Exercises

Chapter 6 Control Charts for Variables

6.1) A manufacturer of component for automobile transmissions wants to use control charts to monitor a
process producing a shaft. The resulting data from 20 samples of 4 shaft diameters that have been
measured are: ∑20 20
𝑖=1 𝑥̅𝑖 = 10.275, ∑𝑖=1 𝑅𝑖 = 1.012

(a) Find the control limits that should be used on the 𝑥̅ and R control charts.
For n = 4, A2 = 0.729, D4 = 2.282, D3 = 0

(b) Assume that the 20 preliminary samples plot in control on both charts. Estimate the process mean and
standard deviation.
6.2) A company manufacturing oil seals wants to establish 𝑥̅ and R control charts on the process. There
are 25 preliminary samples of size 4 on the internal diameter of the seal. The summary data (in mm) are as
follows: ∑20 20
𝑖=1 𝑥̅𝑖 = 1,253.75, ∑𝑖=1 𝑅𝑖 = 14.08

(a) Find the control limits that should be used on the 𝑥̅ and R control charts.
For n = 4, A2 = 0.729, D4 = 2.282, D3 = 0

(b) Assume that the 25 preliminary samples plot in control on both charts. Estimate the process mean and
standard deviation.
6.3) Reconsider the situation described in Exercise 6.1. Suppose that several of the preliminary 20 samples
plot out of control on the R chart. Does this have any impact on the reliability of the control limits on the
𝑥̅ charts?

6.4) Discuss why it is important to establish control on the R chart first when using 𝑥̅ and R control charts
to bring a process into statistical control
6.5) A hospital emergency department is monitoring the time required to admit a patient using 𝑥̅ and R
control charts. Table 6E.1 presents summary data for 20 subgroups of two patients each (time is in
minutes).

(a) Use these data to determine the control limits for the 𝑥̅ and R control charts for this patient admitting
process.
For n = 2, A2 = 1.880, D4 = 3.267, D3 = 0
(b) Plot the preliminary data from the first 20 samples on the control charts that you set up in part (a). Is
this process in statistical control?
6.6) Components used in a digital SLR camera are manufactured with nominal dimension of 0.3 mm and
lower and upper specification limits of 0.295 mm and 0.305 mm respectively. The 𝑥̅ and R control charts
for this process are based on subgroups of size 5 and they exhibit statistical control, with the center line on
the 𝑥̅ at 0.3020 mm and the center line on the R chart at 0.00144 mm.
(a) Estimate the mean and standard deviation of this process.

(b) Suppose that parts below the lower specification limits can be reworked, but parts above the upper
specification limit must be scrapped. Estimate the proportion of scrap and rework produced by this
process.

(c) Suppose that the mean of this process can be reset by fairly simple adjustments. What value of the
process mean would you recommend?
6.7) The data shown in Table 6E.2 are 𝑥̅ and R values for 24 samples of size n = 5 taken from a process
producing bearings. The measurements are made on the inside diameter of the bearing, with only the last
three decimals recorded (i.e., 34.5 should be 0.50345).

(a) Set up 𝑥̅ and R charts on this process. Does the process seem to be in statistical control? If necessary,
revise the trial control limits.
(b) If specifications on this diameter are 0.5030  0.0010, find the percentage of nonconforming bearings
produced by this process. Assume that diameter is normally distributed.
6.8) A high-level voltage power supply should have a nominal output voltage of 350 V. A sample of four
units is selected each day and tested for process-control purposes. The data shown in Table 6E.3 give the
difference between the observed reading on each unit and the nominal voltage times ten; that is,
xi = (observed voltage on unit i - 350)10
(a) Set up 𝑥̅ and R charts on this process. Is the process in statistical control?
(b) If specifications are at 350 V  5 V, what can you say about process capability?

(c) Is here evidence to support the claim that voltage is normally distributed?
6.9) The data shown in Table 6E.4 are the deviations from nominal diameter for holes drilled din a
carbon-fiber composite material used in aerospace manufacturing. The values reported are deviations from
nominal in ten thousandths of an inch.

