請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84875完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李家岩 | zh_TW |
| dc.contributor.advisor | Chia-Yen Lee | en |
| dc.contributor.author | 宋亭遠 | zh_TW |
| dc.contributor.author | Ting-Yuan Song | en |
| dc.date.accessioned | 2023-03-19T22:30:16Z | - |
| dc.date.available | 2023-12-27 | - |
| dc.date.copyright | 2022-09-05 | - |
| dc.date.issued | 2022 | - |
| dc.date.submitted | 2002-01-01 | - |
| dc.identifier.citation | Al-Tahan, H. (2021). Contrastive Learning of Auditory Representations. Bank, T. W. (Accessed on 2022/07/02). Manufacturing, value added. https://data.worldbank.org/indicator/NV.IND.MANF.CD?end=2021&start=2011&view=chart Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16-28. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research. https://proceedings.mlr.press/v119/chen20j.html Chen, X., Fan, H., Girshick, R., & He, K. (2020). Improved Baselines with Momentum Contrastive Learning. arXiv:2003.04297. Retrieved March 01, 2020, from https://ui.adsabs.harvard.edu/abs/2020arXiv200304297C Cheng, Z., Zou, C., & Dong, J. (2019). Outlier detection using isolation forest and local outlier factor. Proceedings of the conference on research in adaptive and convergent systems, Deng, Y. R. X. Z. P. L. Y. W. R. (2019). A Survey of Predictive Maintenance Systems, Purposes and Approaches. IEEE COMMUNICATIONS SURVEYS & TUTORIALS. Hocking, R. R. (1976). The analysis and selection of variables in linear regression. Javed, K., Gouriveau, R., Zerhouni, N., & Nectoux, P. (2015). Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics. IEEE Transactions on Industrial Electronics, 62(1), 647-656. https://doi.org/10.1109/tie.2014.2327917 Johnson, R. A., & Wichern, D. W. (2014). Applied multivariate statistical analysis (Vol. 6). Pearson London, UK:. Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020). Supervised Contrastive Learning. arXiv:2004.11362. Retrieved April 01, 2020, from https://ui.adsabs.harvard.edu/abs/2020arXiv200411362K Kwak, M., & Kim, S. B. (2021). Unsupervised Abnormal Sensor Signal Detection With Channelwise Reconstruction Errors. IEEE Access, 9, 39995-40007. https://doi.org/10.1109/access.2021.3064563 Lee, C.-Y., & Chen, B.-S. (2018). Mutually-exclusive-and-collectively-exhaustive feature selection scheme. Applied Soft Computing, 68, 961-971. https://doi.org/10.1016/j.asoc.2017.04.055 Lee, C.-Y., Huang, T.-S., Liu, M.-K., & Lan, C.-Y. (2019). Data Science for Vibration Heteroscedasticity and Predictive Maintenance of Rotary Bearings. Energies, 12(5). https://doi.org/10.3390/en12050801 Lee, C.-Y., & Tsai, T.-L. (2019). Data science framework for variable selection, metrology prediction, and process control in TFT-LCD manufacturing. Robotics and Computer-Integrated Manufacturing, 55, 76-87. https://doi.org/10.1016/j.rcim.2018.07.013 Liao, L. (2014). Discovering Prognostic Features Using Genetic Programming in Remaining Useful Life Prediction. IEEE Transactions on Industrial Electronics, 61(5), 2464-2472. https://doi.org/10.1109/tie.2013.2270212 Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. 2008 eighth ieee international conference on data mining, Mülle, M. (2007). Information Retrieval for Music and Motion. Springer. Müller, R., Ritz, F., Illium, S., & Linnhoff-Popien, C. (2020). Acoustic Anomaly Detection for Machine Sounds based on Image Transform Learning. arXiv:2006.03429. Retrieved June 01, 2020, from https://ui.adsabs.harvard.edu/abs/2020arXiv200603429M Misra, I., & van der Maaten, L. (2019). Self-Supervised Learning of Pretext-Invariant Representations. arXiv:1912.01991. Retrieved December 01, 2019, from https://ui.adsabs.harvard.edu/abs/2019arXiv191201991M Mobley, R. K. (2002). An introduction to predictive maintence. Elsevier. Mostajeran, A., Iranpanah, N., & Noorossana, R. (2018). An explanatory study on the