Support Vector Data Description-based Multivariate Exponentially Weighted Moving Average Control Chart

Abstract

Abstract: The D2 control chart based on support vector data description (SVDD) has an advantage that it does not require a known sampling distribution for the process data. However, it uses only the current samples, leading to that it is insensitive to small shifts. To solve this problem, based on SVDD method, a multivariate exponentially weighted moving average (MEWMA) control chart (denoted as S-MEWMA) is proposed in this paper. Simulation results show that the S-MEWMA chart outperforms the D2 control chart no matter whether a process follows a normal or non-normal distribution.

Key words: support vector data description, multivariate exponentially weighted moving average(MEWMA) control chart, multivariate statistical process control

He Shu-guang, Qian Ting. Support Vector Data Description-based Multivariate Exponentially Weighted Moving Average Control Chart[J]. Industrial Engineering Journal , 2013, 16(1): 132-.

References

［1］Hotelling H. Multivariate quality control, illustrated by the air testing of sample bombsights［M］∥ New York:Eisenhart C, Hastay M W,Wallis W A. Techniques of Statistical Analysis, 1947:111-184. ［2］Montgomery D C. Introduction to statistical quality control ［M］. New Jersey: John Wiley & Sons, 2007:494-512. ［3］Woodall W H, Montgomery D C. Research issues and ideas in statistical process control ［J］. Journal of Quality Technology, 1999, 31(4):376-386. ［4］Hwang W, Runger G, Tuv E. Multivariate statistical process control with artificial contrasts ［J］. IIE Transactions, 2007, 39(6): 659-669. ［5］Macgregor J F, Kourti T. Statistical process control of multivariate processes ［J］. Control Engineering Practice，1995, 3(3): 403-441. ［6］Hawkins D M. Multivariate quality control based on regression-adjusted variables ［J］. Technometrics, 1991, 33(1):61-75. ［7］Lowry C A, Woodall W H, Champ C W, et al. A multivariate EWMA control chart ［J］. Technometrics, 1992, 34(1):46-53. ［8］Kramer H G, Schmin W. EWMA charts for multivariate time series ［J］. Sequential Analysis, 1997, 16(2):131-154. ［9］Bersimis S, Psarakis S, Panaretos J. Multivariate statistical process control charts: an overview ［J］. Quality & Reliability Engineering International, 2006, 23(5): 517-543. ［10］ Kouri T, MacGregor J F. Multivariate SPC methods for process and product monitoring ［J］. Journal of Quality Tecknology, 1996, 28(4): 409-428. ［11］Zhang Z, Zhu X, Jin J. SVC-based multivariate control charts for automatic anomaly detection in computer networks［EB/OL］.（2007-06-19）.http:∥ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4437933_tag=1. ［12］Tax D M J, Duin R P W. Support vector data description ［J］. Machine Learning, 2004, 54(1):45-66. ［13］Sukchotrar T. Data mining-driven approaches for process monitoring and diagnosis ［D］.Arlington: University of Texas, 2008. ［14］Sun R, Tsung F. A kernel-distance-based multivariate control chart using support vector methods ［J］. International Journal of Production Research, 2003, 41(13): 2975-2989. ［15］Kumar S, Choudhary A K, Kumar M, et al. Kernel distance-based robust support vector methods and its application in developing a robust K-chart［J］. International Journal of Production Research, 2006, 44(1):77-96. ［16］Sukchotrar T, Kim S B, Tsung F. One-class classification-based control charts for multivariate process monitoring ［J］. IIE Transaction, 2009, 42(2): 107-120.