在全球化競爭環境下，半導體廠商為了維持其競爭優勢必須著重於產品品質與良率，而良率提升的技術中包含了流程監控，其在偵測製程異常與辨別異常發生的根本原因扮演著重要的角色。隨著科技的發展，廠商們導入先進設備控制與先進製程控制以達到智慧製造，其功能主要包含批次控制以及錯誤偵測與分類系統用以改善工廠之生產力並降低製造成本。先進設備控制與先進製程控制藉由廣布嵌入於先進機台中的感測器蒐集即時物理參數資料。廠商們從而能利用資料監控製程並且從中獲得洞察。然而，分析由感測器所蒐集龐大的即時參數資料將耗費高計算成本，因此需要一個能夠高效而有效地萃取資訊之分析方法。本研究發展用於半導體製程錯誤偵測與分類系統建構的大數據分析架構，透過資料挖礦方法於大量感測資料中偵測異常晶圓。此架構整合了兩層級的關鍵因子篩選: (1) 使用Least Absolute Shrinkage and Selection Operator (LASSO) (Tibshirani, 1996) 篩選關鍵機台同時降低資訊量，以及(2) Random Forest (RF) (Breiman, 2001) 排序參數之重要性。
本研究以台灣某半導體公司之晶圓廠為實證以檢驗效度，根據本研究提出的架構所建構之錯誤偵測與分類系統能夠精準地偵測出異常晶圓。另一方面，由本架構提供之參數重要性排序表在實證研究中有效地幫助工程師找尋異常發生之根本原因。

To maintain the competitive advantages, process monitoring and quick response for yield enhancement are critical via detecting the root causes of the faults or abnormalities. In terms of intelligent manufacturing, many manufacturers develop advanced equipment control/advanced process control (AEC/APC), which usually comprises run-to-run (R2R) control and fault detection and classification (FDC), focuses on productivity improvement and cost reduction. AEC/APC has the ability to collect the real-time physical sensor data by sensors embedded in the advanced machines during the manufacturing process. Manufacturers should take advantage of the data to monitor the process and get insight from it. However, sensor data is tremendous may lead to high computational cost, a more systematic and efficient way to extract valuable information is needed. This study develops a framework for FDC using big data analytics to detect and classify abnormal objects from the voluminous sensor data. The proposed framework includes two analytical methods as key factors selection for FDC: (1) we applied the Least Absolute Shrinkage and Selection Operator (LASSO) (Tibshirani, 1996) as key operation screening, reducing massive information, and (2) We then applied Random Forest (RF) (Breiman, 2001) for process parameters ranking. We conducted an empirical study in a semiconductor company in Taiwan to validate this approach. The results have shown practical viability of the proposed FDC function to differentiate abnormal wafers from the normal ones with higher accuracy and sensitivity. The ranking of the FDC parameters provided by our framework was effective in the empirical study.

Table of Contents i
List of Tables ii
List of Figures iii
Chapter 1 Introduction 1
1.1 Background and Motivation 1
1.2 Research Objectives 2
1.3 Organization of Thesis 2
Chapter 2 Literature Review 4
2.1 Fault detection and classification (FDC) 5
2.2 Methodologies adopted in FDC 7
2.3 Feature Selection 9
Chapter 3 The Approach 13
3.1 Problem Definition 15
3.2 Data Preparation 15
3.3 Model Development 18
3.4 Model Validation 21
3.5 Evaluation and Interpretation 21
Chapter 4 An Empirical Study 23
4.1 Problem Definition 23
4.2 Data Preparation 23
4.3 Model Development 25
4.4 Model Validation 27
4.5 Evaluation and Interpretation 28
4.6 Discussion 31
Chapter 5 Conclusion 33
References 34

Breiman, L. (2001), “Random forests,” Machine learning, Vol. 45, No. 1, pp., 5-32.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002), “SMOTE: synthetic minority over-sampling technique,” Journal of artificial intelligence research, Vol. 16, pp. 321-357.