non-parametric multivariate T2 control chart. Journal of modern applied statistical methods, 17(1), 12. Pauwels, E. J., & Ambekar, O. (2011). One class classification for anomaly detection: Support vector data description revisited. Industrial Conference on Data Mining, Tsui, K. L., Chen, N., Zhou, Q., Hai, Y., & Wang, W. (2015). Prognostics and Health Management: A Review on Data Driven Approaches. Mathematical Problems in Engineering, 2015, 1-17. https://doi.org/10.1155/2015/793161 Yáñez, S., González, N., & Vargas, J. (2010). Hotelling's T2 control charts based on robust estimators. Dyna (Colombia ) Num.163 Vol.77, 77. Zhang, L., Lin, J., Liu, B., Zhang, Z., Yan, X., & Wei, M. (2019). A review on deep learning applications in prognostics and health management. IEEE Access, 7, 162415-162438. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84875 | - |
| dc.description.abstract | 隨者科技不斷演進與發展，有許多人工智慧與資料科學相關的新技術出現用來輔助解決現實生活中的問題。目前世界上產值相當高的製造業中因為需求不斷的提升，許多企業都將資料科學相關的技術用於提升產能以及降低成本。而為了要兼顧成本以及產能的考量，設備的故障預測以及健康管理是很重要的一個方法，透過監控機台狀況來使機台能在良好的情況下運作，在必要時才進行保養及更換。因此近幾年不僅學界以及業界都投入許多資源研究相關的議題。本研究針對物理氣相沉積設備，建立基於資料導向的健康評估方式及異常偵測模型。本研究與台灣頂尖面板製造公司合作，使用較有解釋性的特徵來建構機台健康指標，並透過實證資料驗證本研究所提出之方法。除此之外，也提出基於深度學習相關的技術萃取特徵並使用異常偵測的模型及驗證於公開資料集上。本研究貢獻在於根據不同使用情境建立不同監控機台狀況的方法，並透過健康指標來提早預警機台故障，同時權衡保養成本及突發錯誤導致的產能損失。 | zh_TW |
| dc.description.abstract | With the continuous evolution and development of technology, many technologies related to artificial intelligence and data science have emerged to assist in solving real-world problems. Due to the continuous increase in demand in the manufacturing industry which has a high value in the world now, many companies use data science to increase production capacity and reduce costs. Prognostic and Health Management is an important method that considers cost reduction and production capacity at the same time. The machine can operate in a good condition, and only carry out maintenance and replacement when necessary by monitoring the machine. Therefore, not only academia but also the industries have devoted a lot of resources to research related issues. In this study, a data-driven health assessment method and anomaly detection model was established for physical vapor deposition equipment. This study cooperated with a leading panel manufacturing company in Taiwan. Use explanatory features to construct health indicators, and validate the proposed method through empirical data. In addition, anomaly detection models based on the deep learning features are proposed and validated by public datasets. The contribution of this study is to establish different monitoring methods for the machine according to different scenarios and to use health indicators to waring machine failures in advance. Taking into consideration maintenance costs and capacity losses caused by sudden errors at the same time. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:30:16Z (GMT). No. of bitstreams: 1 U0001-2608202214014000.pdf: 5155365 bytes, checksum: c76cbe8c06fa2908650711e51555e2c4 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | List of Contents List of Contents V List of Tables VII List of Figures VIII Chapter 1. Introduction 1 1.1 Background and Motivation 1 1.2 Research Objective 4 1.3 Research Architecture 5 Chapter 2. Literature Review 6 2.1 Feature Engineering 9 2.2 Feature Selection 10 2.3 Control Phase 11 2.4 Contrastive Learning 14 Chapter 3. Physical and Statistical-based Features and Case Study 17 3.1 Research Framework 18 3.2 Data Preprocessing 19 3.3 Feature Engineering 19 3.4 Feature Selection 22 3.5 Control Phase 23 3.6 Case study 25 3.7 Summary of Case Study 33 Chapter 4. Deep Learning Methodology and Case Study 34 4.1 Research Framework 34 4.2 Dataset 35 4.3 Time Domain 36 4.4 Time-Frequency Domain 40 4.5 Anomaly Detection Classifier 44 4.6 Experiment and Result 46 4.7 Summary 49 Chapter 5. Conclusion and Future Research 50 5.1 Summary and Contribution 50 5.2 Future Research 52 References 53 List of Tables TABLE 1.1 Comparison between RM, PHM, and PM 3 TABLE 2.1 Anomaly detection scenario 7 TABLE 2.2 Summary of PHM literature 8 TABLE 2.3 Comparison of anomaly detection methodologies 14 TABLE 3.1 Table of all features 20 TABLE 3.2 Building bootstrap multivariate Hotelling T2 control chart. 