Chapter 3

Statistical Process Control

OOppeerraatioonnssManagement
Operations
MMaannaaggeemmeennt
Roberta Russell & Bernard W. Taylor, III
 Lecture Outline

 Basics of Statistical Process

Control
 Control Charts
 Control Charts for Attributes
 Control Charts for Variables
 Control Chart Patterns
 SPC with Excel and OM Tools
 Process Capability
3-121
 Basics of Statistical
Process Control
 Statistical Process Control
(SPC)
 monitoring production process
to detect and prevent poor UCL
quality
 Sample
subset of items
produced to use for LCL
inspection
 Control Charts
 process is within statistical
control limits

3-122
 Basics of Statistical
Process Control (cont.)
 Random 
Non-Random
 inherent in a process  special causes

 depends on equipment  identifiable and

and machinery, correctable
engineering, operator,  include equipment out of
and system of adjustment, defective
measurement materials, changes in
 natural occurrences parts or materials, broken
machinery or equipment,
operator fatigue or poor
work methods, or errors
due to lack of training
3-123
 SPC in Quality Management


SPC  tool for identifying problems in
order to make improvements
 contributes to the TQM goal of
continuous improvements

3-124
 Quality Measures:
Attributes and Variables


Attribute
 a product characteristic that can be

evaluated with a discrete

 response
good – bad; yes - no
 Variable
measure
 a product characteristic that is continuous

and can be measured

 weight - length

3-125
 SPC Applied to
Services

 Nature of defect is different in

services
 Service defect is a failure to meet
customer requirements
 Monitor time and customer
satisfaction

3-126
 SPC Applied to
Services
(cont.)
 Hospitals
 timeliness and quickness of care, staff responses to
requests, accuracy of lab tests, cleanliness, courtesy,
accuracy of paperwork, speed of admittance and checkouts
 Grocery stores
 waiting time to check out, frequency of out-of-stock items,
quality of food items, cleanliness, customer complaints,
checkout register errors
 Airlines
 flight delays, lost luggage and luggage handling, waiting time
at ticket counters and check-in, agent and flight attendant
courtesy, accurate flight information, passenger cabin
cleanliness and maintenance

3-127
 SPC Applied to
Services
(cont.)
 Fast-food restaurants
 waiting time for service, customer complaints,
cleanliness, food quality, order accuracy, employee
courtesy
 Catalogue-order companies
 order accuracy, operator knowledge and courtesy,
packaging, delivery time, phone order waiting
time
 Insurance companies
 billing accuracy, timeliness of claims processing,
agent availability and response time

3-128
 Where to Use Control Charts

 Process has a tendency to go out of control

 Process is particularly harmful and
costly if it goes out of control
 Examples
 at the beginning of a process because it is a waste of
time and money to begin production process with
bad supplies
 before a costly or irreversible point, after
which product is difficult to rework or correct
 before and after assembly or painting operations that
might cover defects
 before the outgoing final product or service
is delivered

3-129
 Control Charts

 A graph that establishes Types of

control limits
of a process charts
 Attributes

 Control limits  p-chart

 upper and lower bands  c-chart
of a control chart
 Variables
 mean (x bar – chart)
 range (R-chart)

3-130
 Process Control Chart
Out of control
Upper

control
limit

Proces
s
average
Lower

control
limit

1 2 3 4 5 6 7 8 9 10
Sample number

3-131
Normal Distribution

95%
99.74%
-3 -2 -1 =0 1 2 3

3-132
 A Process Is in
Control If …

1. … no sample points outside limits

2. … most points near process average
3. … about equal number of points
above and below centerline
4. … points appear randomly distributed

3-133
 Control Charts
for Attributes

 p-chart
 uses portion defective in a sample
 c-chart
 uses number of defective items in
a sample

3-134
p-Chart

UCL = p + zp
LCL = p - zp
z = number of standard deviations from
process average
p = sample proportion defective; an estimate
of process average
p = standard deviation of sample proportion

p(1 - p)
p =
n
3-135
Construction of p-Chart

NUMBER OF PROPORTION
SAMPLE DEFECTIVE
1 DEFECTIVES .06
2 6 .00
3 0 .04
: 4 :
: : :
: .18
20
18
200
20 samples of 100 pairs of jeans

3-136
Construction of p-Chart
(cont.)
total defectives
p= = 200 / 20(100) = 0.10
total sample observations
p(1 - p) 0.10(1 - 0.10)
UCL = p + z = 0.10 + 3
n 100
UCL = 0.190
p(1 - p) 0.10(1 - 0.10)
LCL = p - z = 0.10 - 3
n 100
LCL = 0.010

3-137
 0.20

0.18 UCL = 0.190

0.16

0.14

Proportion defective
of p-
Construction 0.12
p = 0.10
0.10
Chart 0.08

(cont.) 0.06

0.04

0.02 LCL = 0.010

2 4 6 8 10 12 14 16 18
20
Sample number

3-138
c-Chart

UCL = c + zc
c = c
LCL = c - zc

where

c = number of defects per sample

3-139
 c-Chart (cont.)
Number of defects in 15 sample
rooms
NUMBER
OF
SAMPLE
DEFECTS 190
c= = 12.67
1 12 15
2 8
3 16 UCL = c + zc
= 12.67 + 3 12.67
: : = 23.35
: :
LCL = c - zc
15 15
= 12.67 - 3 12.67
190
= 1.99

