Optimum variable-dimension EWMA chart for multivariate statistical process control

ABSTRACT The variable-dimension T2 control chart (VDT2 chart) was recently proposed for monitoring the mean of multivariate processes in which some of the quality variables are easy and inexpensive to measure while other variables require substantially more effort or expense. The chart requires most of the times that only the inexpensive variables be sampled, switching to sampling all the variables only when a warning is triggered. It has good ARL performance compared with the standard T2 chart, while significantly reducing the sampling cost. However, like the T2 chart, it has limited sensitivity to small and moderate mean shifts. To detect such shifts faster, we developed an exponentially weighted moving average (EWMA) version of the VDT2 chart, along with Markov chain models for ARL calculation, and software (made available) for optimizing the chart design. The optimization software, which is based on genetic algorithms, runs in Windows© and has a friendly user interface. The performance analysis shows the great gain in performance achieved by the incorporation of the EWMA procedure.

[1]  Denis Bouchard,et al.  Optimal Parameters , 1997, LACL.

[2]  Antonio Fernando Branco Costa,et al.  X charts with supplementary samples to control the mean and variance , 2000 .

[3]  Francisco Aparisi,et al.  Double sampling hotelling's T2 charts , 2008, Qual. Reliab. Eng. Int..

[4]  J. Edward Jackson,et al.  Principal Components and Factor Analysis: Part I - Principal Components , 1980 .

[5]  I. González,et al.  Principal alarms in multivariate statistical process control using independent component analysis , 2008 .

[6]  Ismael Sánchez,et al.  Principal Alarms in Multivariate Statistical Process Control , 2008 .

[7]  Stelios Psarakis,et al.  Multivariate statistical process control charts: an overview , 2007, Qual. Reliab. Eng. Int..

[8]  Ali Salmasnia,et al.  Change point detection in social networks using a multivariate exponentially weighted moving average chart , 2019, J. Inf. Sci..

[9]  Charles W. Champ,et al.  A multivariate exponentially weighted moving average control chart , 1992 .

[10]  Peihua Qiu,et al.  Multivariate Statistical Process Control Using LASSO , 2009 .

[11]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[12]  Antonio Fernando Branco Costa,et al.  X̄ Charts with Variable Parameters , 1999 .

[13]  J. Daudin,et al.  Double Sampling Charts , 1992 .

[14]  Antonio Fernando Branco Costa,et al.  X̄ charts with variable sample size , 1994 .

[15]  Robert C. Wolpert,et al.  A Review of the , 1985 .

[16]  Francisco Aparisi,et al.  Optimal parameters for CUSUM-FIR control charts for monitoring process mean , 2014 .

[17]  Eugenio K. Epprecht,et al.  A variable sampling interval EWMA chart for attributes , 2010 .

[18]  Antonio Fernando Branco Costa,et al.  X̄ Chart with Variable Sample Size and Sampling Intervals , 1997 .

[19]  Daniel W. Apley,et al.  A Factor-Analysis Method for Diagnosing Variability in Mulitvariate Manufacturing Processes , 2001, Technometrics.

[20]  Jean-Jacques Daudin,et al.  Double sampling X charts , 1992 .

[21]  Isabel González,et al.  Variable Selection for Multivariate Statistical Process Control , 2010 .

[22]  D. Montgomery,et al.  A Combined Adaptive Sample Size and Sampling Interval X Control Scheme , 1994 .

[23]  J. A. Nachlas,et al.  X charts with variable sampling intervals , 1988 .

[24]  W. H. Deitenbeck.  Introduction to statistical process control. , 1995, Healthcare facilities management series.

[25]  Douglas M. Hawkins,et al.  A General Multivariate Exponentially Weighted Moving-Average Control Chart , 2007 .

[26]  Russell R. Barton,et al.  PROCESS-ORIENTED BASIS REPRESENTATIONS FOR MLTLTIVARIATE PROCESS DIAGNOSTICS , 1996 .

[27]  J. B. Keats,et al.  X¯ chart with adaptive sample sizes , 1993 .

[28]  I. Jolliffe.  Principal Component Analysis and Factor Analysis , 1986 .

[29]  P. Croasdale,et al.  Control Charts for a Double-Sampling Scheme Based on Average Production Run Lengths , 1974 .

[30]  Francisco Aparisi,et al.  Hotelling's T2 control chart with adaptive sample sizes , 1996 .

[31]  Giovanna Capizzi,et al.  An Adaptive Exponentially Weighted Moving Average Control Chart , 2003, Technometrics.

[32]  Francisco Aparisi,et al.  Hotelling's T2 control chart with variable sampling intervals , 2001 .

[33]  Francisco Aparisi,et al.  T2 Control Charts with Variable Dimension , 2012 .

[34]  Fah Fatt Gan,et al.  Exponentially weighted moving average control charts with reflecting boundaries , 1993 .

[35]  Stefan H. Steiner.  Confirmation sample control charts , 1999 .

[36]  Fugee Tsung,et al.  LASSO-based multivariate linear profile monitoring , 2012, Ann. Oper. Res..

[37]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[38]  Douglas C. Montgomery,et al.  A review of multivariate control charts , 1995 .

[39]  Fugee Tsung,et al.  An adaptive dimension reduction scheme for monitoring feedback‐controlled processes , 2009, Qual. Reliab. Eng. Int..

[40]  Francisco Aparisi,et al.  Reducing sampling costs in multivariate SPC with a double-dimension T2 control chart , 2013 .

[41]  F. Aparisi,et al.  The variable sample size variable dimension T2 control chart , 2014 .

[42]  Giovanna Capizzi,et al.  A Least Angle Regression Control Chart for Multidimensional Data , 2011, Technometrics.

[43]  James M. Lucas,et al.  Exponentially weighted moving average control schemes: Properties and enhancements , 1990 .

[44]  Wei Jiang,et al.  High-Dimensional Process Monitoring and Fault Isolation via Variable Selection , 2009 .

[45]  Mahmoud A. Mahmoud,et al.  The Inertial Properties of Quality Control Charts , 2005, Technometrics.