簡易檢索 / 詳目顯示

研究生: 林嶸銓
Lin, Rung-Chuan
論文名稱: 通用型虛擬量測機制與系統
Generic Virtual Metrology Scheme and System
指導教授: 鄭芳田
Cheng, Fan-Tien
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 製造工程研究所
Institute of Manufacturing Engineering
論文出版年: 2005
畢業學年度: 93
語文別: 中文
論文頁數: 95
中文關鍵詞: 化學氣相沉積徑向基底函數類神經網路虛擬量測
外文關鍵詞: Chemical Vapor Deposition, Virtual Metrology (VM), Radial Basis Function Neural Network
相關次數: 點閱:105下載:7
分享至:
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
  •   在半導體廠與TFT-LCD廠,生產製程上之機台皆需進行週期性監控,以確保所有機台在製程上均有穩定且合乎品質規格的產出。以半導體廠為例,為達到監控機台效能,且亦偵測出所生產之晶圓品質,則需線上監控晶圓。目前一般的做法為每間隔一段時間,插入乙片以監控為目的之測試晶圓,進行週期性品質量測。因週期性之監控仍無法達到即時性偵測每片晶圓之品質,致無法即時發現機台效能漂移,因此仍可能導致產出之產品被作廢,造成極高的成本損失。基於此,本研究提出一套虛擬量測系統,其不僅可達到即時量測每片晶圓之品質,亦可減少測試晶圓之使用率,並即時監控生產機台效能將其回報予機台工程師。虛擬量測系統是在產品尚未進行實際量測之情況下,利用生產機台之參數,推估其所生產之產品品質,以進行晶圓品質預測及機台效能監控。此系統內部之核心機制為虛擬量測模組,其使用徑向基底函數類神經網路來建構。並設計參數調整器,用以設定及調整徑向基底函數類神經網路之參數。本研究並以半導體廠之化學氣相沉積製程為例,以驗證本架構之效能。

     In a semiconductor or TFT-LCD fab, the production equipment is periodically monitored to assure the stability of production processes and the quality of products. Taking the semiconductor fab for example, on-line monitoring on the wafer is required for equipment performance monitoring to assess wafer quality. At present, the semiconductor fab adopts the method of periodical monitoring by processing the test wafers through the main production equipment. However, periodical monitoring cannot provide real-time and overall monitoring data and quality assurance to each wafer, because the equipment performance drift may happen in the intervals of scheduled monitoring, scrap the wafers and greatly increase the production cost.
     Aiming at the difficulties mentioned above, this work proposes a virtual metrology (VM) system. The VM not only greatly decreases the demand of test wafers, but also realizes the real-time online monitoring of wafer quality to every production wafer and immediately reports the information about equipment performance to maintenance engineers. With the parameters collected from production equipment, VM can effectively prognoses the production quality both on wafer quality and equipment performance before the physical metrology operation is performed. The core mechanism of the proposed system is virtual metrology module developed with radial basis function neural network; besides the model parameter coordinator is also developed to VM to define and adjust the parameters of the radial basis function neural network. Further, in order to verify the performance of the scheme proposed, in this work, we implement VM to the practical production process of chemical vapor deposition in a semiconductor fab.

    目錄 中文摘要 英文摘要 致謝 目錄 i 圖目錄 iii 表目錄 v 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 3 1.3 研究流程 4 1.4 論文架構 5 第二章 文獻探討與理論基礎 6 2.1 相關文獻探討 6 2.1.1 預測系統之相關架構 6 2.1.2 品質預測之相關技術 10 2.2 相關理論基礎 12 2.2.1 常態分配之特性 12 2.2.2 主成份分析 16 2.2.3 類神經網路 19 2.2.3.1 類神經網路原理 19 2.2.3.2 徑向基底函數類神經網路 22 2.2.4 統一塑模語言 26 第三章 通用型虛擬量測機制與系統 30 3.1 通用型虛擬量測機制 30 3.2 通用型虛擬量測系統架構設計 34 3.2.1 需求分析 34 3.2.2 物件導向分析 34 3.2.2.1 使用者案例圖 35 3.2.2.2 循序圖 36 3.2.2.3 類別圖(OOA) 44 3.2.3 物件導向設計 45 3.2.3.1 類別圖(OOD) 45 3.2.3.2 活動圖 47 3.3 系統執行環境 52 第四章 案例分析 54 4.1 半導體製程簡介 54 4.2化學氣相沉積製程參數簡介 57 4.2.1 失效偵測分類資料格式 59 4.2.2 統計製程管制資料格式 62 第五章 系統實作 64 5.1 開發環境 65 5.2 資料前處理技術之建構 65 5.3 虛擬量測模組之建構 67 5.4 信心指標之建構 71 5.5 準確度評估之建構 75 5.6 模組參數調整之建構 76 第六章 實作結果與比較 81 6.1 RBFNN參數調整之比較 81 6.2 VMS與QPS之比較 83 第七章 結論 90 7.1 論文總結 90 7.2 未來研究方向 91 參考文獻 92