Chen, X., and Ishwaran, H. (2012), “Random forests for genomic data analysis,” Genomics, Vol. 99, No. 6, pp. 323-329.
Chien, C. F., and Hsu, C. Y. (2011), “UNISON analysis to model and reduce step-and-scan overlay errors for semiconductor manufacturing,” Journal of Intelligent Manufacturing, Vol. 22, No. 3, pp. 399-412.
Chien, C. F., Chen, Y. J., Hsu, C. Y., and Wang, H. K. (2014), “Overlay error compensation using advanced process control with dynamically adjusted proportional-integral R2R controller,” IEEE Transactions on Automation Science and Engineering, Vol. 11, No. 2, pp. 473-484.
Chien, C. F., Hsu, C. Y., and Chen, P. N. (2013), “Semiconductor fault detection and classification for yield enhancement and manufacturing intelligence,” Flexible Services and Manufacturing Journal, Vol. 25, No. 3, pp. 367-388.
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, Vol. 33, No. 1, pp. 192-198.
Cutler, D. R., Edwards, T. C., Beard, K. H., Cutler, A., Hess, K. T., Gibson, J., and Lawler, J. J. (2007), “Random forests for classification in ecology,” Ecology, Vol. 88, No. 11, pp. 2783-2792.
Díaz-Uriarte, R., and De Andres, S. A. (2006), “Gene selection and classification of microarray data using random forest,” BMC bioinformatics, Vol. 7, No.1, pp. 3.
Edwards, W., and Von Winterfeldt, D. (1986), Decision analysis and behavioral research.
Fan, S. K. S., and Chang, Y. J. (2013), “An integrated advanced process control framework using run-to-run control, virtual metrology and fault detection,” Journal of Process Control, Vol. 23, No. 7, pp. 933-942.
Ferreira, A., Roussy, A., and Condé, L. (2009), “Virtual metrology models for predicting physical measurement in semiconductor manufacturing,” Advanced Semiconductor Manufacturing Conference, pp. 149-154.
Friedman, J., Hastie, T., and Tibshirani, R. (2001), The elements of statistical learning, Vol. 1, Springer, Berlin: Springer series in statistics.
Friedman, J., Hastie, T., and Tibshirani, R. (2010). “Regularization paths for generalized linear models via coordinate descent,” Journal of statistical software, Vol. 33, No. 1.
Genkin, A., Lewis, D. D., and Madigan, D. (2007), “Large-scale Bayesian logistic regression for text categorization,” Technometrics, Vol. 49, No. 3, pp. 291-304.
Genuer, R., Poggi, J. M., and Tuleau, C. (2008), “Random Forests: some methodological insights,” arXiv preprint arXiv:0811.3619.
Goodlin, B. E., Boning, D. S., Sawin, H. H., and Wise, B. M. (2003), “Simultaneous fault detection and classification for semiconductor manufacturing tools,” Journal of the Electrochemical Society, Vol. 150, No. 12, pp. 778-784.
He, Q. P., and Wang, J. (2007), “Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes,” IEEE Transactions on Semiconductor Manufacturing, Vol. 20, No. 4, pp. 345-354.
He, Q. P., and Wang, J. (2008), “Principal component based k-nearest-neighbor rule for semiconductor process fault detection,” American Control Conference, pp. 1606-1611.
Himmelblau, D. M. (1978), Fault detection and diagnosis in chemical and petrochemical processes, Elsevier Scientific Publishing Company, New York.
Hong, S. J., Lim, W. Y., Cheong, T., and May, G. S. (2012), “Fault Detection and Classification in Plasma Etch Equipment for Semiconductor Manufacturing-Diagnostics,” IEEE Transactions on Semiconductor Manufacturing, Vol. 25, No. 1, pp. 83-93.
International Technology Roadmap for Semiconductors 2.0 (ITRS 2.0) reports (2014)
Isermann, R., and Balle, P. (1997), “Trends in the application of model-based fault detection and diagnosis of technical processes,” Control engineering practice, Vol. 5, No. 5, pp. 709-719.
