Lecture 2-2

Statistical
Process Control
2014 Pearson Education, Inc.
S6 - 1
Outline
Statistical Process Control

Process Capability
Acceptance Sampling
S6 - 2
Learning Objectives
When you complete this supplement
you should be able to :
1. Explain the purpose of a control chart
2. Explain the role of the central limit theorem
in SPC
3. Build
x -charts and R-charts
4. List the five steps involved in building

control charts
S6 - 3
Learning Objectives
When you complete this supplement
you should be able to :
5. Build p-charts and c-charts
6. Explain process capability and compute Cp
and Cpk
7. Explain acceptance sampling
S6 - 4

The objective of a process control
system is to provide a statistical
signal when assignable causes of
variation are present
S6 - 5

(SPC)
Variability is inherent
in every process
Natural or common
causes
Special or assignable
causes
Provides a statistical signal when assignable

causes are present
Detect and eliminate assignable causes of

variation
S6 - 6
Common Causes
Common causes of variation are the purely
random, unidentifiable sources of variation that
are unavoidable with the current process. For
example, the time required to process
specimens at an intensive care unit lab in a
hospital will vary. If time is measured to
complete an analysis for a large no. of patients
and plotted the
results, the data would
tend to
form a pattern that can be
described as a distribution.
S6 - 7
Natural Variations
Also called common causes
Affect virtually all production processes
Expected amount of variation
Output measures follow a probability

distribution
For any distribution there is a measure of

central tendency and dispersion
If the distribution of outputs falls within

acceptable limits, the process is said to be
in control
S6 - 8
Common Causes
A distribution may be characterized by its mean,

spread, and shape.
The spread is a measure of the dispersion of
observations about the mean. The standard deviation
is the square root of the variance of a distribution.
Standard Deviation/
Spread
Mean
n
i 1
x x
n 1
S6 - 9
Assignable Variations
Also called special causes of variation
Generally this is some change in the process
Variations that can be traced to a specific

reason
The objective is to discover when assignable

causes are present
Eliminate the bad causes
Incorporate the good causes
S6 - 10
Assignable Causes
The green curve is the process distribution when only common
causes of variation are present. The red lines depict a change in
the distribution because of assignable causes. In Fig. 6.0(a) the
red line indicates that the process took more time than planned
in many of the cases, thereby increasing the average time of
each analysis.
Average
(a)
2014Location
Pearson Education, Inc.
Time
S6 - 6.0
11
Figure
Assignable Causes
An increase in the variability of the time for each case
affected the spread of the distribution.
Average
(b) Spread
Time
Figure
S6 - 6.0
12
Assignable Causes
The red line indicates that the process produced a
preponderance of the tests in less than average time.
A process is said to be in statistical control when the
location, spread, or shape of its distribution does not
change over time.
Average
(c) Shape
Time
Figure
6.0
S6 - 13
Samples
To measure the process, we take samples and
analyze the sample statistics following these
steps
Each of these
represents one
sample of five
boxes of cereal
(a) Samples of the product,

say five boxes of cereal
taken off the filling machine
line, vary from each other
in weight
Frequency
# #
# # #
# # # #
# # # # # # #
Figure S6.1
# # # # # # # # #
Weight
S6 - 14
Samples
steps
Frequency
(b) After enough samples

are taken from a stable
process, they form a
pattern called a
distribution
The solid line

represents the
distribution
Weight
Figure S6.1
S6 - 15
Samples
steps
(c) There are many types of distributions, including the normal (bellshaped) distribution, but distributions do differ in terms of central
tendency (mean), standard deviation or variance, and shape
Frequency
Figure S6.1
Central tendency
Weight
Variation
Weight
Shape
Weight
S6 - 16
Samples
steps
Prediction
Frequency
(d) If only natural causes of

variation are present,
the output of a process
forms a distribution that
is stable over time and
is predictable
Weight
Figure S6.1
S6 - 17
Samples
steps
Prediction
Frequency
(e) If assignable causes are

