臺灣博碩士論文加值系統

由於晶圓增大、IC元件尺寸縮小、線寬日趨細微，使得半導體製程控制也因而日益困難，發生故障的比例相對地增高，嚴格的製程控制已成為重要且基本的要求，一般使用統計製程管制(Statistical Process Control ,SPC)作為品質管制工具，但由於製程數據間具有相關聯性結構，及大部分製程常有不可避免的穩定緩慢漂動變異現象，往往使得錯誤警訊(false alarm)增加進而導致於管制圖的誤判，因此本研究之主要目的是利用幅狀基底函數類神經網路來學習該變異，進而偵測出半導體製程中的故障，以避免錯誤警訊之發生，並提供診斷功能，做為維修與預防保養之依據，以提昇設備總體效能。
幅狀函數類神經網路(Radial Basis Function，簡稱RBF)可平行分散式處理資訊，藉由輸入/輸出資料來學習訓練得到神經網路內部權重參數，而建構此非線性系統模型，充分表現出曲線近似（Curve-fitting）特性和非線性輸入/輸出映射的關係。RBF可以最小之網路架構提供最佳之普遍化歸納，因此適用於更複雜之系統，而達到更好之效能，以及較短之訓練時間，適用於故障偵測與分類系統。

The evolution of semiconductor manufacturing process on the enlargement of wafer size together with the shrink of feature size results in the difficulty of process control. In addition，faulty processes relatively increase. Tight process control then becomes an essential requirement in the fabs. Up to the present，SPC has been used as a tool for quality control. However，many process parameters exhibit correlated relationship and inevitable steady drift. Using SPC control charts sometimes leads to false alarms and erroneous judgments. Therefore，the major motivation of this research is to learn the characteristics of these process variations by using radial basis function (RBF) neural networks. Equipment malfunction and/or the faults can thus be detected and the false alarms can be avoided. Furthermore，the maintenance can be performed based on our provided diagnosis function in order to promote the overall equipment effectiveness.
Radial basis function neural networks have the capability of parallel computation. The neural networks are trained by the input-output data so that the internal weights of networks can be obtained. The constructed non-linear models have characteristics of curve-fitting and mapping relations. RBF networks can provide generalizations with minimum structures. Therefore，they are applicable to the complicated systems, especially for the purposes of fault detection and classification.

第一章 緒論................................ 1
1.1研究動機與目的 1
1.2研究方法 1
1.3文獻回顧 3
1.4論文架構 4
第二章 時間序列 6
2.1時間序列前言 6
2.2時間序列模式建立 7
2.3時間序列模式應用 8
2.4 AR(1)模型與SPC作為IC製程故障偵測………….10
第三章 類神經網路 13
3.1類神經網路 13
3.2幅狀函數神經網路 17
3.2.1幅狀函數神經網路前言 17
3.2.2類神經網路的神經元模型 18
3.2.3幅狀函數神經網路架構 20
3.2.4幅狀函數神經網路訓練學習演算法 23
第四章 幅狀基底函數類神經網路偵測系統 30
4.1製程變異之種類 30
4.2偵測系統設計 32
4.3偵測管制圖 35
4.4半導體製程異常狀態之偵測與監控 37
第五章 RBF在半導體製程失效偵測之應用 40
5.1離子植入機台之實驗 40
5.2電漿蝕刻機台之實驗 49
第六章 結論 55
6.1 綜合結論 55
6.2 未來方向與展望 56
參考資料 58

1. C.J. Spanos, “Statistical Process Control in Semi- conductor Manufacturing,” Proc. of IEEE, Vol. 80, No. 6, June, 1992.
2. C.J. Spanos, H.F. Guo, A. Miller, and J. Levine- Parrill, “Real-Time Statistical Process Control Using Tool Data,” IEEE Trans. on Semiconductor Manufacturing, Vol. 5, No. 4, Nov, 1992.
3. S.M. Wu and S.M. Pandit, Time Series and System Analysis With Applications, J. Wiley, N.Y., 1983.
4. R.S. Guo, A. Chen, C.L. Tseng, I.K. Fong, A. Yang, C.L. Lee, C.H. Wu, S. Lin, S.J. Huang, Y.C. Lee, S.G. Chang, and M.Y. Lee, “A real-time equipment monitoring and fault detection system,” Semiconductor Manu. Tech. Workshop, 1998.
5. Y. Guo, and K.J. Dooley, “Identification of Change Structure in Statistical Process Control,” Inter-national Journal of Production Research, Vol.30, No. 7, 1655-1669, 1992.
6. D.T. Pham, and E. Oztemel, “Control Chart Pattern Recognition Using Neural Networks,” Journal of Systems Engineering, Vol. 2, No. 4, 256-262, 1992.
7. C.S. Cheng “ Detecting Changes in the Process Mean Using Artificial Neural Networks Approach,” Journal Of Chinese Institute of Industial Engineers, 11(1), 47-54,1994.
8. G.E.P. Box, and G.M. Jenkins, “Time Series Analysis. Forecasting, and Control,” Holden-Day, Oakland, CA, 1970.
9. S. Haykin, Neural Networks, A Viacom Company, 1994.
10. J.-S. R. Jang, C.-T. Sun, E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall, Inc, 1997.
11. Y. Maki, K.A. Loparo, “A neural-network approach to fault detection and diagnosis in industrial processes,” IEEE Trans. Control Systems Technology, Vol. 5, No. 6, 529-541, Nov., 1997.
12. M.D. Baker, C.D. Himmel, G.S. May, “Time series modeling of reactive ion etching using neural networks,” IEEE Trans. Semiconductor Manufacturing, Vol. 8, No. 1, 62-71, Feb, 1995.
13. D. Stokes ; G.S. May, “ Real-time plasma etch control using in-situ sensors and neural networks,” IEEE International Conference on, Vol. 1, No. 1, 779 -783, 1999.
14. EATON NV-6200A AND AV ION IMPLANTATION SYSTEM TRAINING SUPPLEMENTS MANUAL
15. EATON NV-6200 SYSTEM DESIGN AND OPERATION
16. B. Zhang,; G.S. May, “Advanced Semiconductor Manufacturing Conference and Workshop” 1998. 1998 IEEE/SEMI, 61—65, 1998.
17. P.M.T. Broersen,; S. de Waele, “Efficient estimation of autocorrelation functions of random data with time series models” Decision and Control Proceedings of the 40th IEEE Conference on , Vol.3, pp.2532 -2537, 2001.
18. 葉怡成，類神經網路—模式應用與實作，五版，儒林圖書出版，台北市， 1998。
19. 蘇木春、張孝德，機器學習：類神經網路、模糊系統以及基因演算法則，全華科技出版，2000年。
20. 莊達人，VLSI製程技術，高利圖書有限公司，1995。
21. 廖德祿，黃俊智，RBF神經網路應用於非線性系統的適應控制，成功大學工程科學研究所碩士論文，1994。
22. 林宏達，徐偉晉，利用RBF 網路與SPC-EPC 系統建構相關性製程回饋與管制模式－以積層陶瓷電容晶片切割作業為例，朝陽科技大學工業工程與管理研究所碩士論文，2001。