8/2/2019 SPC FOR
1/116
8/2/2019 SPC FOR
2/116
Subgroup
A sample of units produced under a similar set
of conditions.
Process average (also, process center)
An estimate of the overall mean or average forthe process. An estimate of where the process
is located, or centered.
Process variation (also, process spread,
process variability)
An estimate of the variation or spread present
in the process.
8/2/2019 SPC FOR
3/116
Two Types of Variation
Common Cause
Noise Predictable
Routine
No Assignable Cause
Expected
Special Cause
Signal Not Predictable
Exceptional
Assignable Cause
Unusual
8/2/2019 SPC FOR
4/116
Stable vs Unstable Processes
A stable (or in control) process is one in
which the key process responses and
product properties show no signs of specialcauses.
An unstable (or out of control) process hasboth common and special causes present.
8/2/2019 SPC FOR
5/116
5
Visualizing Short-Term and Long-Term
Variation
Time
Short-Term
Measuremen
t
Long-Term
Time
Short-Term
Measurement
Long-Term
Long-Term
Time
Short-Term
Measurement
Time
Short-Term
Measurement
Long-Term
8/2/2019 SPC FOR
6/116
6
Visualizing Short-Term and Long-Term
Variation "Individual World"
Time
Short-Term
Measuremen
t
Long-Term
Time
Short-Term
Measurement
Long-Term
Time
Short-Term
Measurement
Long-Term
Time
Short-Term
Measurement
Long-Term
8/2/2019 SPC FOR
7/116
7
Short-Term vs Long-Term Variation
Short-term (sST)
Represents the processcapability
Captures variation due tocommon causes
Measures variation within asubgroup or between
successive values
Used for calculating controlchart limits
Long-term (sLT)
Represents the total processvariation
Captures variation due tocommon and special causes
Measures variation in all data
Should not be used forcalculating control chart limits
8/2/2019 SPC FOR
8/116
8
Calculating Short-Term and Long-
Term Standard Deviations
Long-term (sLT)
XiX2
i = 1
n
n1
sLT =
Short-term (sST)sST = R / d2
sST = s / c4
sST = MR / d2
STLT
STLT
UnstableIf
StableIf
ss
ss
,
,
8/2/2019 SPC FOR
9/116
Rule of Thumb
< 1 Month Short-Term Data
1 to 3 Months Judgment Call
>3 Months Long-Term Data
8/2/2019 SPC FOR
10/116
10
Stability Index
Stability Index =sSTsLT
For a stable process, you would expect index values near 1.
For an unstable process, you would expect index values greater than 1.
Rule of Thumb
< 1.33 Good Process Stability.
1.33 to 1.67 Marginal Process Stability.
> 1.67 Major Process Stability Issues.
Note: For use when n>75. If n
8/2/2019 SPC FOR
11/116
11
Switching Gears to Process Capability
+3s-3s
USLLSL
8/2/2019 SPC FOR
12/116
12
Specification Limits and Capable
Processes
Specification Limits - often called voice of the customer and used todetermine if the product meets a customer requirement. Usually stated as a LSLand USL but sometimes you may only have one of these.
A capable process is a stable process that demonstrates the ability to meetcustomer requirements. (A purist definition The simple fact is that no processis stable forever and ever and we still need to address the capability of ourprocesses in the presence of instability)
When we talk capability indices, we're now comparing the process variation(and sometimes average) to the specification limits.
Before when we were talking stability, we were comparing the process variationto the control limits.
8/2/2019 SPC FOR
13/116
13
The Four Major Capability /
Performance Indices
Cp
and Cpk
address short-term capability
Pp and Ppk address long-term performance
8/2/2019 SPC FOR
14/116
14
Process Capability Indices - Cp
+3s-3s
USLLSL
Spec Width (door*) USL - LSL
Cp =
Mfg Capability (car)
=
3s
8/2/2019 SPC FOR
15/116
15
Process Capability Indices - Cp
Cp
=USL - LSL
6sST
Cp < 1 - not capable
Cp = 1 - marginally capable
Cp > 1 - capable
The average is not part of the formula.
A measure ofpotential "best case" process capability if stable and on-target.