present, the process output
is not stable over time and
is not predicable
?
?? ??
?
?
?
?
?
?
?
?
?
??
??
?
Weight
Figure S6.1
S6 - 18
Control Charts
Constructed from historical data, the
purpose of control charts is to help
distinguish between natural variations
and variations due to assignable causes
S6 - 19
Process Control
Frequency
Lower control limit
(a) In statistical
control and capable
of producing within
control limits
Upper control limit
(b) In statistical control

but not capable of
producing within
control limits
(c) Out of control

Size
(weight, length, speed, etc.)
Figure S6.2
S6 - 20
Control Charts for Variables
Characteristics that can take any real value
May be in whole or in fractional numbers
Continuous random variables
x-chart tracks changes in the central

tendency
R-chart indicates a gain or loss of

dispersion
S6 - 21
Central Limit Theorem

Regardless of the distribution of the population,
the distribution of sample means drawn from the
population will tend to follow a normal curve
1) The mean of the sampling
distribution will be the same as the
population mean m
2) The standard deviation of the
sampling distribution (s x ) will
equal the population standard
deviation ( ) divided by the
square root of the sample size, n
x= = m
sx =
s
n
S6 - 22
Population and Sampling

Distributions
Population
distributions
Distribution of
sample means
=
Mean of sample means = x
Beta
Standard
deviation of
the sample
means
Normal
=sx =
s
n
Uniform
|
-3s x -2s x -1s x
x=
+1s x +2s x +3s x
95.45% fall within 2s x

99.73% of all x
fall within 3s x
Figure S6.3
S6 - 23
Sampling Distribution
Figure S6.4
Sampling
distribution of
means
Process
distribution of
means
x=m
(mean)
S6 - 24
Setting Chart Limits

For x-Charts when we know
Lower control limit (UCL) = x= - zs x
Upper control limit (UCL) = x= + zs x
Where
x= = mean of the sample means or a target value set for the

process
z = number of normal standard deviations
x = standard deviation of the sample means = s / n
= population (process) standard deviation
n = sample size
S6 - 25
Setting Control Limits

Randomly select and weigh nine (n = 9) boxes
each hour
Average weight in 17 +13 +16 +18 +17 +16 +15 +17 +16
=
= 16.1 ounces
the first sample
9
WEIGHT OF SAMPLE
HOUR
(AVG. OF 9
BOXES)
WEIGHT OF SAMPLE
WEIGHT OF SAMPLE
HOUR
(AVG. OF 9
BOXES)
HOUR
(AVG. OF 9
BOXES)
16.1
16.5
16.3
16.8
16.4
10
14.8
15.5
15.2
11
14.2
16.5
16.4
12
17.3
S6 - 26

12
Avg of 9 boxes
Average mean = i=1

= x=
of 12 samples
12
x= = 16 ounces
n=9
z=3
s = 1 ounce
S6 - 27

12
Avg of 9 boxes
Average mean = i=1

= x=
of 12 samples
12
x= = 16 ounces
n=9
z=3
s = 1 ounce
1
1
UCL x = x + zs x = 16 + 3
= 16 + 3 = 17 ounces
3
9
=
1
1
LCL x = x - zs x = 16 - 3
= 16 - 3 = 15 ounces
3
9
=
S6 - 28

Control Chart
for samples
of 9 boxes
Variation due
to assignable
causes
Out of
control
17 = UCL
Variation due to
natural causes
16 = Mean
15 = LCL
| | | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10 11 12
Sample number
Out of
control
Variation due
to assignable
causes
S6 - 29

For x-Charts when we dont know
UCL x = x= + A2 R
LCL x = x= - A2 R
n
R=
where
i=1
= average range of the samples
A2 = control chart factor found in Table S6.1
x= = mean of the sample means
S6 - 30
Control Chart Factors

