.be/danhuayao/introduction-of-the-metallic-contamination/. Li, Z. and Wu, D. (2018). A data-driven approach to material removal rate prediction in chemical mechanical polishing. In Annual Conference of the PHM Society, volume 10. Li, Z., Wu, D., and Yu, T. (2019). Prediction of material removal rate for chemical mechanical planarization using decision tree-based ensemble learning. Journal of Manufacturing Science and Engineering, 141(3). Lin, T.-H., Hung, M.-H., Lin, R.-C., and Cheng, F.-T. (2006). A virtual metrology scheme for predicting cvd thickness in semiconductor manufacturing. In Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., pages 1054–1059. IEEE. Liu, K., Chen, Y., Zhang, T., Tian, S., and Zhang, X. (2018). A survey of run-to-run control for batch processes. ISA transactions, 83:107–125. Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30. Luo, J. and Dornfeld, D. A. (2001). Material removal mechanism in chemical mechanical polishing: theory and modeling. IEEE transactions on semiconductor manufacturing, 14(2):112–133. Moyne, J., Del Castillo, E., and Hurwitz, A. M. (2018). Run-to-run control in semiconductor manufacturing. CRC press. Munirathinam, S. and Ramadoss, B. (2014). Big data predictive analtyics for proactive semiconductor equipment maintenance. In 2014 IEEE International Conference on Big Data (Big Data), pages 893–902. IEEE. PHM (2016). Phm data challenge 2016. https://www.phmsociety.org/events/conference/phm/16/data-challenge. Psarommatis, F., Prouvost, S., May, G., and Kiritsis, D. (2020). Product quality improvement policies in industry 4.0: characteristics, enabling factors, barriers, and evolution toward zero defect manufacturing. Frontiers in Computer Science, 2:26. Purwins, H., Barak, B., Nagi, A., Engel, R., Höckele, U., Kyek, A., Cherla, S., Lenz, B., Pfeifer, G., and Weinzierl, K. (2013). Regression methods for virtual metrology of layer thickness in chemical vapor deposition. IEEE/ASME Transactions on Mechatronics, 19(1):1–8. Rostami, H., Blue, J., and Yugma, C. (2016). Equipment condition diagnosis and fault fingerprint extraction in semiconductor manufacturing. In 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 534–539. IEEE. Runnels, S. R. and Eyman, L. M. (1994). Tribology analysis of chemical-mechanical polishing. Journal of the Electrochemical Society, 141(6):1698. Samek, W., Wiegand, T., and Müller, K.-R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296. Sharma, D., Armer, H., and Moyne, J. (2012). A comparison of data mining methods for yield modeling, chamber matching and virtual metrology applications. In 2012 SEMI Advanced Semiconductor Manufacturing Conference, pages 231–236. IEEE. Shrikumar, A., Greenside, P., and Kundaje, A. (2017). Learning important features through propagating activation differences. In International conference on machine learning, pages 3145–3153. PMLR. Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Stoddard, K., Crouch, P., Kozicki, M., and Tsakalis, K. (1994). Application of feedforward and adaptive feedback control to semiconductor device manufacturing. In Proceedings of 1994 American Control Conference-ACC’94, volume 1, pages 892–896. IEEE. Su, Y.-C., Lin, T.-H., Cheng, F.-T., and Wu, W.