資料前處理對虛擬量測而言，是非常重要之一環，因為資料品質不佳，會嚴重影響虛擬量測之預測精度。資料前處理係透過與製程工程師討論並對資料進行確認與檢查，選取影響製程之重要變數，並對異常資料予以剔除，進而達到提昇虛擬量測精度之目標。

本研究旨在探討資料前處理之變數篩選法則，經由蒐集以往文獻及統計方法上關於參數篩選之方法，針對這些方法進行實驗及分析其結果較佳或不佳之原因，並透過參數分類與篩選實驗，期能找出影響VMS精度之變數。本研究採用之變數篩選方法計有逐步選取法、逐步選取修正法、偏權擾動敏感度分析法、以類神經網路為基之逐步選取法、專家經驗選取法等五種，經實驗結果顯示偏權擾動敏感度分析法在篩選變數時，由於遺漏相當多重要的資訊，導致進行二個案例之預測精度相較於其它篩選方法為差。另實驗結果亦發現二個案例均顯示使用逐步選取法、逐步選取修正法及以類神經網路為基之逐步選取法在小樣本實驗之精度較佳，但如增加測試樣本則其精度會變差，而專家經驗選取法在小樣本實驗中雖非最佳解，但精度相當穩定且能維持在規格內。因此，就本研究之案例而言，採用專家經驗選取法是較佳的方案。

Incorrectness, fragment and asynchrony of collected data may lead to inaccurate virtual metrology results. To improve virtual metrology accuracy, data preprocess is extremely essential. Data preprocess deals with the processes of data examination and sifting. Considering advices from process engineers, important variables of the production process are selected and anomalous data are deleted before conducting sifting rules so as to improve the accuracy of virtual metrology.

This work investigates five sifting rules of independent variables in data preprocess. They are stepwise selection algorithm (SS), modified stepwise selection algorithm (Modified SS), sensitivity analysis of neural network (SA), SS rule on neural network, and expert-recommended rule. Analyses and experiments of two illustrative examples are executed to evaluate the performance of these sifting rules. This work further attempts to find out the key variables that affect the VMS accuracy most by classifying and sifting all the variables. The experimental results show that, due to missing a lot of important data, the sensitivity analysis of neural network is proved to be the worst in conjecture accuracy of all the sifting rules. In addition, the results also show that the stepwise selection algorithm, modified stepwise selection algorithm, and SS rule on neural network perform well in conjecture accuracy when the process-data sample size is small. However, if the sample size becomes large, the conjecture accuracy may perform poorly. On the contrary, when the rule of considering all of expert-recommended variables is applied, in the case of small sample size, its conjecture accuracy may be slightly worse than those of the SS rules, but still acceptable; while, in the case of large sample size, the conjecture accuracy of the expert-recommended rule is still acceptable but not those of the SS rules. In conclusion, the rule of considering all of expert-recommended variables is recommended.

[1] A.C. Diebold, “Overview of Metrology Requirements based on the
1994National Technology Roadmap for Semiconductor,” in Proc. of IEEE/SEMI
Advanced Semiconductor Manufacturing Conference and Workshop, pp. 50-60,
November 1995.

[2] 2003 International Technology Roadmap for Semiconductors (ITRS), December
2003. http://public.itrs.net/

[3] Y.-C. Chang and F.-T. Cheng,"Application Development of Virtual Metrology
in Semiconductor Industry, in Pro. of the 31st Annual Conference of the
IEEE Industrial Electronics (IECON 2005), Raleigh, North Carolina, USA,
pp. 124-129, November 2005.

[4] T.-H. Lin, M.-H. Hung, R.-C. Lin and F.-T. Cheng, “A Virtual Metrology
Scheme for Predicting CVD Thickness in Semiconductor Manufacturing,” in
Proc. Of IEEE International Conference on Robotics and Automation, 2006.

[5] Y.-C. Su, M.-H. Hung, F.-T. Cheng and Y.-T. Chen, " A Processing Quality
Prognostics Scheme for Plasma Sputtering in TFT-LCD Manufacturing," IEEE
Transactions on Semiconductor Manufacturing , vol. 19, issue 2, pp. 183- 194, 2006.