3-140
 24
UCL = 23.35
21

18

Number of defects
c = 12.67

c-Chart
15

12

(cont.) 6

3 LCL = 1.99

2 4 6 8 12 14 16
10
Sample number

3-141
 Control Charts
for Variables
 Range chart ( R-Chart )
 uses amount of dispersion in a
sample
 Mean chart ( x -Chart )
 uses process average of a
sample

3-142
x-bar Chart:
Standard Deviation Known

UCL = x= + zx LCL = =x -

zx
1 + 2 + ... n
x= n
=
wher
e =
x = average of sample
means
3-143
x-bar Chart Example:
Standard Deviation Known (cont.)

3-144
x-bar Chart Example:
Standard Deviation Known (cont.)

3-145
x-bar Chart Example:
Standard Deviation Unknown

UCL = x=+ LCL = x= -

A 2R A 2R

where

x = average of sample
means

3-146
Control
Limits

3-147
 x-bar Chart Example:
Standard Deviation Unknown
OBSERVATIONS (SLIP- RING DIAMETER, CM)
SAMPLE k 1 2 3 4 5 x R
1 5.02 5.01 4.94 4.99 4.96 4.98 0.08
2 5.01 5.03 5.07 4.95 4.96 5.00 0.12
3 4.99 5.00 4.93 4.92 4.99 4.97 0.08
4 5.03 4.91 5.01 4.98 4.89 4.96 0.14
5 4.95 4.92 5.03 5.05 5.01 4.99 0.13
6 4.97 5.06 5.06 4.96 5.03 5.01 0.10
7 5.05 5.01 5.10 4.96 4.99 5.02 0.14
8 5.09 5.10 5.00 4.99 5.08 5.05 0.11
9 5.14 5.10 4.99 5.08 5.09 5.08 0.15
10 5.01 4.98 5.08 5.07 4.99 5.03 0.10
Example 15.4 50.09 1.15
3-148
x-bar Chart Example:
Standard Deviation Unknown (cont.)
∑R 1.15
R= k = 10 = 0.115

x 50.09
= = 5.01
x= cm
= k 10

UCL = x +=A2R = 5.01 + (0.58)(0.115) =

5.08

LCL = x =- A2RRetrieve
= 5.01 -Factor
(0.58)(0.115)
Value A=2 4.94
3-149
 5.10 –

5.08 –
UCL = 5.08

5.06 –

5.04 –

Mean 5.02 – x== 5.01

5.00 –

x- bar 4.98 –
Chart
Example 4.96 – LCL = 4.94

(cont.) 4.94 –

4.92 – | | | | |
| | | | | 1
2 3 4 5 6 7 8 9 10
Sample number

3-150
R- Chart

UCL = D4R LCL = D3R

R
R=
k
where
R = range of each sample
k = number of samples

3-151
 R-Chart Example
OBSERVATIONS (SLIP-RING DIAMETER, CM)
SAMPLE k 1 2 3 4 5 x
R
1 5.02 5.01 4.94 4.99 4.96 4.98 0.08
2 5.01 5.03 5.07 4.95 4.96 5.00 0.12
3 4.99 5.00 4.93 4.92 4.99 4.97 0.08
4 5.03 4.91 5.01 4.98 4.89 4.96 0.14
5 4.95 4.92 5.03 5.05 5.01 4.99 0.13
6 4.97 5.06 5.06 4.96 5.03 5.01 0.10
7 5.05 5.01 5.10 4.96 4.99 5.02 0.14
8 5.09 5.10 5.00 4.99 5.08 5.05 0.11
9 5.14 5.10 4.99 5.08 5.09 5.08 0.15
10 5.01 4.98 5.08 5.07 4.99 5.03 0.10
Example 15.3 50.09 1.15
3-152
 R-Chart Example (cont.)

UCL = D4R = 2.11(0.115) = 0.243

LCL = D3R = 0(0.115) = 0

Retrieve Factor Values D3 and D4

Example 15.3
3-153
R-Chart Example (cont.)
0.28 –

0.24 – UCL = 0.243

0.20 –
Range

0.16 – R = 0.115

0.12 –

0.08 –
LCL = 0
0.04 – | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10
0– Sample number

3-154
 Using x- bar and R-Charts
Together

 Process average and process variability must be in

control
 It is possible for samples to have very narrow
ranges, but their averages might be beyond control
limits
 It is possible for sample averages to be in
control, but ranges might be very large
 It is possible for an R-chart to exhibit a distinct
downward trend, suggesting some nonrandom cause is
reducing variation

3-155
 Control Chart Patterns

 Run
 sequence of sample values that display same
characteristic
 Pattern test
determines if observations within limits of a control chart display
a nonrandom pattern
 To identify a pattern:
 8 consecutive points on one side of the center line
 8 consecutive points up or down
 14 points alternating up or down
 2 out of 3 consecutive points in zone A (on one side of center
line)
 4 out of 5 consecutive points in zone A or B (on one side
of center line)

