5.20. Consider the control chart shown in Exercise 5.17.
Would the use of warning limits reveal any
potential out-of-control conditions?
Yes, the use of warning limits would reveal potential out-of-control conditions in this control chart.
Trend Detection: The chart shows a downward trend after the peak around point 11,
which could indicate a shift in the process. Warning limits (±2σ) would help detect this
earlier.
Points Near Control Limits: Some points appear close to UCL before point 11 and close
to LCL after point 11. If they fall within the warning limit range (±2σ to ±3σ), they could
indicate process instability.
5.21.
Rule 1: One or more points outside of the control limits
- No points appear to be outside UCL or LCL
=>this rule is not violated.
Rule 2: Two of three consecutive points outside the two-sigma warning limits but still inside the control
limits
-From the chart alone, it does not appear that two out of three points are in the ±2σ warning zone
consecutively
=> this rule is not violated
Rule 3: Four of five consecutive points beyond the one-sigma limits
-from roughly point 12 onward, the process is consistently below the center line. Some of those points
might be within ±1σ
=> Possibly violated if those points (12 to 16 or 15 to 19) are indeed all below -1σ
Rule 4: A run of eight consecutive points on one side of the center line
-From about point 12 through point 20, every point is below the center line. That’s 9 points in a
row on the same side.
=> This rule is violated
5.22. Sketch warning limits on the control chart in Exercise5.19. Do these limits indicate any potential
out-of-control conditions?
Sketching the ±2σ (warning) limits on this control chart does not reveal any new out-of-control signals.
No points beyond ±3σ: Visually, none of the data points exceed the upper or lower
control limits (UCL/LCL).
Warning limits at ±2σ: sketching the lines halfway between the center line and the
control limits, while a few points might get close, they don’t consistently stay in that
warning zone.
5.23. Apply the Western Electric rules to the control chartpresented in Exercise 5.19. Would these rules
result in any out-of-control signals?
Rule 1: No points exceed the UCL or LCL, so Rule 1 is not violated.
Rule 2: There are no obvious clusters of two out of three points in the ±2σ zone on the
same side, so Rule 2 appears not violated.
Rule 3: No group of four out of five points all beyond ±1σ on the same side is evident, so
Rule 3 doesn’t seem violated
Rule 4: There is no run of eight or more points continuously above or below the center
line, so Rule 4 is not violated.
5.24. Consider the time-varying process behavior shownbelow and on the next page. Match each of
theseseveral patterns of process performance to the corre-sponding and R charts shown in figures (a) to
(e) below.
Figure (a) – Stable, In-Control Process
All distributions have the same center (mean) and similar spread (range).
No visible trend or shift.
Figure (b) – Cyclical Changes in Variability
Mean remains roughly the same, but the spread (width) of each distribution expands and
contracts in a repeating pattern.
Figure (c) – Gradual Shift (Drift) in the Mean
The distributions’ centers steadily move from one side to another (e.g., left to right or top
to bottom), while the spread remains about the same.
Figure (d) – Changing Mean and Changing Variability
Both the center and the spread are changing (e.g., mean drifting up or down, while the
width narrows or widens).
Figure (e) – Multiple Step Changes in the Mean
The process jumps from one average level to another in discrete steps (e.g., high to
medium to low), but the spread within each “step” may stay roughly the same.
