An optimization design of the 3-EWMA scheme for monitoring mean shifts

This article presents an algorithm for the optimization design of the three exponentially weighted moving average control chart scheme (3-EWMA scheme in short) for monitoring a range of mean shifts. The design algorithm optimizes the charting parameters of the 3-EWMA scheme, based on extra quadratic loss function. The results of comparative studies and an example show that the optimal 3-EWMA scheme always outperforms the basic 3-EWMA scheme, as well as the other EWMA charts under different specifications. According to a 2k factorial experiment, the optimal 3-EWMA scheme outperforms the main competitor, the basic 3-EWMA scheme, by more than 15 %, on average. Although the design of the optimal 3-EWMA scheme is more difficult than that of the conventional EWMA charts, it can be easily computerized. Moreover, this article provides the statistical process control (SPC) practitioners with a design table to facilitate the designs of the 3-EWMA schemes. From this design table, the users can directly find the optimal values of the charting parameters according to the design specifications. In general, this article will help to enhance the detection effectiveness of the 3-EWMA scheme, and facilitate its applications in SPC.

[1]  Karl-Heinz Waldmann,et al.  Design of double CUSUM quality control schemes , 1996 .

[2]  Philippe Castagliola,et al.  What are the best sample sizes for the Xbar and CUSUM charts , 2011 .

[3]  P. Robinson,et al.  Average Run Lengths of Geometric Moving Average Charts by Numerical Methods , 1978 .

[4]  S. W. Roberts.  Control chart tests based on geometric moving averages , 2000 .

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

[6]  Vladimir Dragalin.  The design and analysis of 2-CUSUM procedure , 1997 .

[7]  Francisco Aparisi,et al.  Economic design of EWMA control charts using regions of maximum and minimum ARL , 2005 .

[8]  Emmanuel Yashchin,et al.  Some aspects of the theory of statistical control schemes , 1987 .

[9]  Douglas C. Montgomery,et al.  Introduction to Statistical Quality Control , 1986 .

[10]  Douglas C. Montgomery,et al.  Optimization Problems and Methods in Quality Control and Improvement , 2000 .

[11]  Stefan H. Steiner,et al.  Grouped data exponentially weighted moving average control charts , 2008 .

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

[13]  Rickie J. Domangue,et al.  Some omnibus exponentially weighted moving average statistical process monitoring schemes , 1991 .

[14]  Marion R. Reynolds,et al.  Should Observations Be Grouped for Effective Process Monitoring? , 2004 .

[15]  Emmanuel Yashchin,et al.  On the Analysis and Design of CUSUM-Shewhart Control Schemes , 1985, IBM J. Res. Dev..

[16]  Fugee Tsung,et al.  CUSUM and EWMA multi-charts for detecting a range of mean shifts , 2007 .

[17]  Zhang Wu,et al.  Optimal average sample number of the SPRT chart for monitoring fraction nonconforming , 2013, Eur. J. Oper. Res..

[18]  Zhang Wu,et al.  A combined synthetic and np scheme for detecting increases in fraction nonconforming , 2012, Comput. Ind. Eng..

[19]  Herbert Moskowitz,et al.  Joint economic design of EWMA control charts for mean and variance , 2008, Eur. J. Oper. Res..

[20]  John R. English,et al.  Economic designs of constrained EWMA and combined EWMA-X¯ control schemes , 2001 .

[21]  Ross Sparks,et al.  CUSUM Charts for Signalling Varying Location Shifts , 2000 .

[22]  Mei Yang,et al.  Optimization designs of the combined Shewhart-CUSUM control charts , 2008, Comput. Stat. Data Anal..

[23]  Marion R. Reynolds,et al.  Comparisons of Some Exponentially Weighted Moving Average Control Charts for Monitoring the Process Mean and Variance , 2006, Technometrics.

[24]  James M. Lucas,et al.  Combined Shewhart-CUSUM Quality Control Schemes , 1982 .

[25]  Thong Ngee Goh,et al.  Design and application of exponential chart for monitoring time-between-events data under random process shift , 2011 .

[26]  S. Albin,et al.  An X and EWMA chart for individual observations , 1997 .

[27]  Morais Manuel Cabral,et al.  Combined CUSUM–Shewhart Schemes for Binomial Data , 2006 .

[28]  Fugee Tsung,et al.  Dual CUSUM control schemes for detecting a range of mean shifts , 2005 .

[29]  Francisco Aparisi,et al.  Design and optimization of EWMA control charts for in-control, indifference, and out-of-control regions , 2007, Comput. Oper. Res..

[30]  Yu Tian,et al.  Weighted-loss-function CUSUM chart for monitoring mean and variance of a production process , 2005 .

[31]  Douglas C. Montgomery,et al.  Research Issues and Ideas in Statistical Process Control , 1999 .

[32]  Daniel W. Apley,et al.  Journal of Quality Technology: Message from the editor , 2010 .

[33]  Longcheen Huwang,et al.  New EWMA control charts for monitoring process dispersion , 2010, Comput. Stat. Data Anal..

[34]  Philippe Castagliola,et al.  Computational Statistics and Data Analysis an Ewma Chart for Monitoring the Process Standard Deviation When Parameters Are Estimated , 2022 .

[35]  G. Lorden.  PROCEDURES FOR REACTING TO A CHANGE IN DISTRIBUTION , 1971 .

[36]  Morton Klein.  Composite Shewhart-EWMA statistical control schemes , 1996 .

[37]  Y. K. Chen,et al.  Design of EWMA and CUSUM control charts subject to random shift sizes and quality impacts , 2007 .

[38]  Zhang Wu,et al.  A sum of squares double exponentially weighted moving average chart , 2011, Comput. Ind. Eng..

[39]  Sujin Kim,et al.  Optimal Design of a CUSUM Chart for a Mean Shift of Unknown Size , 2010 .

[40]  S. Crowder.  Average Run Lengths of Exponentially Weighted Moving Average Control Charts , 1987 .

[41]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[42]  Zhang Wu,et al.  Design of EWMA control chart for minimizing the proportion of defective units , 2012 .

[43]  Charles W. Champ,et al.  The Performance of Exponentially Weighted Moving Average Charts With Estimated Parameters , 2001, Technometrics.

[44]  Yu-Chang Lin,et al.  Robustness of the EWMA and the combined X¯–EWMA control charts with variable sampling intervals to non-normality , 2011 .

[45]  James M. Lucas,et al.  Average Run Lengths for Exponentially Weighted Moving Average Control Schemes Using the Markov Chain Approach , 1990 .

[46]  Acheson J. Duncan,et al.  The Economic Design of X Charts Used to Maintain Current Control of a Process , 1956 .

[47]  D. Hawkins,et al.  Cumulative Sum Charts and Charting for Quality Improvement , 1998, Statistics for Engineering and Physical Science.

[48]  Eugenio K. Epprecht,et al.  Performance Comparisons of EWMA Control Chart Schemes , 2010 .

[49]  William H. Woodall,et al.  CUSUM charts with variable sampling intervals , 1990 .

[50]  Petri Helo,et al.  Optimization design of a CUSUM control chart based on taguchi’s loss function , 2008 .

[51]  Mei Yang,et al.  Optimization designs and performance comparison of two CUSUM schemes for monitoring process shifts in mean and variance , 2010, Eur. J. Oper. Res..