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013), An introduction to statistical learning, Vol. 6, Springer, New York.
Lada, E. K., Lu, J. C., and Wilson, J. R. (2002), “A wavelet-based procedure for process fault detection,” IEEE Transactions on Semiconductor Manufacturing, Vol. 15, No. 1, pp. 79-90.
Laney, D. (2001). “3D data management: Controlling data volume, velocity and variety,” META Group Research Note, Vol. 6, pp. 70.
Mahadevan, S., and Shah, S. L. (2009). “Fault detection and diagnosis in process data using one-class support vector machines,” Journal of process control, Vol. 19, No. 10, pp. 1627-1639.
Moore, G. E. (1965), “Cramming more components onto integrated circuits,” Electronics, Vol. 38, No. 8, pp. 114-117.
Moyne, J., and Schulze, B. (2010), “Yield management enhanced advanced process control system (YMeAPC)—Part I: description and case study of feedback for optimized multiprocess control,” IEEE Transactions on Semiconductor Manufacturing, Vol. 23, No. 2, pp. 221-235.
Moyne, J., Del Castillo, E., and Hurwitz, A. M. (Eds.). (2001), Run-to-run control in semiconductor manufacturing, Vol. 200, Springer, London.
Pampuri, S., Schirru, A., Fazio, G., and De Nicolao, G. (2011), “Multilevel lasso applied to virtual metrology in semiconductor manufacturing,” Automation Science and Engineering (CASE), pp. 244-249.
Park, J., Kwon, I. H., Kim, S. S., and Baek, J. G. (2011). “Spline regression based feature extraction for semiconductor process fault detection using support vector machine,” Expert Systems with Applications, Vol. 38, No. 5, pp. 5711-5718.
Peng, J., Zhu, J., Bergamaschi, A., Han, W., Noh, D. Y., Pollack, J. R., and Wang, P. (2010), “Regularized multivariate regression for identifying master predictors with application to integrative genomics study of breast cancer,” The annals of applied statistics, Vol. 4, No. 1, pp. 53.
Ralson P, DePuy G, Graham JH (2001), “Computer-based monitoring and fault diagnosis: a chemical process case study,” ISA Trans, Vol. 40, No. 1, pp. 85–98
Saeys, Y., Inza, I., and Larrañaga, P. (2007), “A review of feature selection techniques in bioinformatics,” Bioinformatics, Vol. 23, No. 19, pp. 2507-2517.
Stehman, S. V. (1997), “Selecting and interpreting measures of thematic classification accuracy,” Remote sensing of Environment, Vol. 62, No. 1, pp. 77-89.
Svetnik, V., Liaw, A., Tong, C., Culberson, J. C., Sheridan, R. P., and Feuston, B. P. (2003), “Random forest: a classification and regression tool for compound classification and QSAR modeling,” Journal of chemical information and computer sciences, Vol. 43, No. 6, pp. 1947-1958.
Tenney, R. R. (1994), FAULT DETECTION AND CLASSIFICATION. Vibration-Institute, 67.
Tibshirani, R. (1996), “Regression shrinkage and selection via the lasso,” Journal of the Royal Statistical Society. Series B (Methodological), pp. 267-288.
Verdier, G., and Ferreira, A. (2011), “Adaptive mahalanobis distance and-nearest neighbor rule for fault detection in semiconductor manufacturing,” IEEE Transactions on Semiconductor Manufacturing, Vol. 24, No. 1, pp. 59-68.
Wang, S., Nan, B., Rosset, S., and Zhu, J. (2011), “Random lasso,” The annals of applied statistics, Vol. 5, No. 1, pp. 468.
Yu, H. C., Lin, K. Y., and Chien, C. F. (2014), ”Hierarchical indices to detect equipment condition changes with high dimensional data for semiconductor manufacturing,” Journal of Intelligent Manufacturing, Vol. 25, No. 5, pp. 933-943.
Zou, H., and Hastie, T. (2005), “Regularization and variable selection via the elastic net,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 67, No. 2, pp. 301-320.