Can be misleading if process is unstable or off target.
Must have both a LSL and USL to calculate.
LSL USL
8/2/2019 SPC FOR
16/116
16
Visualizing Process Capability
43210- 1- 2- 3-4
0 .4
0 .3
0 .2
0 .1
0 .0
Lower
Spec. Limit
Upper
Spec.Limit
Cust. Tolerance
Cp
=1
Process Capability
86420- 2- 4-6- 8
0 .4
0 .3
0 .2
0 .1
0 .0
Lower
SpecLimit
Upper
Spec.Limit
Cust. Tolerance
Cp
=2
Process
Capability
8/2/2019 SPC FOR
17/116
17
What if Process is Off-Target?
Cp = 1.33
Cpk = 1.33
5.334.02.671.33-1.33-2.67-4.0-5.33 0
0 .4
0 .3
0 .2
0 .1
0 .0
Lower
Spec.
Limit
Upper
Spec.
Limit
Cust. Tolerance
0
0 .4
0 .3
0 .2
0 .1
0 .0
5.334.02.671.33-1.33-2.67-4.0-5.33
LowerSpec.
Limit
UpperSpec.
Limit
Cust. Tolerance
Cp = 1.33
Cpk = 0.83
8/2/2019 SPC FOR
18/116
18
Process Capability Indices - Cpk
Cpk
=Min (USL - avg, avg - LSL)
3sST
Cpk < 1 - not capable
Cpk = 1 - marginally capable
Cpk > 1 - capable
Cp = Cpk if process is on target.
Still a measure ofpotential capability if the process is stable.
Can be used for 1-sided specs. (Cpu, Cpl)
A negative Cpk is possible if the average is outside specifications.
LSL USL
avg
8/2/2019 SPC FOR
19/116
19
Process Performance Indices - Pp
Pp
=USL - LSL
6sLT
Pp < 1 - not meeting specs
Pp = 1 - marginally meeting specs
Pp > 1 - meeting specs
Considered a Process Performance Index
If stable, Cp = PpCan be misleading if process is off target.
LSL USL
8/2/2019 SPC FOR
20/116
20
Process Performance Indices - Ppk
Ppk
=Min (USL - avg, avg - LSL)
3sLT
Ppk < 1 - not meeting specs
Ppk = 1 - marginally meeting specs
Ppk > 1 - meeting specs
If stable, Cpk = Ppk
If on target, Pp = Ppk
If stable and on target, Cp = PpkCan be used for 1-sided specs. (Ppu, Ppl)
Best indicator of actual process performance.
A negative Ppk is possible if the average is outside specifications.
LSL USL
avg
8/2/2019 SPC FOR
21/116
21
Summary of Indices
Cp is the best indicator ofpotential process capabilitybecause it assumes a stable and on-target process.
Cpk is an indicator of potential process capability if theprocess is stable. It does take into consideration if theprocess is off-target.
Pp is an indicator of actual process performance if theprocess is on-target. It does take into consideration the
long-term variability. Ppk is the best indicator ofactual process performance
because it considers the process average and long-termvariability.
8/2/2019 SPC FOR
22/116
One more Index
Sometimes it is desirable to operate the process
at a target that is not midway between the
specification limits. Cpk can still be used to
estimate defect levels but does not reflectwhether the process is centered on the target.
Use Cpm for this.
22
Cpm =USL - LSL
6 sST2 + (avg-tgt)2
8/2/2019 SPC FOR
23/116
A run chart is the simplest of charts.It is a single line plotting some value over time.
A run chart can help you spot upward and downward trends
it can show you a general picture of a process
RUN CHART
8/2/2019 SPC FOR
24/116
Control charts are designed to prevent two common
mistakes:
1) Adjusting the process when it should be left alone;
2) Ignoring the process when it may need to be adjusted.
Control Charts
Control (also, in control)
The absence ofspecial-cause variation.
A process that is in control exhibits only random variation. In other words, the
process is stable or consistent.
Control charts assess statistical control by determining whether the process
output falls within statistically calculated control limits and exhibits only random
variation.