    [1] Diebold, A.C. “Overview of metrology requirements based on the 1994National Technology Roadmap for semiconductor,” Advanced Semiconductor Manufacturing Conference and Workshop, 1995.ASMC 95 Proceedings. IEEE/SEMI 1995. 13-15 Nov. 1995 Page(s):50-60.
    [2] Stanley, K.J.; Stanley, T.D.; Maia, J. “Realizing 300 mm fab productivity improvements through integrated metrology,” Simulation Conference, 2002. Proceedings of the Winter, Volume 2, 8-11 Dec. 2002 Page(s): 1369 -1376 vol.2.
    [3] TSMC, “AEC/APC Challenges-Today and in the Future,” 2004.
    [4] Y.-C. Su, F.-T. Cheng, Y.-C. Lin, M.-H. Hung, R.-C. Lin, and H.C. Huang “Intelligent Prognostics System Design and Implementation1,” 2004.
    [5] 林彥璋 「一個適用於半導體業網路式診斷應用之介面的通用型嵌入式裝置」,國立成功大學製造工程研究所碩士論文,2004.
    [6] Y.-C. Su, F.-T. Cheng, G.-W. Huang, M.-H. Hung, and T. Yang, "A Quality Prognostics Scheme for Semiconductor and TFT-LCD Manufacturing Processes," in Proc. of The 30th Annual Conference of the IEEE Industrial Electronics Society (IECON 2004), Busan, Korea, November 2004.
    [7] P.-F. Tsai, J.-Z. Chu, S.-S. Jang, S.-S. Shieh. “Developing a robust model predictive control architecture through regional knowledge analysis of artificial neural networks,” Journal of Process Control, Vol.13 no.5, 2003.
    [8] Zurada J.M. “Introduction to Artificial Neural Systems,” St. Paul, MN: West Publishing, 1992.
    [9] Web site of the Center for Intelligent Maintenance Systems (IMS). http://www.imscenter.net
    [10] J. Lee, “E-Manufacturing/E-Business: Transformation, Needs, Issues, and Collaborative Research Opportunities,” 2001. http://www.uwm.edu/CEAS/ims
    [11] M. Koc and J. Lee, “A System Framework for Next-Generation E-Maintenance System,” 2001.
    [12] NSF Workshop, NSF I/UCR Center, Oct. 1-2,2001.
    [13] 黃國偉 「半導體機台網路式預防保養功能架構之設計與實作」,國立成功大學製造工程研究所碩士論文,2003.
    [14] 李柏甫 「TFT-LCD濺鍍製程之智慧型診斷系統發展」,國立成功大學製造工程研究所碩士論文,2004.
    [15] S.-F. Lee, and C.-J. Spanos, “Prediction of wafer state after plasma processing using real-time tool data,” IEEE Trans. Semiconductor Manufacturing, Vol. 8, pp. 252-261, Aug 1995.
    [16] B. Kim and K. Kim, “Prediction of profile surface roughness in CHF3 /CF4 plasma using neural network,” Appl. Surf. Sci. 222(2004)17-22.
    [17] B. Kim, D.-W. Lee, K.-Y. Park, S.-R. Choi and S. Choi, “Prediction of plasma etching using a randomized generalized regression neural network,” Vacuum 76(2004)37-43.
    [18] 顧尚芳 「生產系統中利用製程不良率評估設備預防維護之研究」,中原大學工業工程學系碩士論文,2003.
    [19] Benyong Zhang and Gary S. May “Towards Real-Time Fault Identification in Plasma Etching Using Neural Network,” IEEE/SEMI Advanced Semiconductor Manufacturing Conference, 1998.
    [20] Tsung-Nan Tsai, Shih-Yaug Liu, and Taho Yang, “A SMT Reflow Soldering Process Diagnosis System Using Neurofuzzy Approach,” International Journal of Fuzzy Systems, Vol.3, No.4, Dec. 2001.
