Using Independent Component Analysis Based Process Monitoring in TFT-LCD Manufacturing

應用獨立成分分析於TFT-LCD製程變異偵測

10.29977/JCIIE.200605.0010

曾彥馨(Yan-Hsin Tseng)；蔡篤銘(Du-Ming Tsai)

獨立成分分析 ； 管制圖 ； 統計品質管制 ； ICA ； Statistical process control ； TFT-LCD

工業工程學刊

23卷3期（2006 / 05 / 01）

262 - 267

英文

顯示器(Display)是資訊時代人們訊息傳遞與溝通之重要界面，平面顯示器(Flat-Panel Displays, FPD)具有輕薄與可攜性更加帶給人們許多生活上之便利，形成了繼積體電路後，突飛猛進的新科技領域。大量生產下，良率是影響製造成本的主要因素，透過對關鍵製程參數的監測能夠於製程中即時有效的提升良率與避免材料的浪費。本研究導入獨立成分分析(Independent Component Analysis, ICA)於TFT面板之製程參數變異偵測，偵測對象選定為總斜度變異量(Total Pitch variance, TP)，總斜度變異量是一個關鍵監控參數，主要目的為觀測對組工程中Array基板與彩色濾光片(Color Filter, CF)對組位移(Assembly shift)的變異量，該變異量會形成如對組位移造成顯示畫面不均勻的斑(MURA)或漏光之現象，進而使得顯示器出現大量的微亮點，透過總斜度變異量的監控可以有效回饋生產線及時且快速之製程變異資訊，避免大量不良品的產生。本研究透過ICA分別出製程參數資料之獨立成分，針對獨立成分資訊即可明顯分辨出製程變異。相對於目前TFT-LCD的製程變異偵測多採用傳統的統計管制圖，如使用平均數管制圖、全距管制圖與EWMA(Exponentially Weighted Moving Average)管制圖皆無法獲得良好之變異偵測結果，其中總斜度變異量所重視的平均數的位移皆無法偵測。經實驗驗證本研究採用之ICA方法對TFT面板型態變異量監控具有良好效果。

Large-sized Flat-Panel Displays (FPDs) have become increasingly important for use in PC monitors and TVs. To improve the yield of Liquid Crystal Display (LCD) panels, process control becomes a critical task in LCD manufacturing. In this paper we propose a control chart based on Independent Component Analysis (ICA) to monitor TFT-LCD process variations. The proposed method can be effectively used in monitoring an LCD critical process parameter called Total Pitch (TP). TP is a parameter that is used to control alignment errors in the TFT-LCD process. TP variations may cause serious defects like mura (brightness unevenness of a panel) and small bright points on the display area of LCD panels. Since the collected data may be a mixture of noise and different source signals, ICA is first applied to separate mixed signals into independent data. Further, X-bar and R control charts are used to monitor the separated source signals. Experimental results on real measured TP data collected from the TFT-LCD process showed that the proposed method can reliably detect process variation.

1. Tseng Y.H.,Tsai D.M.(2005).Using Independent Component Analysis for Process Monitoring in TFT-LCD Manufacturing.The 3rd ANQ Congress & The 19th Asia Quality Symposium,20-23.
   連結：
2. Bell, A. J.,Sejnowski, T. J.(1995).An information-maximization approach to blind separation and blind deconvolution.Neural Computation.
3. Borror, C.,Champ, C.,Rigdon, S.(1998).EWMA control charts for Poisson data.Journal of Quality Technology,30,352-361.
4. Borror, C.,Montgomery, D.,Runger, G.(1999).Robustness of the EWMA control charts to non-normality.Journal of Quality Technology,31(3),309-316.
5. Crowder, S. A.(1987).Simple method for studying run-length distribution of exponentially weighted moving average charts.Technometrics,29,401-407.
6. Crowder, S. A.(1989).Design of exponentially weighted moving average schemes.Journal of Quality Technology,21,155-162.
7. Gelle, G.,Colas, M.,Serviere, C.(2001).Blind source separation: a tool for rotating machine monitoring by vibrations analysis.J Sound Vibration,248,865-85.
8. Harris, T.J.,Ross, W.H.(1991).Statistical process control procedures for correlated observations.The Canadian Journal of Chemical Engineering,69,48-57.
9. Hunter, J.(1986).The exponential weighted moving average.Journal of Quality Technology,18,203-209.
10. FastICA Package, Online Available
11. Hyvärinen, A.,Oja, E.(2000).Independent component analysis: algorithms and applications.Neural Computation.
12. Hyvärinen,J. Karhunen,E. Oja(2001).Independent Component Analysis.
13. Kano, M.,Tanaka, S.,Hasebe, S.,Hashimoto, I.,Ohno, H.(2003).Monitoring of independent components for fault detection.AIChE J.
14. Li, W. Gu, F.,Ball, A. D.,Leung, A. Y. T.,Phipps, E.(2001).A study of the noise from diesel engines using the independent component analysis.Mech Syst Signal Process.
15. Lucas, J.,Saccucci, M.(1990).Exponentially weighted moving average control schemes: Properties and enhancements.Technometrics,32,1-12.
16. MacGregor, J.,Harris, T.(1993).The exponentially weighted moving variance.Journal of Quality Technology,25(1),106-118.
17. Montegomery, D. C.(1985).Introduction to Statistical Quality Control
18. Montegomery, D.C.,Mastrangelo, C.M.(1991).Some statistical process control methods for auto-correlated data.Journal of Quality Technology,23,179-193.
19. Roberts, S.(1959).Control chart tests based on geometric moving averages.Technometrics,1,239-250.

1. 陳偉星(2012).Variation Pattern Identification and Fault Diagnosis of Solder Paste Deposit by Using Independent Component Analysis.品質學報,19(1),21-39.
2. (2010).Data mining for yield enhancement in TFT-LCD manufacturing: an empirical study.工業工程學刊,27(2),140-156.