-M. (2008). Accuracy and real-time considerations for implementing various virtual metrology algorithms. IEEE Transactions on Semiconductor Manufacturing, 21(3):426–434. Suthar, K., Shah, D., Wang, J., and He, Q. P. (2019). Next-generation virtual metrology for semiconductor manufacturing: A feature-based framework. Computers & Chemical Engineering, 127:140–149. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9. Terzi, M., Masiero, C., Beghi, A., Maggipinto, M., and Susto, G. A. (2017). Deep learning for virtual metrology: Modeling with optical emission spectroscopy data. In 2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI), pages 1–6. IEEE. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903. Wang, P., Gao, R. X., and Yan, R. (2017). A deep learning-based approach to material removal rate prediction in polishing. CIRP Annals, 66(1):429–432. Wang, Z. and Oates, T. (2015). Imaging time-series to improve classification and imputation. In Twenty-Fourth International Joint Conference on Artificial Intelligence. Yang, H.-C., Adnan, M., Huang, C.-H., Cheng, F.-T., Lo, Y.-L., and Hsu, C.-H. (2019). An intelligent metrology architecture with avm for metal additive manufacturing. IEEE Robotics and Automation Letters, 4(3):2886–2893. Yugma, C., Blue, J., Dauzère-Pérès, S., and Obeid, A. (2015). Integration of scheduling and advanced process control in semiconductor manufacturing: review and outlook. Journal of Scheduling, 18(2):195–205. Yung-Cheng, J. C. and Cheng, F.-T. (2005). Application development of virtual metrology in semiconductor industry. In 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005., pages 6–pp. IEEE. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85168 | - |
| dc.description.abstract | 因應市場高度需求，半導體製程的發展速度已經演進到超越摩爾 (More Than Morre) 的世代。為了有效應對更複雜製程設計，先進的製程控管技術已經是製造商不可或缺的基本能力。如今，半導體製造通常由數千道製程所組成，每道製程步驟都有特定的品質標準，而做完關鍵製程之後，品質量測是評估製程能力的基本且必要手段。因為製程愈趨精密，單片晶圓的測量時間亦越來越長，致使大量抽測已不符合生管標準，因此使虛擬量測模型成為更受重視的技術。
虛擬量測系統旨在利用錯誤偵測與分類 (Fault Detection and Classification, FDC) 資料預測晶圓的量測值，使每片晶圓都有相對的量測品質能被即時監控，而藉由模型預測可同時保持製程效率。回顧過往的虛擬量測相關文獻，在面對處理多變量時間序列的 FDC 資料時，主流方法是先利用領域知識從 FDC 資料中萃取出物理或統計特徵，然而過於主觀的特徵萃取與轉換會丟失大量的潛在資訊，使得模型準確度無法進一步提升，同時也容易失去製程變數和輸出測量值之間的連結。因此本研究提出了一整合卷積神經網路與圖神經網路的虛擬量測模型，並進一步發展此模型背後的可解釋性。 首先使用一維卷積層加強資料的時間特性，並經由圖神經網路萃取變數之間的交互作用關係，最後透過二維卷積與全連接層神經網路預測量測結果。為針對工業機台之特性進行可解釋性之設計，利用 DeepSHAP 演算法剖析模型的決策邏輯與各個製程變數對量測結果之影響，另外透過圖神經網路訓練的圖結構可以了解製程變數之間的交互作用關係。此外，在研究過程中發現使用相關矩陣 (correlation matrix) 來近似真實圖結構的可行性，在模型訓練最佳化的過程中取得變數之間的真實交互作用關係，發展出同時兼具準確度與解釋性之虛擬量測模型。 本研究以 2016 PHM Data Challenge 之半導體化學機械研磨製程公開資料進行案例分析，將本研究提出之模型預測結果與當前國際學術研究成果進行比較，目前在預測準確度方面與最佳結果相近，惟本研究提出之模型具有泛化與可解釋性之優勢。 | zh_TW |
| dc.description.abstract | In response to the urgent demand of the consumer market, the semiconductor technology node has evolved to the More Than Moore generation. In order to effectively deal with more complex process designs, advanced process control technology has become an indispensable capability for IC makers. Nowadays, semiconductor manufacturing usually consists of thousands of operations that have specific quality standards. After processing the critical operations, quality inspection is a basic and necessary manner to evaluate process capability. Due to the more and more complex design, the measuring time of a single wafer is getting longer and longer, making it impossible to do a full-spectrum inspection. As a result, virtual metrology is coming to the center of the stage.