TABLE S6.1
Factors for Computing Control Chart Limits (3 sigma)
SAMPLE SIZE,
n
MEAN FACTOR,
A2
UPPER RANGE,
D4
LOWER RANGE,
D3
1.880
3.268
1.023
2.574
.729
2.282
.577
2.115
.483
2.004
.419
1.924
0.076
.373
1.864
0.136
.337
1.816
0.184
10
.308
1.777
0.223
12
.266
1.716
0.284
S6 - 31

Super Cola Example
Labeled as net weight
12 ounces
Process average = 12 ounces

Average range = .25 ounce
Sample size = 5
UCL x = x= + A2 R
= 12 + (.577)(.25)
UCL = 12.144
= 12 + .144
= 12.144 ounces
LCL x = x= - A2 R
= 12 - .144
Mean = 12
From Table
S6.1
LCL = 11.856
= 11.856 ounces
S6 - 32
Restaurant Control Limits

Sample Mean
For salmon filets at Darden Restaurants

x Bar Chart
11.5
UCL = 11.524
11.0
x = 10.959
10.5
11
13
15
17
LCL = 10.394
Sample Range
Range Chart
0.8
UCL = 0.6943
0.4
R = 0.2125
0.0 |
1
11
13
15
17
LCL = 0
S6 - 33
R Chart
Type of variables control chart
Shows sample ranges over time
Difference between smallest and

largest values in sample
Monitors process variability
Independent from process mean
S6 - 34

For R-Charts
Upper control limit (UCL R ) = D4 R
Lower control limit (LCL R ) = D3 R
where
UCL R = upper control chart limit for the range

LCL R = lower control chart limit for the range
D4 and D3 = values from Table S6.1
S6 - 35

Average range = 5.3 pounds
Sample size = 5
From Table S6.1 D4 = 2.115, D3 = 0
UCL R = D4 R
= (2.115)(5.3)
= 11.2 pounds
UCL = 11.2
Mean = 5.3
LCL R = D3 R
= (0)(5.3)
= 0 pounds
LCL = 0
S6 - 36
Mean and Range Charts

(a)
(Sampling mean is
shifting upward, but
range is consistent)
These
sampling
distributions
result in the
charts below
UCL
(x-chart detects
shift in central
tendency)
x-chart
LCL
UCL
(R-chart does not

detect change in
mean)
R-chart
Figure S6.5
LCL
S6 - 37
Mean and Range Charts

(b)
These
sampling
distributions
result in the
charts below
(Sampling mean
is constant, but
dispersion is
increasing)
UCL
(x-chart indicates
no change in
central tendency)
x-chart
LCL
UCL
(R-chart detects
increase in
dispersion)
R-chart
Figure S6.5
LCL
S6 - 38
Steps In Creating Control

Charts
1. Collect 20 to 25 samples, often of n = 4 or n = 5
observations each, from a stable process and
compute the mean and range of each
2. Compute the overall means ( x= and R ), set
appropriate control limits, usually at the 99.73%
level, and calculate the preliminary upper and
lower control limits
If the process is not currently stable and in control, use

=
the desired mean, m, instead of x to calculate limits.
S6 - 39
Steps In Creating Control

Charts
3. Graph the sample means and ranges on their
respective control charts and determine whether
they fall outside the acceptable limits
4. Investigate points or patterns that indicate the
process is out of control try to assign causes
for the variation, address the causes, and then
resume the process
5. Collect additional samples and, if necessary,
revalidate the control limits using the new data
S6 - 40
Setting Other Control Limits

TABLE S6.2
Common z Values
DESIRED CONTROL
LIMIT (%)
Z-VALUE (STANDARD
DEVIATION REQUIRED
FOR DESIRED LEVEL OF
CONFIDENCE
90.0
1.65
95.0
1.96
95.45
2.00
99.0
2.58
99.73
3.00
S6 - 41
Example
Control Charts
for Variables
West Allis Industries