(a) Set up 𝑥̅ and R charts on the process. Is the process in statistical

control?
(b) Estimate the process standard deviation using the range method.

(c) If specifications are at nominal  100, what can you say about the capability of this process? Calculate
the PCR Cp.
6.10) The thickness of a printed circuit board is an important quality parameter. Data on board thickness
(in inches) are given in Table 6E.5 for 25 samples of three boards each.

(a) Set up 𝑥̅ and R control charts. Is the process in statistical control?

(b) Estimate the process standard deviation.

(c) What are the limits that you would expect to contain nearly all the process measurements?
(d) If the specifications are at 0.0630 in.  0.0015 in., what is the value of the PCR Cp?
6.11) The fill volume of soft-drink beverage bottles is an important quality characteristic. The column is
measured (approximately) by placing a gauge over the crown and comparing the height of the liquid in the
neck of the bottle against a coded scale. On this scale a reading fo zero corresponds to the correct fill
height. Fifteen samples of size n = 10 have been analyzed, and the fill heights are shown in Table 6E.6.

(a) Set up 𝑥̅ and S and control charts on this process. Does the process exhibit statistical control? If
necessary construct revised control limits.
(b) Set up an R chart, and compare it with the s chart in part (a).
(c) Set up an s2 chart and compare it with the s chart in part (a).
6.12) The net weight (in oz.) of a fertilizer product is to be monitored by up 𝑥̅ and R control charts using a
sample size of n = 5. Data for 20 preliminary samples are shown in Table 6E.7.

(a) Set up 𝑥̅ and R control charts using these data. Does the
process exhibit statistical control?
(b) Estimate the process mean and standard deviation.

(c) Does the fill weight seem to follow a normal distribution?

(d) If the specifications are at 16.2  0.5, what conclusions would you draw about process capability?

(e) What fraction of containers produced by this process is likely to be below the lower specification limit
of 15.7 oz?
6.15) Consider the piston ring data shown in Table 6.3. Assume that the specifications on this component
are 74.000  0.05 mm.

(a) Set up x̅ and R control charts on this process. Is the process in statistical control?
(b) Note that the control limits on the x̅ Chart in part (a) are identical to the control limits on the x̅ chart in
Example 6.3, where the limits were based on s. Will this always happen?

(c) Estimate process capability for the piston-ring process. Estimate the percentage of piston rings
produced that will be outside of the specification.
6.16) Table 6E.8 shows 15 additional samples for the piston ring process (Table 6.3), taken after the initial
control charts were established. Plot these data on the 𝑥̅ and R chart developed in Exercise 6.15. Is the
process in control?
6.17) Control charts on 𝑥̅ and s are to be maintained on the torque readings of a earing used in a wingflap
actuator assembly. Samples of size n = 10 are to be used, and we know from past experience that when the
process is in control, bearing torque has a normal distribution with mean  = 80 inch-pounds and standard
deviation of  = 10 inch pounds. Find the center line and control limits for these control charts.
6.18.
Samples of n = 4 items each are taken from a process at regular intervals. A quality characteristic is
measured, and 𝑥̅ and R values are calculated for each sample. After 50 samples, we have
50 50

∑ 𝑥̅𝑖 = 2100; ∑ 𝑅𝑖 = 175; 𝑚 = 50 𝑠𝑎𝑚𝑝𝑙𝑒𝑠

𝑖=1 𝑖=1
Assume that the quality characteristic is normally distributed.
(a) Compute control limits for the 𝑥̅ and R control charts.

(b) All points on both control charts fall between the control limits computed in part (a). What are the
natural tolerance limits of the process?
(c) If the specification limits are 41  4.5, what are your conclusions regarding the ability of the process
to produce items within these specifications?

(d) Assuming that if an item exceeds the upper specification limit it can be reworked, and if it is below the
lower specification limit it must be scrapped, what percent scrap and rework is the process producing?

