成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	吳偉民 Wu, Wei-Ming
論文名稱：	虛擬量測精度之提升機制 Accuracy-Enhancement Schemes of Virtual Metrology
指導教授：	鄭芳田 Cheng, Fan-Tien
學位類別：	博士 Doctor
系所名稱：	電機資訊學院 - 製造資訊與系統研究所 Institute of Manufacturing Information and Systems
論文出版年：	2012
畢業學年度：	100
語文別：	英文
論文頁數：	48
中文關鍵詞：	虚擬量測、雙虚擬量測輸出、簡易挑選機制、預測值合成機制、動態移動視窗機制、加權歐式距離、靜態移動視窗機制
外文關鍵詞：	Virtual metrology (VM), dual-VM outputs, simple selection scheme (SS-scheme), weighted selection scheme (WS-scheme) model refreshing, dynamic-moving-window (DMW) scheme, weighted-Euclidean-distance (WED) method, static-moving-window (SMW) scheme
相關次數：	點閱：124 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

虛擬量測迷人之處，已是眾所皆知，不僅能即時地達到線上監控產品品質之外，更是先進製程控制所依賴之關鍵要素。因此，精進推估能力與即時監控能力，進而提高製程能力或其它虛擬量測之應用，虛擬量測精度之提升將是首要目標。
然而，對於虛擬量測系統而言，類神經網路與迴歸皆能運用於建構虛擬量測模型之演算法，當製程穩定時，迴歸模型有較佳之預測精度，若機台出現漂移時，類神經網路則有較佳之預測精度；為了同時獲得迴歸與類神經網路之優點，簡易挑選機制 (Simple-Selection Scheme, SS-scheme) 為首推之提升虛擬量測精度方法，簡易挑選機制係根據線上製程資料與歷史資料間之馬氏距離 (Mahalanobis Distance, MD)，從類神經網路與迴歸中，挑選出最終推估值。本論文同時亦發完成預測值合成機制 (Weighted-Selection Scheme, WS-scheme)，本機制為利用類神經網路與迴歸預測值，配合其權重加總，以求得最終預測結果，且經測試結果顯示，預測值合成機制較簡易挑選機制、類神經網路、迴歸之預測精度佳。
此外，預測模型之預測精度，將與其首套模型之建模樣本，和線上換模期間所採用之建模樣本，有密切關係。因進行實驗設計需耗費大量的資源，而難以實踐。因此，如何獲得並留住重要且足夠的建模樣本，是確保預測精度的主要課題。傳統上，都是採用靜態移動視窗機制來維持及管理建模樣本。然而，靜態移動視窗機制乃以固定樣本數量之方式，進行預測模型之更新；使得其預測模型內原有之歷史偏移樣本，會因時間一久，而被摒棄於預測模型之外，致使未來再面臨類似之機台偏移狀況時，該預測架構就無法準確地預測了。本發明之目的為提出動態移動視窗機制來維持及管理建模樣本。當動態移動視窗機制加入一筆新樣本於模型後，將先利用分群技術進行分群，使得特性相近的數個樣本將被歸類於同一群內。然後，各個群集內之樣本數將被檢視。假使最大群集之樣本數大於預設門檻時，此最大群集內之最舊樣本將被摒棄。

The advantages of virtual metrology are well-known, it cannot only monitor the product quality online and in real-time but it also is a very important factor for advanced process control (APC). Therefore, to achieve better real-time monitoring for enhancing the process capability or other process applications of VM, the first priority is to enhance the VM accuracy.
Both NN and MR are applicable algorithms for implementing VM conjecture models. A MR algorithm may achieve better accuracy only with a stable process, whereas a NN algorithm may have superior accuracy when equipment property drift or shift occurs. To take advantage of both MR and NN algorithms, the simple-selection scheme (SS-scheme) is first proposed to enhance the virtual-metrology (VM) conjecture accuracy. This SS-scheme simply selects either NN or MR output according to the smaller Mahalanobis distance between the input process data set and the NN/MR-group historical process data sets. Furthermore, a weighted-selection scheme (WS-scheme), which computes the VM output with a weighted sum of NN and MR results, is also developed.
The accuracy of VM highly depends on the modeling samples adopted during initial-creating and on-line-refreshing periods. Since large resources required, design-of-experiments may not be performed. In that case, how could we guarantee the stability of the models and predictions as they move into the unknown environment? Conventionally, static-moving-window (SMW) schemes with a fixed window size are adopted in the on-line-refreshing period. The purpose of this paper is to propose a dynamic-moving-window (DMW) scheme for VM model refreshing to enhance prediction accuracy. The DMW scheme adds a new sample into the model and applies a clustering technology to do similarity clustering. Next, the number of elements in each cluster is checked. If the largest number of the elements is greater than the predefined threshold, then the oldest sample in the cluster with the largest population is deleted.