The management of West Allis Industries is concerned about
the production of a special metal screw used by several of
the companys largest customers. The diameter of the screw
is critical to the customers. Data from five samples appear in
the accompanying table. The sample size is 4. Is the process
in statistical control?
S6 - 42
Control Charts
for Variables
Special Metal Screw
Sample
Number
1
2
3
4
5
1
0.5014
0.5021
0.5018
0.5008
0.5041
Example
Sample
2
3
0.5022 0.5009
0.5041 0.5024
0.5026 0.5035
0.5034 0.5024
0.5056 0.5034
4
0.5027
0.5020
0.5023
0.5015
0.5039
_
x
S6 - 43
Control Charts
for Variables
Special Metal Screw
Sample
Number
1
2
3
4
5
1
0.5014
0.5021
0.5018
0.5008
0.5041
Example
Sample
2
3
4
0.5022 0.5009 0.5027
0.5041 0.5024 0.5020
0.5026 0.5035 0.5023
0.5027 0.5009
0.5034 0.5024 0.5015
0.5056 0.5034 0.5039
R
x
0.0018 0.5018
0.0018
S6 - 44
Control Charts
for Variables
Special Metal Screw
Sample
Number
1
2
3
4
5
1
0.5014
0.5021
0.5018
0.5008
0.5041
Example
Sample
2
3
4
0.5022 0.5009 0.5027
0.5041 0.5024 0.5020
0.5026 0.5035 0.5023
0.5027 0.5009
0.5034 0.5024 0.5015
0.5056 0.5034 0.5039
R
x
0.0018 0.5018
0.0018
S6 - 45
Control Charts
for Variables
Special Metal Screw
Sample
Number
1
2
3
4
5
1
0.5014
0.5021
0.5018
0.5008
0.5041
Example
Sample
2
3
4
0.5022 0.5009 0.5027
0.5041 0.5024 0.5020
0.5026 0.5035 0.5023
0.5027 0.5009
0.5034 0.5024 0.5015
(0.5014 + 0.5022 +
0.50560.5009
0.5034
0.5039
+ 0.5027)/4
R
x
0.0018 0.5018
0.0018
0.5018
S6 - 46
Control Charts
for Variables
Special Metal Screw
Sample
Number
1
2
3
4
5
1
0.5014
0.5021
0.5018
0.5008
0.5041
Example
Sample
2
3
0.5022 0.5009
0.5041 0.5024
0.5026 0.5035
0.5034 0.5024
0.5056 0.5034
4
0.5027
0.5020
0.5023
0.5015
0.5047
R=
R
0.0018
0.0021
0.0017
0.0026
0.0022
0.0021
=
x=
x
0.5018
0.5027
0.5026
0.5020
0.5045
0.5027
S6 - 47
Control Charts
for Variables
Control Charts Special Metal Screw
R-Charts
R = 0.0021
UCLR = D4R
LCLR = D3R
Example
5.1
S6 - 48
Table 5.1 Control Chart Factors
Control Charts
for Variables
Size of
Sample
(n)
Factor for UCL

and LCL for
x-Charts
(A2)
Factor for
LCL for
R-Charts
(D3)
Factor
UCL for
R-Charts
(D4)
2
3
4
5
6
7
8
9
10
1.880
1.023
0.729
0.577
0.483
0.419
0.373
0.337
0.308
0
0
0
0
0
0.076
0.136
0.184
0.223
3.267
2.575
2.282
2.115
2.004
1.924
1.864
1.816
1.777
Example
5.1
S6 - 49
Control Charts
for Variables
Control Charts Special Metal Screw
R-Charts
R = 0.0021
UCLR = D4R
LCLR = D3R
Example
5.1
S6 - 50
Control Charts
for Variables
Control ChartsSpecial Metal Screw
R-Charts
R = 0.0021
D4 = 2.282
D3 = 0
UCLR = D4R
LCLR = D3R
Example
5.1
S6 - 51
Control Charts
for Variables
R-Charts
R = 0.0021
D4 = 2.282
D3 = 0
UCLR = D4R
LCLR = D3R
UCLR = 2.282 (0.0021) = 0.00479 in.
Example
5.1
S6 - 52
Control Charts
for Variables
R-Charts
R = 0.0021
D4 = 2.282
D3 = 0
UCLR = D4R
LCLR = D3R
UCLR = 2.282 (0.0021) = 0.00479 in.
LCLR = 0 (0.0021) = 0 in.
Example
5.1
S6 - 53
Control Charts
for Variables
R-Charts
R = 0.0021
D4 = 2.282
D3 = 0
UCLR = D4R
LCLR = D3R
UCLR = 2.282 (0.0021) = 0.00479 in.
LCLR = 0 (0.0021) = 0 in.
Example
5.1
S6 - 54
Range Chart Special Metal Screw
Example
S6 - 55
Control Charts
for Variables
R = 0.0021
x== 0.5027
X-Charts
=
UCLx = x + A2R
LCL = x=- A R
x
Example
5.1
S6 - 56
Table 5.1 Control Chart Factors
Control Charts
for Variables
Factor for UCL