8/2/2019 SPC FOR
25/116
EXAMPLE
Median Line
8/2/2019 SPC FOR
26/116
8/2/2019 SPC FOR
27/116
A control chart is a statistical tool used todistinguish between variation in a process resulting
from common causes and variation resulting from
special causes.
What is a Control Chart?
8/2/2019 SPC FOR
28/116
One goal of using a Control Chart is to achieve and
maintain process stability.
Process stability is defined as a state in which a processhas displayed a certain degree of consistency in the
past and is expected to continue to do so in the future.
This consistency is characterized by a stream of datafalling within control limits
8/2/2019 SPC FOR
29/116
An automobile assembly plant collected camshaft length
measurements to assess the quality of the process.
Five camshafts were measured from each of four shiftsdaily for five days.
The five samples that comprise each subgroup were
selected within a short period of time to minimizevariation from one camshaft to the next.
Example
8/2/2019 SPC FOR
30/116
8/2/2019 SPC FOR
31/116
Control limits represent the limits of variation that shouldbe expected from a process in a state of statistical control.
Control limits
Control limitsSpecification limits?
8/2/2019 SPC FOR
32/116
Specification limits
Limits that are established for the process - they do not reflect
how the process is actually performing. Specification limits are
based on the customer requirements and detail how one wants
the process to behave.
8/2/2019 SPC FOR
33/116
A stable process is one that is consistent over time with
respect to the center and the spread of the data.
X bar Chart - Center
8/2/2019 SPC FOR
34/116
R bar Chart - Spread
A stable process is one that is consistent over time with
respect to the center and the spread of the data.
8/2/2019 SPC FOR
35/116
Why Use Control Charts?
Monitor process variation over time
Differentiate between special causeand common cause variation
Assess effectiveness of changes
Communicate process performance
8/2/2019 SPC FOR
36/116
What are the types of Control Charts?
There are two main categories of Control Charts,
1.Those that display attribute data.
2.Those that display variables data.
8/2/2019 SPC FOR
37/116
Attribute Data:
This category of Control Chart displays data that result
from counting the number of occurrences or
items in a single category of similar
items or occurrences.
These count data may be expressed as pass/fail,
yes/no, or presence/absence of a defect.
8/2/2019 SPC FOR
38/116
Variables Data:
This category of Control Chart displays values
resulting from the measurement of a continuous
variable.
Examples of variables data
elapsed time, temperature, and radiation dose.
8/2/2019 SPC FOR
39/116
There are three types that will work for the
majority of the data analysis cases you will
encounter
X-Bar and R Chart
Individual X and Moving Range Chart for
Variables Data
Individual X and Moving Range Chart for
Attribute Data
8/2/2019 SPC FOR
40/116
8/2/2019 SPC FOR
41/116
What are the elements of a Control Chart?
Each Control Chart actually consists of twographs an upper and lower
A Control Chart is made up of eight elements.
8/2/2019 SPC FOR
42/116
1.Briefly describes the information which is
displayed.
2.Information on how and when the data were
collected.
3.The counts or measurements are recorded in
the data collection section of the Control Chart
prior to being graphed.
8/2/2019 SPC FOR
43/116
Plotting Areas. A Control Chart has two areasan upper
graph and a lower graphwhere the data is plotted.
a. The upper graph plots either the individual values, in the
case of an Individual X and Moving Range chart, or the average(mean value) of the sample or subgroup in the case of an X-Bar
and R chart.
b. The lower graph plots the moving range for Individual X andMoving Range charts, or the range of values found in the
subgroups for X-Bar and R charts.
8/2/2019 SPC FOR
44/116
8/2/2019 SPC FOR
45/116
6. Horizontal or X-Axis. This axis displays thechronological order in which the data were collected.
8/2/2019 SPC FOR
46/116
l
8/2/2019 SPC FOR
47/116
8. Centerline.
This line is drawn at the average or mean value of
all the plotted data. The upper and lower graphseach have a separate centerline.
8/2/2019 SPC FOR
48/116
8/2/2019 SPC FOR
49/116
What are the steps for calculating and plotting an
X-Bar and R Control Chart for Variables Data?