    [21] Huang S, and Zhang H., “Neural Network in Manufacturing: A Survey,” IEEE/CPMT International Electronics Manufacturing Technology Symposium, pp.177-190, 1993.
    [22] 楊博文 「鉻鉬鋼鑽孔擴孔量預測模式之探討」,國立屏東科技大學機械工程學碩士論文,2002.
    [23] Byungwhan Kim, and Gary S. May, “An Optimal Neural Network Process Model for Plasma Etching,” IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, VOL. 7, NO. 1, FEBRUARY 1994.
    [24] Hogg and Tanis, “Probability and Statistical Inference,” Prentice Hall, NJ:07458, 1997.
    [25] W.-J. Conover, “Practical Nonparametric Statistics,” New York, Wiley, 1980.
    [26] Anderson, T.W, “An Introduction to Multivariate Statistical Methods,” 1984.
    [27] 陳業統 「多變量製程能力指標在評估環境風險上之研究」,國立成功大學統計學系碩士論文,2003.
    [28] Y. L. Huang, T. F. Edgar, D. M. Himmmelblau, and I. Trachtenberg, “Constructing a reliable neural network model for a plasma etching process using limited experimental data,” IEEE Trans. Semicond. Manuf., Vol. 3, pp. 333-344, Aug 1994.
    [29] F. Nadi, A. M. Agogino, and D. A. Hodges, “Use of influence diagram and neural networks in modeling semiconductor manufacturing processes,” IEEE Trans. Semicond. Manuf., Vol. 4, no. 1, Feb 1991.
    [30] M. T. Mocella, J. A. Bondur, and T. R. Turner, “Etch process characterization using neural network methodology: A case study,” in SPIE proc. Process Module Metrology, Control, and Clustering, Vol. 1594, 1992, pp. 232-242.
    [31] C. D. Himmel, and G. S. May, “Advantages of plasma etch modeling using neural networks over statistical techniques,” IEEE Trans. Semicond. Manuf., Vol. 6, pp. 103-111, May 1993.
    [32] 葉怡成 「應用類神經網路」,儒林圖書公司,1997.
    [33] 葉怡成 「類神經網路模式應用與實作」,儒林圖書公司,2003.
    [34] 張斐章,張麗秋,黃浩倫 「類神經網路理論與實務」,東華書局,2003.
    [35] Simon Haykin, “Neural Networks, A Comprehensive Foundation,” Prentice Hall, NJ:07458, 1999.
    [36] Grady Booch, James Rumbaugh, Ivar Jacobson, “The Unified Modeling Language User Guide,” ADDISON-WESLEY, April 2000.
    [37] Gary B. Shelly, Thomas J. Cashman, Harry J. Rosenblatt, “Systems Analysis and Design,” Thomson Learning, 2001
    [38] ISMI, “Data Quality Proof of Concept Test Method,” 2005.
    [39] Ming Lu, S. M. AbouRizk and U. H. Hermann, “Sensitivity Analysis Of Neural Networks In Spool Fabrication Productivity Studies,” 2002.
    [40] Honh Xiao, “Introduction to Semiconductor Manufacturing Technilogy,” PRENTICE HALL, 2001
    [41] Borland C++ Bulider 6.0, Borland Corporation. http://www.borland.com/cbuilderx
    [42] Matlab 7.0, The MathWork Corporation. http://www.mathworks.com/
    [43] 陳順宇 「多變量分析」,二版,華泰書局,2000.
    [44] 陳順宇 「迴歸分析」,三版,華泰書局,2000.
    [45] 羅華強 「類神經網路,MATLAB的應用」,清蔚科技,2001.
    [46] 張智星 「MATLAB程式設計與應用」,清蔚科技,2000.

    下載圖示 校內:2008-09-06公開
    校外:2010-09-06公開
    QR CODE