RECALCULATING TARGETS, NOT CONTROL LIMITS


RECALCULATING CONTROL LIMITS

With traditional control charts (and the nominal and target charts ), the control limits are recalculated when an improvement has been made to the process. An example of this is shown in Figure 13.8 with the range chart. When a reduction in process variation is detected (middle section), the control limits are recalculated ("Recalc") to reflect this change.

click to expand
Figure 13.8: Recalculating control limits.

RECALCULATING TARGET VALUES

For most of the applications of any short-run chart, the control limits are constant values that are not calculated to begin with, nor are they ever recalculated. To incorporate process improvement with these short-run methods , the control limits are left as is, and the target values are recalculated (see Figure 13.9).

click to expand
Figure 13.9: Recalculating target values.

Initially, when the actual process variation is the same as the expected ("Target Rbar"), the ratio of the subgroup range ("R Original") to the target Rbar value is close to 1, as shown in the Original Process section of Figure 13.9.

When a reduction in process variation occurs, the subgroup ranges are smaller ("R Reduced"), and the ratios are now less than 1 (middle section of Figure 13.9). When the target Rbar value is recalculated to reflect this new reduced expectation of process variation ("Target Rbar Recalc"), the numerator and denominator now match up, and their ratio is again close to 1 (see the "Recalculate Target Rbar" section in Figure 13.9).

This chart will display a good state of control as long as the process continues to operate in the improved state. There is no need to recalculate the limits or rescale the chart. Just recalculate the target value by using the data from the improved section and the appropriate formulas from Method 2 of the Target Values section.

The same concept applies to all the short-run charts that have constant control limits. The nominal and target charts have their control limits calculated directly from the plotted data, and these limits are recalculated in the same manner as traditional charts.




Six Sigma and Beyond. Statistical Process Control (Vol. 4)
Six Sigma and Beyond: Statistical Process Control, Volume IV
ISBN: 1574443135
EAN: 2147483647
Year: 2003
Pages: 181
Authors: D.H. Stamatis

flylib.com © 2008-2017.
If you may any questions please contact us: flylib@qtcs.net