M3D1: Statistical Process Control

Control charts show the variation in a measurement during the time period that the process is
observed. Process control charts are fairly simple-looking connected-point charts. The points are plotted
on an x/y axis with the x-axis usually representing time. The plotted points are usually averages of
subgroups or ranges of variation between subgroups, and they can also be individual measurements.
Some additional horizontal lines representing the average measurement and control limits are drawn
across the chart. Notes about the data points and any limit violations can also be displayed on the chart.

A control chart shows if a process is in control or out of control. They show the variance of the
output of the process over time. They compare this variance against upper and lower limits to see if it
fits within normal variation levels. If it is then the process is in control and any variance is normal and
inherent in the process. If it is outside the limits or has non-natural points the process is out of control.

The text shows three warning signals that a process may be out of control:

1. A point lies beyond 3 standard deviations of the mean

2. There are nine consecutive points that fall on one side of the mean
3. At least 2 of 3 consecutive points lie more than 2 standard deviations from the mean
(2012,p.256)

Control charts are used in the six sigma (6σ) process improvement methodology. This was
developed by Motorola and became famous when Jack Welch introduced it to GE in the 1990’s. Control
charts could be used to improve quality in two ways for my job. We deal with material which undergoes
strict quality assurance testing prior to installation and we perform multiple forms of nondestructive
testing after installation is complete. Control charts could be used to track the batches of material to
ensure that the construction process is up to snuff. Secondly, we train approximately 1440 junior
personnel a year and make them into nuclear operators. Control charts allow us to track their learning
process either by individual, job, or class in order to ensure that they are being trained correctly.

References:

Larson, R., & Farber, B. (2012). Elementary statistics: Picturing the world. (5th ed., p. 256). Boston:
Prentice Hall.