[6] International Sematech, “Equipment Engineering System Guideline v2.5”,
Nov 2002. http://www.sematech.org/.

[7] S. F. Lee and C. J. Spanos, "Prediction of Wafer State After Plasma
Processing Using Real-Time Equipment Data,” IEEE Transactions on
Semiconductor Manufacturing, vol. 8, no.3, pp. 252-261, August 1995.

[8] B. Kim and K. Kim, “Prediction of profile surface roughness in CHF3 /CF4
plasma using neural network,” Applied Surface Science, 222 (2004) 17-22.

[9] B. Kim, and G. S. May, “An Optimal Neural Network Process Model for
Plasma Etching,” IEEE Transactions on Semiconductor Manufacturing, vol.
7, no. 1, pp. 12-21, February 1994.86

[10] T. Matsuura, “An application of neural network for selecting feature
parameters in machinery diagnosis,” Journal of Materials Processing
Technology, 157–158 (2004) 203–207.

[11] E. W. Steyerberg, J. C. Eijkemans, and J. Dik F. Habbema, “Stepwise
Selection in Small Data Sets: A Simulation Study of Bias in Logistic
Regression Analysis,” Journal of Clinical Epidemiology, Vol. 52, No. 10,
pp. 935–942, 1999.

[12] L. Xu, W. J. Zhang, “Comparison of different methods for variable
selection,” Analytica Chimica Acta, Vol. 446, pp. 477–483, 2001.

[13] M.Lu, S. M. AbouRizk, and U. H. Hermannm, “Sensitivity Analysis Of Neural
Networks In Spool Fabrication Productivity Studies,” Journal of Computing
in Civil Engineering, Volume 15, Issue 4, pp. 299-308, 2002.

[14] L. Jenkins, M. Anderson, “A multivariate statistical approach to
reducing the number of variables in data envelopment analysis,” European
Journal of Operational Research, Vol. 147, pp. 51–61,2003.

[15] E. Vigneau, E.M. Qannari and D. Bertrand, “A new method of regression on
latent variables Application to spectral data,” Chemometrics and
Intelligent Laboratory Systems, Vol. 63, pp.7– 14, 2002.

[16] J. D. Olden, M. K. Joy and R. G. Death, “An accurate comparison of
methods for quantifying variable importance in artificial neural networks
using simulated data,” Ecological Modelling, Vol. 178, pp. 389–397,
2004.

[17] K. V. Montfort, C. Bijleveld, “Dynamic analysis of multivariate panel
data with non-linear transformations,” Journal of Mathematical
Psychology, Vol.48, pp.322–333, 2004.

[18] R. Leardi, M. B. Seasholtz and R. J. Pell, “Variable selection for
multivariate calibration using a geneticalgorithm: prediction of additive
concentrations in polymer films from Fourier transform-infrared spectral
data,” Analytica Chimica Acta, Vol. 461, pp. 189–200, 2002.

[19] L. H. Chiang, R. J. Pell, “Genetic algorithms combined with discriminant
analysis for key variable identification,” Journal of Process Control,
Vol. 14, pp.143–155, 2004.

[20] 林嶸銓 「通用型虛擬量測機制與系統」，國立成功大學製造工程研究所碩士論文，
2005.

[21] 周乃昉，鄭子璉，林柏承 「應用類神經網路於颱風降雨量的預測」，第十一屆水利
工程研討會論文集，台灣，台北，pp. C23-C28, 2000

[22] 蘇朝墩 「品質工程」，中華民國品質學會，2003.

[23] 陳順宇 「多變量分析」，三版，華泰書局，2004.

[24] 陳順宇 「迴歸分析」，三版，華泰書局，2000.

[25] 陳順宇，鄭碧娥 「統計學」，四版，華泰書局，2004.

[26] 張智星 「MATLAB程式設計」，清蔚科技，2004.

[27] 洪維恩 「C語言教學手冊」，博碩文化，2000.