(e) Make suggestions as to how the process performance could be improved.

6.19) Samples of n = 4 items are taken from a process at regular intervals. A normally distributed quality
characteristic is measured and 𝑥̅ and s values are calculated for each sample. After 50 subgroups have
been analyzed, we have
50 50

∑ 𝑥̅𝑖 = 1000; ∑ 𝑆𝑖 = 72 ; 𝑚 = 50 𝑠𝑢𝑏𝑔𝑟𝑜𝑢𝑝𝑠

𝑖=1 𝑖=1
(a) Compute the control limit for the 𝑥̅ and s control charts

(b) Assume that all points on both charts plot within the control limits. What are the natural tolerance
limits of the process?
to produce items conforming to specifications?

(d) Assuming that if an item exceeds the upper specification limit it can be reworked, and if it is below the
lower specification limit it must be scrapped, what percent scrap and rework is the process now
producing?
6.20) Table 6E.9 presents 20 subgroups of five measurements on the critical dimension of a part produced
by a welding process.

(a) Set up 𝑥̅ and R control charts on this process. Verify that the process is in statistical control.
 (b) Following the establishment of control charts in part (a) above, 10 new samples in Table 6E.10 were
collected Plot the 𝑥̅ and R values on the control chart you established in part (a) and draw conclusions.
(c) Suppose that the assignable cause responsible for the action signals generated in part (b) has been
identified and adjustments made to the process to correct its performance. Plot the 𝑥̅ and R values from
the new subgroups shown in Table 6E.11 which were taken following the adjustment, against the control
chart limits established in part (a). What are your conclusions?
6.21) Parts manufactured by an injection molding process are subjected to a compressive strength test.
Twenty samples of five parts each are collected, and the compressive strengths (in psi) are shown in Table
6E.12.

(a) Establish 𝑥̅ and R control charts for compressive strength using these data. Is the process in statistical
control?
(b) After establishing the control charts in part (a), 15 new subgroups were collected and the compressive
strengths are shown in Table 6E.13. Plot the 𝑥̅ and R values against the control units from part (a) and
draw conclusions.
Reconsider the data presented in Exercise 6.21.
(a) Rework both parts (a) and (b) of Exercise 6.21 using the 𝑥̅ and s charts.
6.25) Control charts for 𝑥̅ and R are maintained for an important quality characteristic. The sample size is
n= 7; 𝑥̅ and R are computed for each sample. After 35 samples we have found that
35 35

∑ 𝑥̅𝑖 = 7,805; ∑ 𝑅𝑖 = 1,200 ; 𝑚 = 35 𝑠𝑎𝑚𝑝𝑙𝑒𝑠

𝑖=1 𝑖=1
(a) Set up 𝑥̅ and R charts using these data.

(b) Assuming that both charts exhibit control, estimate the process mean and standard deviation.
(c) If the quality characteristic is normally distributed and if the specifications are 220  35, can the
process meet the specifications? Estimate the fraction nonconforming.

(d) Assuming the variance to remain constant, state where the process mean should be located to minimize
the fraction nonconforming. What would be the value of the fraction nonconforming under these
conditions?
6.26) Samples of size n = 4 are taken from a transactional process every hour. A quality characteristic is
measured, and 𝑥̅ and R are computed for each sample. After 2 samples have been analyzed, we have
25 25

∑ 𝑥̅𝑖 = 657.50 ; ∑ 𝑅𝑖 = 9.00

𝑖=1 𝑖=1
The quality characteristic is normally distributed.
(a) Find the control limits for the 𝑥̅ and R charts.

(b) Assume that both charts exhibit control. If the specifications are 26.40  0.50, estimate the fraction
nonconforming.
(c) If the mean of the process were 26.40, what fraction nonconforming would result?
6.27) Samples of size n = 5 are collected from a process every half hour. After 50 samples have been
collected, we calculate 𝑥̅ = 20.0 and s = 1.5. Assume that both charts exhibit control and that the quality
characteristic is normally distributed.
(a) Estimate the process standard deviation.

