Abstract
The cumulative sum scheme (CUSUM) and the adaptive control chart are two approaches to improve chart performance in detecting process shifts. A weighted loss function CUSUM scheme (WLC) is able to monitor both the mean shift and the increasing variance shift by manipulating a single chart. This paper investigates the WLC scheme with a variable sample sizes (VSS) feature. A design procedure is firstly proposed for the VSS WLC scheme. Then, the performance of the chart is compared with that of four other competitive control charts. The results show that the VSS WLC scheme is more powerful than the other charts from an overall viewpoint. More importantly, the VSS WLC scheme is simpler to design and operate. A case study in the manufacturing industry is used to illustrate the chart application. The proposed VSS WLC scheme suits the scenario where the strategy of varying sample sizes is feasible and preferable to pursue a high capability of detecting process variations.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Abbreviations
- CUSUM:
-
Cumulative sum chart
- WL :
-
Weighted loss function chart or statistic used by this chart
- WLC :
-
Weighted loss function CUSUM scheme
- CCC :
-
Joint three one-sided CUSUM chart (I, D and V charts)
- I :
-
CUSUM chart for detecting increasing mean shifts
- D :
-
CUSUM chart for detecting decreasing mean shifts
- V :
-
CUSUM chart for detecting increasing variance shifts
- VSS:
-
Variable sample sizes
- VSI:
-
Variable sampling intervals
- VSSI:
-
Variable sample sizes and variable sampling intervals
- A t :
-
Statistic used by a WLC scheme
- λ :
-
Weighting factor in a WLC scheme
- w A , H A :
-
Warning and control limits of a WLC scheme
- k A :
-
Reference parameter of a WLC scheme
- \(LWL_{{\overline{X} }} ,\;UWL_{{\overline{X} }} \) :
-
Lower and upper warning limits of an \(\overline{X} \) chart
- \(LCL_{{\overline{X} }} ,\;UCL_{{\overline{X} }} \) :
-
Lower and upper control limits of an \(\overline{X} \) chart
- UWL S1, UCL S1 :
-
Warning and control limits of an S chart when using relax samples
- UWL S2, UCL S2 :
-
Warning and control limits of an S chart when using alert samples
- w I , H I , k I :
-
Warning limit, control limit and reference parameter of an I chart
- w D , H D , k D :
-
Warning limit, control limit and reference parameter of a D chart
- w V , H V , k V :
-
Warning limit, control limit and reference parameter of a V chart
- x :
-
Quality parameter
- μ, σ 2 :
-
Mean and variance of x
- \(\overline{x} ,\;s\) :
-
Sample mean and standard deviation
- μ 0, δ 0 :
-
In-control mean and standard deviation
- μ d , δ d :
-
Out-of-control mean and standard deviation
- n 1, n 2 :
-
Relax and alert sample sizes
- h :
-
Sampling interval
- B 2 :
-
Stabilised probability for a process being in a warning zone
- ATS :
-
Average time to signal
- ATS 0 :
-
In-control average time to signal
- ATS min :
-
Used to store the minimum ATS during a chart design
- ARATS :
-
Average ratios of ATSs
- ARATS s :
-
ARATS in a small shift region
- ARATS m :
-
ARATS in a moderate shift region
- ARATS l :
-
ARATS in a large shift region
- ARATS o :
-
ARATS in an overall shift region
- \(\overline{{ARATS}} \) :
-
Average of ARATS values for a chart over all runs
- τ :
-
Allowed minimum in-control ATS
- R :
-
Allowed maximum in-control average inspection ratio
- n max :
-
Allowed maximum sample size
- \(\delta _{{\mu d}} ,\;\delta _{{\sigma d}} \) :
-
Selected mean shift and variance shift for chart design
- \(\widehat{\delta }_{\mu } ,\;\widehat{\delta }_{\sigma } \) :
-
Estimated mean shift and variance shift
- m 1, m 2 :
-
Numbers of relax and alert samples taken after a change point
- \(\overline{x} _{{ij}} ,\;s^{2}_{{ij}} \) :
-
Sample mean and variance of the jth sample of size n i after a change point
References
Montgomery DC (2001) Introduction to statistical quality control, 4th edn. Wiley, New York
