Variables control charts are used to evaluate variation
in a process where the measurement is a variable-i.e.
the variable can be measured on a continuous scale.
Many quality
characteristics can be
expressed in terms of a
numerical measurement.
A single measurable
quality characteristic,
such as a dimension,
weight, or volume, is
called a variable.
When working with variables data, both the mean and
variability are usually tracked. 50
Taking m samples each containing n observations on the quality
characteristic. Typically, n will be small, often either 4, 5, or 6.
If x , x , . . . , x is a sample of size n, then the average of this
1 2 n
sample is:
ത 𝑥1 +𝑥2 +𝑥3 +⋯+𝑥𝑛
𝑋= Average of each sample
𝑛
𝑋ത1 + 𝑋ത2 + ⋯ + 𝑋ത𝑚
The process average is: 𝑋ധ =
𝑚
Thus, 𝑋ധ would be used as the center line on the chart.
the range of the sample is the difference between the largest and the smallest
observations
𝑅 = 𝑥𝑚𝑎𝑥 − 𝑥𝑚𝑖𝑛
51
Let R , R , . . . , R be the ranges of the m samples. The average range is
1 2 m
𝑅1 + 𝑅2 + ⋯ + 𝑅𝑚
𝑅ത =
𝑚
the formulas for constructing the control limits on the chart. They
are as follows:
𝑈𝐶𝐿 = 𝑋ധ + 𝐴2 𝑅ത
Center line = 𝑋ധ
L𝐶𝐿 = 𝑋ധ − 𝐴2 𝑅ത
The constant A is tabulated
2
for various sample sizes.
3 𝑅ത
𝐴2 = , 𝜎𝑝 =
𝑑2 𝑛 𝑑2 52
53
Process variability may be monitored by plotting values of the sample range R on
a control chart. The center line and control limits of the R chart are as follows:
ത 𝐷4
𝑈𝐶𝐿 = 𝑅.
LCL= 𝑅.ത 𝐷3
CL= 𝑅ത
The constants D3 and D4
are tabulated for various
values of n.
𝜎𝑅 = 𝑑3 𝜎𝑝
𝑑3 𝑑3
𝐷3 = 1 − 3 𝑎𝑛𝑑 𝐷4 = 1 + 3
𝑑2 𝑑2
54
55
n= 4
m= 14
56
Example:
A hard-bake process is used in
conjunction with photolithography
in semiconductor manufacturing.
We wish to establish statistical
control of the flow width of the
resist in this process using and R
charts. Twenty-five samples, each
of size five wafers, have been taken
when we think the process is in
control. The interval of time
between samples or subgroups is
one hour. The flow width
measurement data (in x microns)
from these samples are shown in
Table.
Determine if the process is
under statistical control or
not.
57
n= 5
m= 25
58
59
60 why?
What other type of statistical tool could be used in conjunction with this control chart and
We must then examine the samples for nonrandom pattern.
61
zone A
zone B
zone C
zone C
zone B
zone A
zone A
zone B
zone C
zone C
zone B
zone A
62
No non-random (out of control) pattern
No points exceed the control limits
No non-random (out of control) pattern
So, the process is under statistical control
63
Example 2:
The basic size of the
depth of the keyway
is 6 mm. Table shows
the variations
related to the basic
size in 0.01 mm.
a) Determine the
trial central line and
control limits.
b) If any points
exceed control limits,
calculate the revised
control limits.
64
Determine the trial central line and control limits if :
m= 25 samples
𝑋ሜ = 6.41𝑚𝑚
𝑅ሜ = 0.0876𝑚𝑚
𝑈𝐶𝐿𝑋ሜ = 6.47𝑚𝑚
𝐿𝐶𝐿𝑋ሜ = 6.35𝑚𝑚
𝑈𝐶𝐿𝑅 = 0.2𝑚𝑚
𝐿𝐶𝐿𝑅 = 0𝑚𝑚
65
𝑈𝐶𝐿𝑋ሜ = 6.47𝑚𝑚
𝐿𝐶𝐿𝑋ሜ = 6.35𝑚𝑚
𝑈𝐶𝐿𝑅 = 0.2𝑚𝑚
𝐿𝐶𝐿𝑅 = 0𝑚𝑚
66
Points 4, 16, 18, 20 out of control limits.
Establish the revised central line and control limits:
ሜ ሜ 𝑋ሜ 𝑑 160.25−6.65−6.34−6.42−6.51
σ 𝑋−
𝑋𝑛𝑒𝑤 = =
𝑚−𝑚𝑑 25−4
=6.397
σ 𝑅−𝑅𝑑 2.19−0.1−0.1−0.3−0.11
𝑅ሜ 𝑛𝑒𝑤 = = = 0.070
𝑚−𝑚𝑑 25−4
A2=0.729, D3=0, D4=2.282
UCLX new = X new + A2 Rnew
LCLX new = X new − A2 Rnew =0.16
UCLRnew = D4 Rnew
=0.07
LCLR new = D3 Rnew 67
Example:
Control charts for x and R are maintained for an important quality
characteristic. The sample size is n=7; x and R are computed for
each sample. After 35 samples, we have found that:
σ35 ഥ
𝑋
𝑖=1 𝑖 =7805 and σ35
𝑖=1 𝑅𝑖=1200
a) Set up x 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 specification?
68
The sample size is n=7; x and R are computed for each sample.
After 35 samples, we have found that:
σ35 ഥ
𝑖=1 𝑋𝑖 =7805 and σ35
𝑖=1 𝑅𝑖=1200
a) Set up x and R charts using these data.
ത
σ 𝑋 7805
𝐶𝐿 = 𝑋ധ = = =233
𝑚 35
σ 𝑅 1200
ത
𝑅= = =34.29
𝑚 35
ധ 2 . 𝑅 =233+(0.419)(34.29)=247.37
𝑈𝐶𝐿𝑋ത = 𝑋+𝐴
𝐿𝐶𝐿𝑋ത = 𝑋ധ − 𝐴2 . 𝑅 =233-(0.419)(34.29)=218.63
𝑈𝐶𝐿𝑅 = 𝐷4 𝑅ሜ =(1.924)(34.29)=65.97
𝐿𝐶𝐿𝑅 = 𝐷3 𝑅ሜ =(0.076)(34.29)=2.606
69
The sample size is n=7; x and R are computed for each sample.
After 35 samples, we have found that:
σ35 𝑋
𝑖=1 𝑖
ഥ =7805 and σ 35
𝑖=1 𝑅𝑖=1200
b) Assuming that both charts exhibit control, estimate
the process mean and standard deviation.
𝜇 = 𝑋ധ = 233
𝑅ത 34.29
𝜎= = = 12.68
𝑑2 2.704
c) If the quality characteristic is normally distributed
and if the specifications are 220± 35, can the process
meet the specification?
= (70)/(6)(12.68)=0.92 < 1
70
The process is not capable (process does not meet specification limits).