Factor for
Size of
and LCL for
LCL for
Control
ChartsSpecial
Metal
Screw
Sample
x-Charts
R-Charts
(n)
(A2) R = 0.0021
(D3)
X-Charts
x = 0.5027
2
1.880=
0
3
1.023
=
4
0.729
UCL
x = x + A2R
5
0.577
=
LCL
R
6 x = x - A20.483
7
0.419
8
0.373
9
0.337
10
0.308
Example
5.1
0
0
0
0
0.076
0.136
0.184
0.223
Factor
UCL for
R-Charts
(D4)
3.267
2.575
2.282
2.115
2.004
1.924
1.864
1.816
1.777
S6 - 57
Control Charts
for Variables
R = 0.0021
x== 0.5027
x-Charts
A2 = 0.729
=
UCLx = x + A2R
LCL = x=- A R
x
Example
5.1
S6 - 58
Control Charts
for Variables
R = 0.0021
x== 0.5027
x-Charts
A2 = 0.729
=
UCLx = x + A2R
LCL = x=- A R
x
UCLx = 0.5027 + 0.729 (0.0021) = 0.5042 in.

Example
5.1
S6 - 59
Control Charts
for Variables
R = 0.0021
x== 0.5027
x-Charts
A2 = 0.729
=
UCLx = x + A2R
LCL = x=- A R
x
UCLx = 0.5027 + 0.729 (0.0021) = 0.5042 in.

LCLx = 0.5027 0.729 (0.0021) = 0.5012 in.
Example
5.1
S6 - 60
x-Chart
Special Metal Screw
Example
S6 - 61
x-Chart
Special Metal Screw
Example
Sample the process

Find the assignable cause
Eliminate the problem
Repeat the cycle
S6 - 62
Control Charts for Attributes
For variables that are categorical
Defective/nondefective, good/bad,
yes/no, acceptable/unacceptable
Measurement is typically counting

defectives
Charts may measure

1. Percent defective (p-chart)
2. Number of defects (c-chart)

S6 - 63
Control Limits for p-Charts

Population will be a binomial distribution, but
applying the Central Limit Theorem allows us
to assume a normal distribution for the sample
statistics
UCL p = p + zs p
LCL p = p - zs p
s p =
p 1- p
where
p = mean fraction (percent) defective in the samples

z = number of standard deviations
s p = standard deviation of the sampling distribution

n = number of observations in each sample
S6 - 64
p-Chart for Data Entry

SAMPLE
NUMBER
NUMBER
OF
ERRORS
NUMBER
OF
ERRORS
FRACTION
DEFECTIVE
SAMPLE
NUMBER
.06
11
.06
.05
12
.01
.00
13
.08
.01
14
.07
.04
15
.05
.02
16
.04
.05
17
11
.11
.03
18
.03
.03
19
.00
10
.02
20
.04
FRACTION
DEFECTIVE
80
S6 - 65