摘 要		I
ABSTRACT		II
致  謝		III
ACKNOWLEDGEMENTS	IV
FIGURE CONTENTS	VII
TABLE CONTENTS	VIII
CHAPTER 1 INTRODUCTION	1
1.1	Background and Motivation	1
1.2	Purpose of this Dissertation	4
1.3	Accuracy Evaluator	5
1.4	Organization	5
CHAPTER 2 SELECTION SCHEMES OF DUAL VIRTUAL-METROLOGY OUTPUTS FOR ENHANCING PREDICTION ACCURACY	6
2.1	Introduction	6
2.2	SS-Scheme and WS-Scheme	8
2.2.1 Off-line Classification Flow of Modeling Data Sets	8
2.2.2 On-line Selection Flow of the SS-scheme	11
2.2.3 On-line Selection and Computing Flow of the WS-Scheme	12
2.3	Illustrative Examples	13
2.3.1 Conjecture Results of Example 1	15
2.3.2 Conjecture Results of Example 2A	18
2.3.3 Conjecture Results of Example 2B	19
CHAPTER 3 A DYNAMIC-MOVING-WINDOW SCHEME FOR VIRTUAL-METROLOGY MODEL REFRESHING	22
3.1	Introduction	22
3.2	Dynamic Moving Window Scheme	24
3.2.1 Applying ART2 for Similarity Clustering	26
3.2.2 Applying WED for Similarity Clustering	26
3.3	Illustrative Examples	29
3.3.1 Conjecture Results of Example 1	30
3.3.2 Conjecture Results of Example 2	33
CHAPTER 4 FUTURE WORK	36
4.1 Selection Schemes with Partial Least Square for Section 2.3.1 Example	36
4.2 Selection Schemes with Partial Least Square for Section 2.3.2 Example	37
4.3 Selection Schemes with Partial Least Square for Section 2.3.3 Example	37
4.4 DMW Schemes with Partial Least Square for Section 3.3.1 Example	39
4.5 DMW Schemes with Partial Least Square for Section 3.3.2 Example	39
CHAPTER 5 CONCLUSION	40
5.1	Discussion	40
5.2	Summary and Conclusions	41
APPENDIX - BPNN PARAMETERS OPTIMIZATION SOP	43
ABBREVIATION LIST	45
REFERENCES	46
BIOGRAPHY	49
PUBLICATION LISTS	50
                                    