The X-Bar (arithmetic mean) and R (range) Control Chart is used
with variables data when subgroup or sample size is between 2
and 15. The steps for constructing this type of Control Chart are:
8/2/2019 SPC FOR
50/116
Step 1 - Determine the data to be collected.
Decide what questions about the process you plan to answer.
1.Determine what characteristic to be measured
2.Determine what characteristic to be measured
3.Determine what characteristic to be measured
4.Determine what characteristic to be measured
8/2/2019 SPC FOR
51/116
Step 2 - Collect and enter the data by subgroup. A subgroup is made up
ofvariables data that represent a characteristic of a product produced by
a process.
The sample size relates to how large the subgroups are. Enter the
individualsubgroup measurements in time sequence in the portion of
the data collection section of the Control Chart labeled MEASUREMENTS
8/2/2019 SPC FOR
52/116
STEP 3 - Calculate and enter the average for each
subgroup.
Use the formula below to calculate the average (mean)for each subgroup and enter it on the line labeled
Average in the data collection section
8/2/2019 SPC FOR
53/116
8/2/2019 SPC FOR
54/116
8/2/2019 SPC FOR
55/116
Step 4 - Calculate and enter the range for each
subgroup.
Use the following formula to calculate the range (R) for
each subgroup. Enter the range for each subgroup on the
line labeled Range in the data collection section
RANGE = (Largest Value in each Subgroup) -(Smallest
Value in each Subgroup)
8/2/2019 SPC FOR
56/116
Range
8/2/2019 SPC FOR
57/116
8/2/2019 SPC FOR
58/116
Step 5 - Calculate the grand mean of the subgroups
average.
The grand mean of the subgroups average (X-Bar)becomes the centerline for the upper
plot.
S 6 C l l h f h b
8/2/2019 SPC FOR
59/116
Step 6 - Calculate the average of the subgroup
ranges.
The average of all subgroups becomes thecenterline for the lower plotting area.
8/2/2019 SPC FOR
60/116
Step 7 - Calculate the upper control limit (UCL)
and lower control limit (LCL) for the averages of
the subgroups.
Control limits define the parameters for
determining whether a process is in statistical
control.
NOTE: Constants, based on the subgroup size (n), are
used in determining control limits for variables charts.
8/2/2019 SPC FOR
61/116
Use the following constants (A2) in the computation
8/2/2019 SPC FOR
62/116
8/2/2019 SPC FOR
63/116
Step 8 - Calculate the upper control limit for the ranges.
When the subgroup or sample size (n) is less than 7, thereis no lower control limit. To find the upper
control limit for the ranges, use the formula:
8/2/2019 SPC FOR
64/116
Use the following constants (D4) in the computation
8/2/2019 SPC FOR
65/116
Step 9 - Select the scales and plot the control limits,
centerline, and data points, in each plotting area.
The scales must be determined before the data
points and centerline can be plotted. Once the upper
and lower control limits have been computed, the
easiest way to select the scales is to have the currentdata take up approximately 60 percent of the vertical
(Y) axis.
The scales for both the upper and lower plotting areasshould allow for future high or low out-of control
data points.
Plot each subgroup average as an individual data point in
8/2/2019 SPC FOR
66/116
Plot each subgroup average as an individual data point in
the upper plotting area. Plot individual range data points in
the lower plotting area
UCL
CENTRE LINE
LCL
i bl l h f i di id l
8/2/2019 SPC FOR
67/116
Variables control charts for individuals are powerful and simple visualtools for determining whether a process is in or out of control.
Variables control charts for individuals
When to use individuals control charts
8/2/2019 SPC FOR
68/116
When collecting samples to learn about a process, it is sometimes easier to combine the
samples into subgroups, if it makes sense to group the samples together. When grouping is
not appropriate, then a subgroup size of one provides a method for evaluating the process.
Samples that cannot logically be grouped together are good candidates for individuals (I) and
moving range (MR) charts.
Some conditions that make using subgroups unfeasible or undesirable include:
When each sample is uniquely identified with a specific period of time
When each sample represents one distinct batch
When there are long time intervals between each sample
When sampling or testing is destructive and/or expensive
When output is continuous and homogenous
When there is a long cycle time for production
When the measurements are not necessarily related in time (for example, business
data such as time to complete a contract or time to answer a question)
Example
8/2/2019 SPC FOR
69/116
Example A liquid detergent company wants to assess whether
or not its process is in control.