Tagaras G (1998) A survey of recent developments in the design of adaptive control charts. J Qual Technol 30(3):212–231
Wu Z, Luo H (2004) Optimal design of the adaptive sample size and sampling interval np control chart. Qual Reliab Eng Int 20(6):553–570
Prabhu SS, Runger GC, Keats JB (1993) An adaptive sample size \(\overline{X} \) chart. Int J Prod Res 31(12):2895–2909
Zimmer LS, Montgomery DC, Runger GC (1998) Evaluation of a three-state adaptive sample size \(\overline{X} \) control chart. Int J Prod Res 36(3):733–743
Costa AFB (1999) Joint \(\overline{X} \) and R charts with variable sample sizes and sampling intervals. J Qual Technol 31(4):387–397
Annadi HP, Keats JB, Runger GC, Montgomery DC (1995) An adaptive sample size CUSUM control chart. Int J Prod Res 33(6):1605–1616
Arnold JC, Reynolds MR Jr (2001) CUSUM control charts with variable sample sizes and sampling intervals. J Qual Technol 33:66–81
Reynolds MR Jr, Amin RW, Arnold JC, Nachlas JA (1988) \(\overline{X} \) charts with variable sampling intervals. Technometrics 30(2):181–192
Daudin JJ (1992) Double sampling \(\overline{X} \) charts. J Qual Technol 24(2):78–87
Das TK, Jain V, Gosavi A (1997) Economic design of dual-sampling-interval policies for \(\overline{X} \) charts with and without run rules. IIE Trans 29(6):497–506
Gan FF (1995) Joint monitoring of process mean and variance using exponentially weighted moving average control charts. Technometrics 37(4):446–453
Reynolds MR Jr, Amin RW, Arnold JC (1990) CUSUM charts with variable sampling intervals. Technometrics 32:371–384
Reynolds MR Jr, Stoumbos ZG (2004) Control charts and the efficient allocation of sampling resources. Technometrics 46(2):200–214
Reynolds MR Jr, Glosh BK (1981) Designing control charts for means and variances. ASQC Quality Congress Transactions, pp 400–407
Domangue R, Patch SC (1991) Some omnibus exponentially weighted moving average statistical process monitoring schemes. Technometrics 33(3):299–313
Grabov P, Ingman D (1996) Adaptive control limits for bivariate process monitoring. J Qual Technol 28(3):320–330
Sullivan JH, Woodall WH (1996) A control chart for preliminary analysis of individual observations. J Qual Technol 28(3):265–278
Amin RW, Wolff H, Besenfelder W, Baxley R Jr (1999) EWMA control charts for the smallest and largest observations. J Qual Technol 31(2):189–206
Chen G, Cheng SW, Xie HS (2001) Monitoring process mean and variability with one EWMA chart. J Qual Technol 33(2):223–233
Cyrus D (1997) Statistical aspects of quality control. Academic Press, New York
Wu Z, Tian Y, Zhang S (2005) Adjusted-loss-function charts with variable sample sizes and sampling intervals. J Appl Stat 32(3):221–242
Spiring FA, Yeung AS (1998) A general class of loss functions with individual applications. J Qual Technol 30:152–162
Wu Z, Shamsuzzaman M, Pan ES (2004) Optimization design of control charts based on Taguchi’s loss function and random process shifts. Int J Prod Res 42(2):379–390
Wu Z, Tian Y (2005) Weighted-loss-function CUSUM chart for monitoring mean and variance of a production process. Int J Prod Res 43(14):3027–3044
Zhang S, Wu Z (2005) Monitoring the process mean and variance by the WLC scheme with variable sampling intervals. IIE Trans 38(6):377–387
Reynolds MR Jr, Arnold JC (2001) EWMA control charts with variable sample sizes and variable sampling intervals. IIE Trans 33(6):511–530
Duncan AJ (1956) The economic design of \(\overline{X} \) charts used to maintain current control of a process. J Am Stat Assoc 51:228–241
Reynolds MR Jr, Stoumbos ZG (2001) Monitoring the process mean and variance using individual observations and variable sampling intervals. J Qual Technol 33(2):181–205
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, S., Wu, Z. A CUSUM scheme with variable sample sizes for monitoring process shifts. Int J Adv Manuf Technol 33, 977–987 (2007). https://doi.org/10.1007/s00170-006-0544-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-006-0544-0