SAMPLE
NUMBER
p=
1
2
Total number
of records
examined
6
.06
11
s p 3=
4
5
NUMBER
OF
FRACTION
SAMPLE
Total
number
of
errors
ERRORS
DEFECTIVE
NUMBER
5
.05
12
NUMBER
OF
80
=ERRORS
(100)(20)
6
1
(.04)(1- .04)
0
.00 (rounded
13up from .0196)
8
= .02
100
1
.01
14
7
4
.04
15
UCL
= p +.02
zs p = .04 +16
3(.02) = .104
2
p
5
.05
17
11
LCL
=
p
z
s
=
.04
3(.02)
=
0
p
p
FRACTION
DEFECTIVE
= .04
.06
.01
.08
.07
.05
.04
.11
.03
18
.03
.03
19
.00
10
.02
20
.04
80
S6 - 66
Fraction defective

.11
.10
.09
.08
.07
.06
.05
.04
.03
.02
.01
.00
UCLp = 0.10
p = 0.04
10
12
14
16
18
20
LCLp = 0.00
Sample number
S6 - 67
Fraction defective
Possible assignable
causes present
.11
.10
.09
.08
.07
.06
.05
.04
.03
.02
.01
.00
UCLp = 0.10
p = 0.04
10
12
14
16
18
20
LCLp = 0.00
Sample number
S6 - 68
Control Limits for c-Charts

Population will be a Poisson distribution, but
applying the Central Limit Theorem allows us
to assume a normal distribution for the sample
statistics
c = mean number of defects per unit

c = standard deviation of defects per unit
Control limits (99.73%) = c 3 c

S6 - 69
c-Chart for Cab Company

c = 54 complaints/9 days = 6 complaints/day
= 6+3 6
= 13.35
LCLc = c - 3 c
= 6-3 6
=0
Number defective
UCLc = c + 3 c
UCLc = 13.35
14
12
10
8
6
4
c= 6
2
0 |
|
1 2
|
3
|
4
|
5
|
6
|
7
|
8
LCLc = 0
|
9
Day
S6 - 70
Managerial Issues and

Control Charts
Three major management decisions:
Select points in the processes that

need SPC
Determine the appropriate charting

technique
Set clear policies and procedures
S6 - 71
Which Control Chart to Use

TABLE S6.3
Helping You Decide Which Control Chart to Use
VARIABLE DATA
USING AN x-CHART AND R-CHART
1. Observations are variables

2. Collect 20 - 25 samples of n = 4, or n = 5, or more, each from a stable
process and compute the mean for the x-chart and range for the R-chart
3. Track samples of n observations
S6 - 72
Which Control Chart to Use

TABLE S6.3
Helping You Decide Which Control Chart to Use
ATTRIBUTE DATA
USING A P-CHART
1. Observations are attributes that can be categorized as good or bad (or
passfail, or functionalbroken), that is, in two states
2. We deal with fraction, proportion, or percent defectives
3. There are several samples, with many observations in each
ATTRIBUTE DATA
USING A C-CHART
1. Observations are attributes whose defects per unit of output can be
counted
2. We deal with the number counted, which is a small part of the possible
occurrences
3. Defects may be: number of blemishes on a desk; crimes in a year;
broken seats in a stadium; typos in a chapter of this text; flaws in a bolt
of cloth
S6 - 73
Patterns in Control Charts

Upper control limit
Target
Lower control limit

Normal behavior. Process is in
control.
Figure S6.7
S6 - 74

Upper control limit
Target
Lower control limit

One plot out above (or below).
Investigate for cause. Process is
out of control.
Figure S6.7
S6 - 75

Upper control limit
Target
Lower control limit

Trends in either direction, 5 plots.
Investigate for cause of
progressive change.
Figure S6.7
S6 - 76

Upper control limit
Target
Lower control limit

Two plots very near lower (or
upper) control. Investigate for
cause.
Figure S6.7
S6 - 77