The liquid detergent is made in batches by mixingtogether a number of ingredients.
The quality characteristic of interest is the pH value
for each batch. Measurements of the pH value for 25
consecutive batches were taken.
Because the liquid detergent is created in a batch
process and only one measurement is taken for each
batch, it is not appropriate to place the data insubgroups. Instead, the liquid detergent data should
be analyzed using an Individuals (I) control chart,
which considers each measurement to be an
independent observation.
8/2/2019 SPC FOR
70/116
Step 2 - Collect and enter the individual measurements.
Enter the individual measurements in time sequence on the
line labeled Individual X in the data collection section of theControl Chart.
These measurements will
be plotted as individual data points in the upper plotting
area.
Step 1 - Determine the data to be collected.
Decide what questions about the process you plan to
answer.
8/2/2019 SPC FOR
71/116
8/2/2019 SPC FOR
72/116
STEP 3 - Calculate and enter the moving ranges.
Use the following formula to calculate the moving ranges
between successive data entries. Enter them on theline labeled Moving R in the data collection section.
8/2/2019 SPC FOR
73/116
8/2/2019 SPC FOR
74/116
Step 4 Calculate the overall average of the individual
8/2/2019 SPC FOR
75/116
Step 4 - Calculate the overall average of the individual
data points.
The average of the Individual-X data becomes the
centerline for the upper plot.
Step 5 - Calculate the average of the moving ranges.
8/2/2019 SPC FOR
76/116
Step 5 Calculate the average of the moving ranges.
The average of all moving ranges becomes the centerline
for the lower plotting area.
Step 6 - Calculate the upper and lower control limits for
8/2/2019 SPC FOR
77/116
Step 6 Calculate the upper and lower control limits for
the individual X values.
The calculation will compute the upper and lower control
limits for the upper plotting area. To find these controllimits, use the formula:
Y h ld th t t l t 2 66 i b th
8/2/2019 SPC FOR
78/116
You should use the constant equal to 2.66 in both
formulas when you compute the upper and lower
control limits for the Individual X values.
Step 7 - Calculate the upper control limit for the ranges.
8/2/2019 SPC FOR
79/116
This calculation will compute the upper control limit for the
lower plotting area. There is no lowercontrol limit.
You should use the constant equal to 3.268 in the formula
when you compute the upper control limit for the moving
range data.
Step 8 - Select the scales and plot the data points and centerline
8/2/2019 SPC FOR
80/116
in each plotting area.
Once the upper and lower control limits have been computed,
the easiest way to select the scales is to have the current
spread of the control limits take up approximately 60 percent
of the vertical (Y) axis.
Y Axis
X Axis
UCL
LCL
60 % of Y Axis
8/2/2019 SPC FOR
81/116
Step 9 - Provide the appropriate documentation.
Each Control Chart should be labeled with who, what, when,
where, why, and how information to describe where the data
originated, when it was collected, who collected it, anyidentifiable equipment or work groups, sample size, and all the
other things necessary for understanding and interpreting it.
It is important that the legend include all of theinformation that clarifies what the data describe.
8/2/2019 SPC FOR
82/116
If you are working with attribute data, continue through steps 10,
8/2/2019 SPC FOR
83/116
11, 12a, and 12b
Step 10 - Check for inflated control limits.
When either of the following conditions exists, the control limits
are said to be inflated, and you must
recalculate them:
If any point is outside of the upper control limit for the
8/2/2019 SPC FOR
84/116
moving range (UCLmR)
If two-thirds or more of the moving range values are
below the average of the moving ranges computed inStep 5.
8/2/2019 SPC FOR
85/116
When there is an odd number of values the median is
8/2/2019 SPC FOR
86/116
When there is an odd number of values, the median is
the middle value.
When there is an even number of values, average the
two middle values to obtain the median.
8/2/2019 SPC FOR
87/116
8/2/2019 SPC FOR
88/116
8/2/2019 SPC FOR
89/116
Step 12a - Do not compute new limits if the product of
3.144 times the median moving range value is greater
than the product of 2.66 times the average of the moving
ranges.