25 TABLE 3.3 Data information for benchmarking 27 TABLE 3.4 Data information on self-control 27 TABLE 3.5 Ensemble result of benchmarking 30 TABLE 3.6 Numerical values of normal distribution 31 TABLE 4.1 MIMII dataset description 36 TABLE 4.2 Time domain model information 38 TABLE 4.3 Contrastive learning model information 43 TABLE 4.4 Pseudocode of iForest 44 TABLE 4.5 Pseudocode of iTree 44 TABLE 4.6 Pseudocode of PathLength 45 TABLE 4.7 Experiment result 47 TABLE 4.8 Result of expenditure research 49 TABLE 4.9 Summary of different methodologies of feature engineering 50 List of Figures FIGURE 1.1 Global manufacturing value-added 1 FIGURE 1.2 Comparison between RM, PHM, and PM adapted 3 FIGURE 1.3 Research architecture 6 Figure 2.1 SimCLR framework 16 FIGURE 2.2 Moco 17 FIGURE 3.1 Research framework 18 FIGURE 3.2 Motion type 19 FIGURE 3.3 Stepwise regression model of benchmarking 29 FIGURE 3.4 Random forest model of benchmarking 29 FIGURE 3.5 Gradient boosting machine model of benchmarking 30 FIGURE 3.9 Visualization of feature selection result 30 FIGURE 3.11 Testing phase of control chart 32 FIGURE 3.12 Benchmarking result 33 FIGURE 4.1 Deep learning-based feature framework 35 FIGURE 4.2 Time domain model architecture 39 FIGURE 4.3 Framework of time-frequency domain 41 FIGURE 4.4 Normal signals and the anomaly signals in Mel-spectrogram 41 Figure 4.5 Framework of retraining ResNet-34 with contrastive learning 43 Figure4.6 Isolation forest 46 Figure 4.7 Add noise to the frequency domain 48 | - |
| dc.language.iso | en | - |
| dc.subject | 故障預測與健康管理 | zh_TW |
| dc.subject | 管制圖 | zh_TW |
| dc.subject | 作動 | zh_TW |
| dc.subject | 作動 | zh_TW |
| dc.subject | 故障預測與健康管理 | zh_TW |
| dc.subject | 管制圖 | zh_TW |
| dc.subject | 異常偵測 | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | 對比學習 | zh_TW |
| dc.subject | 非監督式學習 | zh_TW |
| dc.subject | 非監督式學習 | zh_TW |
| dc.subject | 對比學習 | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | 異常偵測 | zh_TW |
| dc.subject | unsupervised learning | en |
| dc.subject | Prognostic and Health Management | en |
| dc.subject | motion-based | en |
| dc.subject | control chart | en |
| dc.subject | transform learning | en |
| dc.subject | contrastive learning | en |
| dc.subject | unsupervised learning | en |
| dc.subject | Prognostic and Health Management | en |
| dc.subject | motion-based | en |
| dc.subject | control chart | en |
| dc.subject | transform learning | en |
| dc.subject | contrastive learning | en |
| dc.title | 基於作動深度學習於物理氣相沉積設備故障預測與健康管理 | zh_TW |
| dc.title | Motion-based Deep Learning for Prognostic and Health Management of Physical Vapor Deposition Equipment | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 110-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 魏志平;許嘉裕;陳以錚 | zh_TW |
| dc.contributor.oralexamcommittee | Chih-Ping Wei;Chia-Yu Hsu;Yi-Cheng Chen | en |
| dc.subject.keyword | 故障預測與健康管理,作動,管制圖,異常偵測,遷移學習,對比學習,非監督式學習, | zh_TW |
| dc.subject.keyword | Prognostic and Health Management,motion-based,control chart,transform learning,contrastive learning,unsupervised learning, | en |
| dc.relation.page | 56 | - |
| dc.identifier.doi | 10.6342/NTU202202857 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2022-08-29 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2025-09-01 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-110-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 5.03 MB | Adobe PDF |
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。