Virtual Metrology (VM) system is designed to predict the measurements of a wafer by using Fault Detection and Classification (FDC) data, such that the relative wafer quality can be monitored in real-time. FDC data are collected in the format of multivariate time series per wafer. In reviewing the recent literature related to VM, the mainstream usually starts by using domain knowledge to extract physical or statistical features from FDC data. However, subjective feature extraction and conversion often lead to information loss or distortion. Not to mention the link between process variables and output measurements can be broken. Therefore, this study proposes a 1-2D CNN-based VM model integrating the convolutional neural network and graph neural network, and further develops the interpretability of this model. We first use the 1D convolutional layer to enhance the temporal information. The interactions among variables are extracted through a Graph Neural Network (GNN). Finally, the measurements are predicted through the 2D convolutional layer and fully connected neural network. In order to interpret the VM model, DeepSHAP algorithm is employed to infer the decision logic and the importance of process variables. In addition, the trained graph structure can be used to understand the interactions among variables. It can be regarded as a model that combines prediction accuracy and explainability at the same time. The 2016 PHM Data Challenge open dataset on the chemical mechanical polishing process is used for the case study. The performance of the proposed VM model is compared with that on the leaderboard. Our accuracy is close to the best ones, and the proposed model has the advantages of generalization and explainability. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:47:51Z (GMT). No. of bitstreams: 1 U0001-0808202213531800.pdf: 8998039 bytes, checksum: 9e2a0082e94bc57a9d1606d8df5ea2da (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 口試委員審定書 i
摘要 ii Abstract iii 目錄 v 圖目錄 vii 表目錄 ix 第一章 緒論 1 1.1 研究背景 1 1.2 動機與目的 3 1.3 研究架構 5 第二章 文獻回顧 6 2.1 先進製程控制 6 2.1.1 錯誤偵測與分類 9 2.1.2 虛擬量測模型 10 2.2 卷積神經網路 12 2.2.1 卷積層 12 2.2.2 池化層 15 2.2.3 全連接層 15 2.3 圖神經網路 16 2.3.1 圖的基本原則和符號 16 2.3.2 頻譜法 (Spectral methods) 17 2.3.3 空間法 (Spatial methods) 19 2.4 可解釋性演算法 22 2.4.1 DeepLIFT 22 2.4.2 SHAP 25 2.4.3 Deep SHAP 26 第三章 研究方法 28 3.1 資料格式與資料前處理 29 3.2 輸入層與一維卷積層 31 3.3 圖交互作用層 32 3.4 二維卷積層與全連接層 33 3.5 可解釋性推論 34 第四章 案例分析與討論 36 4.1 資料集說明 36 4.2 資料前處理 38 4.3 模型建立 41 4.4 標竿模型 42 4.4.1 物理模型 42 4.4.2 資料驅動模型 43 4.4.3 相關文獻模型 44 4.5 模型預測結果評比 47 4.6 解釋性推論結果 50 4.6.1 SHAP 貢獻值 50 4.6.2 圖交互作用 53 第五章 結論與未來展望 58 5.1 研究結論 58 5.2 未來展望 59 參考文獻 60 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 可釋性人工智慧 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 錯誤偵測與分類 | zh_TW |
| dc.subject | 虛擬量測 | zh_TW |
| dc.subject | 圖神經網路 | zh_TW |
| dc.subject | Explainable AI (XAI) | en |
| dc.subject | Virtual Metrology (VM) | en |
| dc.subject | Fault Detection and Classification (FDC) | en |
| dc.subject | Convolutional Neural Networks (CNN) | en |
| dc.subject | Graph Neural Network (GNN) | en |
| dc.title | 單維轉二維卷積神經網路虛擬量測模型及其可釋性發展 | zh_TW |
| dc.title | 1-2D CNN-based Virtual Metrology Model and Its Explainability | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 110-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 楊惟婷;許嘉裕 | zh_TW |
| dc.contributor.oralexamcommittee | Wei-Ting Yang;Chia-Yu Hsu | en |
| dc.subject.keyword | 虛擬量測,錯誤偵測與分類,卷積神經網路,圖神經網路,可釋性人工智慧, | zh_TW |
| dc.subject.keyword | Virtual Metrology (VM),Fault Detection and Classification (FDC),Convolutional Neural Networks (CNN),Graph Neural Network (GNN),Explainable AI (XAI), | en |
| dc.relation.page | 65 | - |
| dc.identifier.doi | 10.6342/NTU202202143 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2022-08-08 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 工業工程學研究所 | - |
| dc.date.embargo-lift | 2027-08-08 | - |
| 顯示於系所單位： | 工業工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-110-2.pdf 未授權公開取用 | 8.79 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。