Step 12b - Recompute all of the control limits and
centerlines for both the upper and lower plotting areas if
the product of 3.144 times the median moving range
value is less than the product of 2.66 times the average ofthe moving range.
8/2/2019 SPC FOR
90/116
These new limits must be redrawn on the corresponding
charts before you look for signals of special causes. Theold control limits and centerlines are ignored in
any further assessment of the data.
8/2/2019 SPC FOR
91/116
What do we need to know to interpret Control Charts?
8/2/2019 SPC FOR
92/116
p
If a process is stable, the likelihood of a point falling
outside this band is so small that such an occurrence is
taken as a signal of a special cause of variation.
Even though all the points fall inside the control limits, special
8/2/2019 SPC FOR
93/116
cause variation may be at work.
The presence of unusual patterns can be evidence that your
process is not in statistical control.
Such patterns are more likely to occur when one or more special
causes is present.
The three standard deviations are sometimes identified by
8/2/2019 SPC FOR
94/116
zones.
Each zones dividing line is exactly one-third the distance
from the centerline to either the upper control limit or thelower control limit
What are the rules for interpreting X-Bar and R Charts?
8/2/2019 SPC FOR
95/116
p g
Interpreting the tests for special causes
8/2/2019 SPC FOR
96/116
Note that only tests 1-4 are available for R, S, and moving range charts.
One point more than 3-s from center line. Test 1 evaluates the patternof variation for stability. Test 1 provides the strongest evidence of lack of
control. If small shifts in the process are of concern, Tests 2, 5, and 6 can
be used to supplement Test 1 to produce a control chart with greater
sensitivity.
Test 1
Test 2
8/2/2019 SPC FOR
97/116
Nine points in a row one the same side of the center line. Test 2
evaluates the pattern of variation for stability. If small shifts in the
process are of concern, Test 2 can be used to supplement Test 1 toproduce a control chart with greater sensitivity.
Test 3
8/2/2019 SPC FOR
98/116
Six points in a row, all increasing or all decreasing.
Detects a trend or continuous movement up or down. This test looks
for long series of consecutive points without a change in direction.
Test 4
8/2/2019 SPC FOR
99/116
Test 4
Fourteen points in a row, alternating up or down.Points tothe presence of a systematic variable. The pattern of
variation should be random, but when a point fails Test 4 it
means that the pattern of variation is predictable.
Test 5
8/2/2019 SPC FOR
100/116
Two out of three points more than 2s from the centerline (same side).Test 5 evaluates the pattern of variation
for small shifts in the process.
Test 5
Test 6
8/2/2019 SPC FOR
101/116
Four out of five points more than 1s from center line
(same side).Test 6 evaluates the pattern of variation forsmall shifts in the process.
Test 6
Test 7
8/2/2019 SPC FOR
102/116
Fifteen points in a row within 1s of center line (either side).Test 7
identifies a pattern of variation that is sometimes mistaken as a
display of good control. This type of variation is called stratificationand is characterized by points that hug the center line too closely.
Test 7 identifies a pattern of variation that is sometimes mistaken as a
display of good control. This type of variation is called stratification and
is characterized by points that hug the center line too closely.
Test 8
8/2/2019 SPC FOR
103/116
Eight points in a row more than 1s from center line (either side).Test 8
is referred to as a mixture. A mixture pattern occurs when the pointstend to avoid the center line and instead plot near the control limits.
What are the rules for interpreting XmR Control Charts?
To interpret XmR Control Charts you have to apply a set of rules
8/2/2019 SPC FOR
104/116
To interpret XmR Control Charts, you have to apply a set of rules
for interpreting the X part of the chart, and a further single rule
for the mR part of the chart.
RULES FOR INTERPRETING THE X-PORTION of XmR Control
Charts:
Apply the four rules discussed above, EXCEPT apply them only to
the upper plotting area graph.
RULE FOR INTERPRETING THE mR PORTION of XmR Control
Charts for attribute data:
Rule 1 is the only rule used to assess signals of special causes in
the lower plotting area graph. Therefore, you dont need to
identify the zones on the moving range portion of an XmR chart.