(b) Find the control limits on the charts.

(c) If the process mean shifts to 22, what is the probability of concluding that the process is still in
control?
6.28) Control chart for 𝑥̅ and R are maintained on a process. After 20 preliminary subgroups each of size
5 are evaluated, you have the following data:
20 20

∑ 𝑥̅𝑖 = 5,498 ; ∑ 𝑅𝑖 = 60
𝑖=1 𝑖=1
(a) Set up control charts using these data.

(b) Assume that the process exhibits statistical control. Estimate the process mean and standard deviation.
𝜇̂ =

𝜎̂ 𝑥 =

(c) Suppose that the quality characteristic is normally distributed with specifications at 275  6. Estimate
the fraction nonconforming produced by this process.

(d) How much reduction in process variability would be required to make this a Six Sigma process?
6.29) Control chart for 𝑥̅ and s are maintained on a process. After 25 preliminary subgroups each of size 3
are evaluated, you have the following data:
25 25

∑ 𝑥̅𝑖 = 55.45 ; ∑ 𝑠𝑖 = 28.67

𝑖=1 𝑖=1
(a) Set up control charts using these data.

(b) Assume that the process exhibits statistical control. Estimate the process mean and standard deviation.
𝜇̂ =

𝜎̂ 𝑥 =

(c) Suppose that the quality characteristic is normally distributed with specifications at 2.25  4. Estimate
the fraction nonconforming produced by this process

(d) How much reduction in process variability would be required to make this a Six Sigma process?
6.30) An x chart is used to control the mean of a normally distributed quality characteristic. It is known
that  = 6.0 and n = 4. The center line = 200, UCL = 209, and LCL = 191. If the process mean shifts to
188, find the probability that this shift is detect on the first subsequent sample.

6.31) A critical dimension of a machined part has specifications 100  10. Control chart analysis indicates
tht the process is in control with 𝑥̅ =104 and R =9.30. The control charts use samples of size n = 5. If we
assume that the characteristic is normally distributed, can the mean be located (by adjusting the tool
position) so that all output meets specifications?
6.32) A process is to be monitored with standard values  = 10 and  = 1.5. The sample size is n = 3.
(a) Find the center line and control limits for the 𝑥̅ chart.

Centerline𝑥̅ =

UCL𝑥̅ =

LCL𝑥̅ =

(b) Find the center line and control limits for the R chart.

Centerline𝑅 =

UCL𝑅 =

LCL𝑅 =

(b) Find the center line and control limits for the s chart.

Centerline𝑠 =

UCL𝑠 =

LCL𝑠 =
6.33) Samples f n= 5 units are taken from a process every hour. The x R and values for a particular quality
characteristic are determined. After 25 sample have been collected, we calculate 𝑥̅ = 20 and R = 4.56.
(a) What are the three-sigma control limits for the 𝑥̅ and R?

UCL𝑥̅ =

LCL𝑥̅ =

UCL𝑅 =

LCL𝑅 =

(b) Both charts exhibit control. Estimate the process standard deviation.

(c) Assume that the process output is normally distributed. If he specifications are 19  5, what are your
conclusions regarding the process capability?

(d) If the process mean shifts to 24, what is the probability of not detecting this shift on the first
subsequent sample?
6.34 A TiW layer is deposited on a substrate using a sputtering tool. Table 6E.14 contains layer thickness
measurements (in angstroms) on 20 subgroups of four substrates.

(a) Setup 𝑥̅ and R control charts on this process.

Is the process in control? Revise the control limits as necessary.
(b) Estimate the mean and standard deviation of the process.

(c) Is the layer thickness normally distributed?

(d) f the specifications are at 450  30, estimate the process capability
6.35) Continuation of Exercise 6.34. Table 6E.15 contains 10 new subgroups of thickness data. Plot this
data on the control charts constructed in Exercise 6.26 (a). Is the process in statistical control?