Making Statistics Fun and Quality Management Simple!

SPC for the Process Industries

 

HOME

Training

Consulting

Successful Six Sigma

Auditing

ISO-9001:2000
ISO/TS-16949 Registration

MCG Experience

MCG Clients

Information Request

Thy Word Ministries

 

[ Statistical Process Control ] [ SPC for the Process Industries ] [ Working with Data ] [ Design of Experiments ]
[ Statistics Training ] [ Continuous Improvement Training ] [ ISO-9001 & TS-16949 Training ] [ Training Schedule ] [ Successful Six Sigma Training ] [ Quality Function Deployment ] [ Training Aids ]

Process industries such as paper and chemical present rather unique problems for SPC implementation.  Namely that several assumptions of X-Bar charts are violated:

Problems

bulletSamples or subgroups are usually limited to a size of one.
bulletA control chart with a sample size of one is not sensitive to small process shifts.   It would take on average over 16 samples to detect just a one and a half sigma shift in the process.
bulletSuccessive data points in continuous processes are often autocorrelated, i.e. related in value.  For example in the diagram below successive samples will be correlated do to mixing in the tank.

wpe1.jpg (6370 bytes)

Solutions

bulletExponentially Weighted Moving Average (EWMA) and Cumulative Sum (CUSUM) Charts provide an increased sensitivity to small shifts
bulletAutoregressive Integrated Moving Average (ARIMA) models provide a means to remove the noise in the data caused by autocorrelation.

These tools are mentioned in the course outline on the SPC page.

To request information send us an e-mail

All workshops can be held on-site!
For a rate quote call
860-940-7799
or e-mail:  info@mesacg.com

[ Home ]

Send mail to Mesa Consulting Group with questions or comments about this web site.
Copyright © 2008 Mesa Consulting Group, Inc.
Last modified: January 16, 2008