When should we change the control limits?
8/2/2019 SPC FOR
105/116
There are only three situations in which it is appropriate to change the control
limits:
When removing out-of-control data points.When a special cause has been identified and removed while you are working to achieve
process stability, you may want to delete the data points affected by special causes and use
the remaining data to compute new control limits.
When replacing trial limits.
When a process has just started up, or has changed, you may want to calculate control limits
using only the limited data available. These limits are usually called trial control limits. You
can calculate new limits every time you add new data. Once you have 20 or 30 groups of 4 or
5 measurements without a signal, you can use the limits to monitor future performance. You
dont need to recalculate the limits again unless fundamental changes are made to the
process.
When there are changes in the process.When there are indications that your process has changed, it is necessary to recompute the
control limits based on data collected since the change occurred. Some examples of such
changes are the application of new or modified procedures, the use of different machines,
the overhaul of existing machines, and the introduction of new suppliers of critical input
materials.
8/2/2019 SPC FOR
106/116
EXERCISE 1: A team collected the variables data recorded in the table below.
Use these data to answer the following questions and plot a Control
8/2/2019 SPC FOR
107/116
Use these data to answer the following questions and plot a Control
Chart:
1. What type of Control Chart would you use with these data?
2. Why?
3. What are the values of X-Bar for each subgroup?
4. What are the values of the ranges for each subgroup?
5. What is the grand mean for the X-Bar data?6. What is the average of the range values?
7. Compute the values for the upper and lower control limits for both
the upper and lower plotting areas.
8. Plot the Control Chart.
9. Are there any signals of special cause variation? If so, what rule did
you apply to identify the signal?
EXERCISE 1 ANSWER KEY:
1 X B d R
8/2/2019 SPC FOR
108/116
1. X-Bar and R.
2. There is more than one measurement within each
subgroup.3. Refer to Fig. 24.
4. Refer to Fig. 24.
5. Grand Mean of X = 4.52.
6. Average of R = 4.38.
7. UCLX = 4.52 + (0.729) (4.38) = 7.71.
LCLX = 4.52 - (0.729) (4.38) = 1.33.
UCLR = (2.282) (4.38) = 10.0.
LCLR = 0.
8. Refer to Fig. 25.
9. No.
EXERCISE 2: A team collected the dated shown in the
8/2/2019 SPC FOR
109/116
chart below.
Use these data to answer the following questions and plot aControl Chart:
f
8/2/2019 SPC FOR
110/116
1. What are the values of the moving ranges?
2. What is the average for the individual X data?
3. What is the average of the moving range data?4. Compute the values for the upper and lower control limits for
both the upper and lower plotting areas.
5. Plot the Control Chart.
6. Are the control limits inflated? How did you determine your
answer?
7. If the control limits are inflated, what elements of the Control
Chart did you have to recompute?
8. If the original control limits were inflated, what are the new
values for the upper and lower control limits and centerlines?9. If the original limits were inflated, replot the Control Chart using
the new information.
10. After checking for inflated limits, are there any signals of special
cause variation? If so, what rule did you use to identify the signal?
EXERCISE 2 ANSWER KEY:
8/2/2019 SPC FOR
111/116
1. Refer to Fig. 26.
2. 19.2.
3. 5.5.4. UCLX = 33.8. LCLX = 4.6. UCLmR =18.0. LCLmR = 0.
5. Refer to Fig. 27.
6. Yes; one point out of control, and 2/3 of all points below the
centerline.7. All control limits and the centerline for the lower chart. The
median value will be used in the re computation rather than the
average.
8. UCLX = 31.8. LCLX = 6.6. UCLmR = 15.5. LCLmR = 0.
CenterlinemR = 4 (median value).
9. Refer to Viewgraph 28.
10. Yes; the same point on the mR chart is out of control. Rule 1.
8/2/2019 SPC FOR
112/116
8/2/2019 SPC FOR
113/116
8/2/2019 SPC FOR
114/116
8/2/2019 SPC FOR
115/116
BACK
8/2/2019 SPC FOR
116/116