[1] J. Moyne, E. del Castillo, and A. M. Hurwitz, Run-to-Run Control in Semiconductor Manufacturing. Boca Raton, FL: CRC Press, 2001.
[2] A. Weber, “Virtual metrology and your technology watch list: ten things you should know about this emerging technology,” Future Fab International, issue 22, section 4, pp. 52-54, Jan. 2007.
[3] P.-H. Chen, S. Wu, J. Lin, F. Ko, H. Lo, J. Wang, C.-H. Yu, and M.-S. Liang, “Virtual metrology: a solution for wafer to wafer advanced process control,” in Proc. 2005 IEEE International Symposium on Semiconductor Manufacturing (ISSM 2005), pp. 155-157, Sept. 2005.
[4] Y.-C. Chang and F.-T. Cheng, “Application development of virtual metrology in semiconductor industry,” in Proc 31st Annual Conference IEEE Industrial Electronics, Raleigh, NC, Nov. 2005, pp. 124-129.
[5] A. A. Khan, J. R. Moyne, and D. M. Tilbury, “An approach for factory-wide control utilizing virtual metrology,” IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, pp. 364-375, Nov. 2007.
[6] A. A. Khan, J. R. Moyne, and D. M. Tilbury, “Virtual metrology and feedback control for semiconductor manufacturing processes using recursive partial least squares,” Journal of Process Control, vol. 18, pp. 961-974, 2008.
[7] M.-F. Wu, C.-H. Lin, D. S.-H. Wong, S.-S. Jang, and S.-T. Tseng, “Performance Analysis of EWMA Controllers Subject to Metrology Delay,” IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 3, pp. 413-425, August 2008.
[8] O. Rothe, “ISMI Next Generation Factory,” in Proc. e-Manufacturing Workshop, SEMICON West, July, 2008. [Online]. Available: http://www.sematech.org/meetings/archives/emanufacturing/8546/01-NGF.pdf
[9] J. Moyne, “International Technology Roadmap for Semiconductors (ITRS) Perspective on AEC/APC,” in Proc. 21st ISMI AEC/APC Symposium, Ann Arbor, Michigan USA, Sep. 2009.
[10] J. Moyne, “PCS Mechanisms for Fab-Wide Development and Latest Trends, New Directions in PCS: Virtual Metrology,” in Proc. 21st ISMI AEC/APC Symposium, Ann Arbor, Michigan USA, Sep. 2009.
[11] K. Olson and J. Moyne, “Adaptive Virtual Metrology Applied to a CVD Process,” 2010 IEEE/SEMI Advanced Semiconductor Manufacturing Conference (ASMC), pp. 353 – 358, July 2010.
[12] J. Scoville, “Predictability as a Key Component of Productivity: The Move Towards Smart Yield,” ISMI Manufacturing Week Conference, October 2011.
[13] F.-T. Cheng, Y.-T. Chen, Y.-C. Su, and D.-L. Zeng, "Evaluating reliance level of a virtual metrology system," IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 1, pp. 92-103, Feb. 2008.
[14] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, “Dual-phase virtual metrology scheme,” IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, pp. 566-571, Nov. 2007.
[15] W.-M. Wu, F.-T. Cheng, D.-L, Zeng, T.-H. Lin, J.-F. Chen, " Developing a selection scheme for dual virtual-metrology outputs," in Proc. 2008 IEEE International Conference on Automation Science and Engineering, Washington, D.C., U.S.A, Aug. 2008, pp.230-235.
[16] W.-M. Wu and F.-T. Cheng, “Preliminary Study of a Dynamic-Moving-Window Scheme for Virtual-Metrology Model Refreshing,” submitted to 2012 IEEE International Conference on Robotics and Automation, St. Paul, Minnesota, U.S.A, May, 2012.
[17] F. Ko, C.-W. Lai, K. Zuo, H. Lo, J. Wang, P.-H Chen, C.-H Lin, and C.-H Yu, “Novel methodology to realize automatic virtual metrology,” United States Patent, Pub No.: US 2008/0275586 A1, Nov. 2008.
[18] T.-H. Lin, F.-T. Cheng, W.-M. Wu, Chi-An Kao, A.-J. Ye, and F.-C. Chang, "NN-based key-variable selection method for enhancing virtual metrology accuracy," IEEE Transactions on Semiconductor Manufacturing, vol. 22, no. 1, pp. 204-211, February 2009.
[19] N. Chaudhry, J. Moyne, E. Rundensteiner, “Utilizing Fuzzy Data and Rules for Discrete Control of Semiconductor Manufacturing Processes,” DKSME ‘96, Phoenix, October 1996.
[20] I. S. Markham and T. R. Rakes, “The effect of sample size and variability of data on the comparative performance of artificial neural networks and regression,” Computers and Operations Research, vol. 25, no. 4, pp. 251-263, 1998.
[21] Y.-C. Su, T.-H. Lin, F.-T. Cheng, and W.-M. Wu, "Accuracy and real-time considerations for implementing various virtual metrology algorithms," Transactions on Semiconductor Manufacturing, vol. 21, no. 3, pp. 426-334, Aug. 2008.
[22] Y.-T. Huang, F.-T. Cheng, and Y.-T. Chen, "Importance of data quality in virtual metrology, " in Proc. of the 32nd Annual Conference of the IEEE Industrial Electronics Society (IECON 2006), Paris, France, pp.3727-3732, November 2006.
[23] S. Lynn, J. V. Ringwood, and N. MacGearailt, “Weighted Windowed PLS Models for Virtual Metrology of an Industrial Plasma Etch Process,” in IEEE Int. Conf. Indust. Tech., Valpariaso, Chile,, pp. 271–276, Mar. 2010.
[24] G. A. Carpenter & S. Grossberg, “ART 2: Self-Organization of Sable Category Recognition Codes for Analog Input Patterns,” Applied Optics, vol. 26, no. 12, pp. 4919-4930, Dec 1987.
[25] G. A. Carpenter & S. Grossberg, “A Massively Parallel Architecture for A Self-Organizing Neural Pattern Recognition Machine”, Computer Vision Graphics Image Processing, vol.13, Issue 7, pp.37-54, July 1987.
[26] Y.-T. Huang and F.-T. Cheng, "Automatic Data Quality Evaluation for the AVM System," IEEE Transactions on Semiconductor Manufacturing, vol. 24, no. 3, pp. 445-454, August 2011.
[27] Elena Deza & Michel Marie Deza, Encyclopedia of Distances, Springer, 2009.
[28] David W. Scott, Wiley Interdisciplinary Reviews: Computational Statistics, vol. l, issue 3, pp. 303-306, Nov 2009.
[29] Hogg and Tanis, “Probability and Statistical Inference,” Prentice Hall, NJ: 07458, 1997.
[30] T. Byrne, “Cost Reduction Strategy Including Equipment Matching, FDC, and Metrology Prediction,” e-Manufacturing & Design Collaboration Symposium 2011, Hsinchu Taiwan, Sep. 2011.

校內：2017-06-25公開
校外：不公開電子論文尚未授權公開，紙本請查館藏目錄

簡易檢索 / 詳目顯示

相關論文