Upper control limit
Target
Lower control limit

Run of 5 above (or below) central
line. Investigate for cause.
Figure S6.7
S6 - 78

Upper control limit
Target
Lower control limit

Erratic behavior. Investigate.
Figure S6.7
S6 - 79
Process Capability
The natural variation of a process should

be small enough to produce products that
meet the standards required
A process in statistical control does not

necessarily meet the design specifications
Process capability is a measure of the

relationship between the natural variation
of the process and the design
specifications
S6 - 80
Process Capability Ratio

Cp =
Upper Specification Lower Specification

6
A capable process must have a Cp of at

least 1.0
Does not look at how well the process is

centered in the specification range
Often a target value of Cp = 1.33 is used to

allow for off-center processes
Six Sigma quality requires a Cp = 2.0
S6 - 81

Insurance claims process
Process mean x = 210.0 minutes
Process standard deviation = .516 minutes
Design specification = 210 3 minutes
Cp =
Upper Specification - Lower Specification

6
S6 - 82

Cp =

6
213 207
=
= 1.938
6(.516)
S6 - 83

Cp =

6
213 207
=
= 1.938
6(.516)
Process is
capable
S6 - 84
Process Capability Index

The process capability index, Cpk, measures the
difference between the desired and actual
dimensions of goods or services produced.
Cpk = minimum of
Upper
Lower
Specification x , , x Specification
Limit
Limit
3
3
A capable process must have a Cpk of at least

1.0
A capable process is not necessarily in the

center of the specification, but it falls within the
specification limit at both extremes
S6 - 85

New Cutting Machine
New process mean x = .250 inches
Process standard deviation = .0005 inches
Upper Specification Limit = .251 inches
Lower Specification Limit = .249 inches
S6 - 86

New Cutting Machine
(.251) - .250
Cpk = minimum of
,
(3).0005
S6 - 87

New Cutting Machine
(.251) - .250 .250 - (.249)

Cpk = minimum of
,
(3).0005
(3).0005
S6 - 88

New Cutting Machine
(.251) - .250 .250 - (.249)

Cpk = minimum of
,
(3).0005
(3).0005
Both calculations result in
.001
Cpk =
= 0.67
.0015
New machine is
NOT capable
S6 - 89
Figure S6.8
Interpreting Cpk
Cpk = negative number (Process

does not meet specifications)
Cpk = zero (Process
Cpk = between 0 and 1(Process
Cpk = 1 (Process meets
Specifications)
Cpk > 1 (Process meets
Specifications)
Lower
specification
limit
Upper
specification
limit
S6 - 90
Acceptance Sampling
Form of quality testing used for incoming

materials or finished goods
Take samples at random from a lot

(shipment) of items
Inspect each of the items in the sample
Decide whether to reject the whole lot

based on the inspection results
Only screens lots; does not drive quality

improvement efforts
S6 - 91
Acceptance Sampling
Form of quality testing used for incoming

materials or finished goods
Rejected lots can be:

Take samples at random from a lot
1.
Returned
to
the
(shipment) of items
supplier
Inspect each of the items in the sample
2. Culled for defectives
Decide whether to reject
theinspection)
whole lot
(100%
based on the inspection results
3. May be re-graded to a
lower
Only screens lots; does
notspecification
drive quality
improvement efforts
S6 - 92
Operating Characteristic
Curve
Shows how well a sampling plan

discriminates between good and bad
lots (shipments)
Shows the relationship between the

probability of accepting a lot and its
quality level
S6 - 93
The Perfect OC Curve

