Study on Vacuum Pump Monitoring Using MPCA Statistical Method

MPCA 기반의 통계기법을 이용한 진공펌프 상태진단에 관한 연구

  • Sung D. (Seoul National University) ;
  • Kim J. (Seoul National University) ;
  • Jung W. (Seoul National University) ;
  • Lee S. (Seoul National University) ;
  • Cheung W. (Korea Research Institute of Standards and science) ;
  • Lim J. (Korea Research Institute of Standards and science) ;
  • Chung K. (Korea Research Institute of Standards and science)
  • Published : 2006.07.01

Abstract

In semiconductor process, it is so hard to predict an exact failure point of the vacuum pump due to its harsh operation conditions and nonlinear properties, which may causes many problems, such as production of inferior goods or waste of unnecessary materials. Therefore it is very urgent and serious problem to develop diagnostic models which can monitor the operation conditions appropriately and recognize the failure point exactly, indicating when to replace the vacuum pump. In this study, many influencing factors are totally considered and eventually the monitoring model using multivariate statistical methods is suggested. The pivotal algorithms are Multiway Principal Component Analysis(MPCA), Dynamic Time Warping Algorithm(DTW Algorithm), etc.

반도체 공정에 사용되는 진공펌프는 가혹한 운전조건과 비선형적 특성으로 인하여 고장시점을 정확히 예측해내기가 어려운데 이로 인해 불량품이 양산되거나 불필요한 재원이 낭비되는 등의 문제가 발생하게 된다. 따라서 펌프의 운전상태를 올바르게 모니터링하고 고장 지점을 정확히 인지해 적절한 펌프 교체 시점을 알려주는 진공펌프 상태진단 모델의 개발은 매우 시급하고도 중대한 문제라 할 수 있겠다. 본 연구에서는 다변량 통계기법을 이용하여 영향력 있는 인자들을 종합적으로 고려하였으며 최종적으로 Hotelling's T2 통계량을 이용한 진공펌프 상태진단 모델을 제안하였다. 핵심적인 알고리즘으로는 Multiway Principal Component Analysis(MPCA)와 Dynamic Time Warping Algorithm(DTW Algorithm) 기법 등이 사용되었다.

Keywords

References

  1. Robert L. Mason, and John C. Young, Multivariate Statistical Process Control with Industrial Applications, (ASA SIAM, Philadelphia, 2002), Chap. 1-6
  2. Athanassios Kassidas, John F. MacGregor, and Paul A. Taylor, AIChE Journal 44, 864 (1998) https://doi.org/10.1002/aic.690440412
  3. Rasmus Bro and Age K. Smilde, Journal of Chemometrics 17, 16 (2003) https://doi.org/10.1002/cem.773
  4. Sergio Valle, Weihua Li, and S. Joe Qin, Ind. Eng. Chem. Res. 38, 4389 (1999) https://doi.org/10.1021/ie990110i
  5. Robert L. Mason, Young-min Chou, and John C. Young, Journal of Quality Technology 33, 466 (2001)
  6. Elaine Martin, Julian Morris, and Steven Lane, IEEE Control, Systems Magazine, 26 (2002)
  7. Jong-Min Lee, ChangKyoo Yoo, and In-Beum Lee, Computers & Chemical Engineering 27, 1903 (2003) https://doi.org/10.1016/S0098-1354(03)00151-0
  8. Jong-Min Lee, ChangKyoo Yoo, and In-Beum Lee, Journal of Biotechnology 110, 119 (2004) https://doi.org/10.1016/j.jbiotec.2004.01.016
  9. Henk-Jan Ramaker, Eric N.M. van Sprang, Johan A. Westerhuis, and Age K.Smilde, Analytica Chimica Acta 498, 133 (2003) https://doi.org/10.1016/j.aca.2003.08.045
  10. V. Pravdova, B. Walczak, and D.L. Massart, Analytica Chimica Acta 456, 77 (2002) https://doi.org/10.1016/S0003-2670(02)00008-9
  11. J. Edward Jackson, A User's Guide to Principal Components (John Wiley & Sons, Inc., Canada, 1991), Chap. 1-2