P(Accept Whole Shipment)
Keep whole
shipment
100
75
Return whole
shipment
50
25
|
0 | |
0 10 20
Cut-Off
|
30 40
50 60
70 80
90 100
% Defective in Lot
S6 - 94
An OC Curve
Figure S6.9
= 0.05 producers risk for AQL
Probability of
Acceptance
= 0.10
Consumers
risk for LTPD
|
0
|
1
|
2
|
3
|
4
|
5
AQL
Good
lots
|
6
|
7
|
8
Percent
defective
LTPD
Indifference
zone
Bad lots
S6 - 95
AQL and LTPD
Acceptable Quality Level (AQL)
Poorest level of quality we are willing to

accept
Lot Tolerance Percent Defective (LTPD)
Quality level we consider bad
Consumer (buyer) does not want to accept

lots with more defects than LTPD
The probability of rejecting a good lot is called a

type I error. The probability of accepting a bad lot is
a type II error.
S6 - 96
Producers and Consumers

Risks
Producer's risk ()
Probability of rejecting a good lot
Probability of rejecting a lot when the

fraction defective is at or above the AQL
Consumer's risk ()
Probability of accepting a bad lot
Probability of accepting a lot when

fraction defective is below the LTPD
S6 - 97
OC Curves for Different

Sampling Plans
n = 50, c = 1
n = 100, c = 2
S6 - 98
Average Outgoing Quality

AOQ =
(Pd)(Pa)(N n)
where
Pd = true percent defective of the lot
Pa = probability of accepting the lot
N = number of items in the lot

n = number of items in the sample
S6 - 99
Average Outgoing Quality

1. If a sampling plan replaces all defectives
2. If we know the incoming percent defective
for the lot
We can compute the average outgoing

quality (AOQ) in percent defective
The maximum AOQ is the highest percent
defective or the lowest average quality
and is called the average outgoing quality
limit (AOQL)
S6 - 100
Automated Inspection
Modern
technologies
allow virtually
100% inspection
at minimal costs
Not suitable for
all situations
S6 - 101
SPC and Process Variability

Lower
specification
limit
Upper
specification
limit
(a) Acceptance sampling

(Some bad units
accepted; the lot is
good or bad)
(b) Statistical process
control (Keep the
process in control)
Process mean, m
(c) Cpk > 1 (Design

a process that
is in within
specification)
Figure S6.10
S6 - 102
Thank you
S6 - 103

Lecture 2-2

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lecture 2-2

Uploaded by

Copyright:

Available Formats

Statistical

2014 Pearson Education, Inc.

Statistical Process Control

2014 Pearson Education, Inc.

x -charts and R-charts

4. List the five steps involved in building

2014 Pearson Education, Inc.

2014 Pearson Education, Inc.

Statistical Process Control

2014 Pearson Education, Inc.

Statistical Process Control

Provides a statistical signal when assignable

Detect and eliminate assignable causes of

2014 Pearson Education, Inc.

2014 Pearson Education, Inc.

Also called common causes

Affect virtually all production processes

Expected amount of variation

Output measures follow a probability

For any distribution there is a measure of

If the distribution of outputs falls within

2014 Pearson Education, Inc.

A distribution may be characterized by its mean,

2014 Pearson Education, Inc.

Also called special causes of variation

Generally this is some change in the process

Variations that can be traced to a specific

The objective is to discover when assignable

Eliminate the bad causes

Incorporate the good causes

2014 Pearson Education, Inc.

2014 Pearson Education, Inc.

2014 Pearson Education, Inc.

(a) Samples of the product,

(b) After enough samples

The solid line

(d) If only natural causes of

2014 Pearson Education, Inc.

(e) If assignable causes are

2014 Pearson Education, Inc.

2014 Pearson Education, Inc.

Lower control limit

(b) In statistical control

(c) Out of control

Control Charts for Variables

Characteristics that can take any real value

May be in whole or in fractional numbers

Continuous random variables

x-chart tracks changes in the central

R-chart indicates a gain or loss of

Central Limit Theorem

2014 Pearson Education, Inc.

Population and Sampling

Mean of sample means = x

-3s x -2s x -1s x

+1s x +2s x +3s x

95.45% fall within 2s x

2014 Pearson Education, Inc.

Setting Chart Limits

x= = mean of the sample means or a target value set for the

2014 Pearson Education, Inc.

Setting Control Limits

2014 Pearson Education, Inc.

Setting Control Limits