3-156
 Control Chart Patterns (cont.)
UCL

UCL

LCL

Sample observations
LCL
consistently below the
center line
Sample observations
consistently above the
center line
3-157
 Control Chart Patterns (cont.)
UCL

UCL

LCL

Sample observations
consistently increasing LCL

Sample observations
consistently decreasing

3-158
 Zones for Pattern Tests
UCL =
3 sigma = x + A2R
Zone A
= 2
2 sigma = x + (A2R)
3
Zone B
= 1
1 sigma = x + (A2R)
3
Zone C
Process =
x
average Zone C
= 1
1 sigma = x - (A2R)
3
Zone B
= 2
2 sigma = - (A R)
x
Zone A
2
=
LCL 3 sigma = x - A2R
| | | | | | | |
1 2 3 4 | | |
Sample number
| | 5 6 7
8 9 10 11 12 13
3-159
 Performing a Pattern Test
SAMPLE x ABOVE/BELOW UP/DOWN ZONE

1 4.98 B — B
2 5.00 U
3 4.95 B C
4 4.96 D
5 4.99 B U A
C
6 5.01 — D
7 5.02 B
A U A
C
8 5.05
9 5.08 A U C
10 5.03
A U B

A U A
3-160

D B
 Sample Size Determination

 Attribute charts require larger sample

sizes  50 to 100 parts in a sample
 Variable charts require smaller samples
 2 to 10 parts in a sample

3-161
SPC with Excel

3-162
SPC with Excel and OM Tools

3-163
 Process Capability


Tolerances
 design specifications reflecting product

requirements
 Process
capability
 range of natural variability in a process—

what we measure with control charts

3-164
 Process Capability (cont.)
Design
Specifications

(a)Natural variation
exceeds design
specifications; process
is not capable of
meeting specifications
all the time.
P
r
o
c
e
s
s
Design
Specifications

(b)Design specifications
and natural variation the
same; process is capable
of meeting specifications
most of the time. 3-165
 Process Capability (cont.)
Design
Specifications

(c)Design
specifications greater
than natural variation;
process is capable of
always conforming to
specifications.
P
r
o
c
e
s
s
Design
Specifications

(d)Specifications
greater than natural
variation, but process off 3-166
center; capable but
Process Capability Measures

Process Capability Ratio

tolerance range
Cp
= process range

upper specification limit -

lower specification limit
=
6

3-167
Computing Cp
Net weight specification = 9.0 oz  0.5 oz
Process mean = 8.80 oz
Process standard deviation = 0.12 oz

upper specification limit -

lower specification limit
Cp
= 6

= 9.5 - 8.5 = 1.39

6(0.12)

3-168
 Process Capability Measures

Process Capability Index

= x - lower specification limit

3
,
Cpk = minimum
=
upper specification limit - x
3

3-169
Computing Cpk
Net weight specification = 9.0 oz  0.5 oz
Process mean = 8.80 oz
Process standard deviation = 0.12 oz

=
x - lower specification limit
,
= minimum 3 =
Cpk upper specification limit - x
3

8.80 - 8.50 9.50 - 8.80

= minimum 3(0.12) , 3(0.12) = 0.83

3-170
Process Capability
with Excel

3-171
Process Capability
with Excel and OM Tools

3-172
Chapter 3 Supplement

Acceptance Sampling

OOppeerraatioonnssManagement
Operations
MMaannaaggeemmeennt
Roberta Russell & Bernard W. Taylor, III
 Lecture Outline

 Single-Sample Attribute Plan

 Operating Characteristic Curve
 Developing a Sampling Plan with
Excel
 Average Outgoing Quality
 Double - and Multiple-Sampling Plans

Supplement 3-174
 Acceptance Sampling

Accepting or rejecting a production lot

based
on the number of defects in a sample
philosophy
Not consistent with TQM or Zero Defects
 producer and customer agree on the number of
acceptable defects
 a means of identifying not preventing poor
quality
 percent of defective parts versus PPM
Sampling plan
 provides guidelines for accepting a lot
Supplement 3-175
 Single–Sample
Attribute Plan
Single sampling plan
N = lot size
n = sample size (random)
c = acceptance number
d = number of defective items in sample
If d ≤ c, accept lot; else reject

Supplement 3-176
 Producer’s and
Consumer’s Risk
 AQL or acceptable quality level
 proportion of defects consumer will accept in
a given lot
  or producer’s risk
 probability of rejecting a good lot
 LTPD or lot tolerance percent
defective
 limit on the number of defectives the
customer will accept
 β or consumer’s risk
 probability of accepting a bad lot
Supplement 3-177
Producer’s and
Consumer’s Risk
(cont.)Accept
Good Lot
Reject

Type I Error
No Error
Producer’ Risk
Bad Lot

Type II Error
No Error
Consumer’s Risk

Sampling Errors

Supplement 3-178
 Operating Characteristic
(OC) Curve
 shows probability of accepting lots of
different quality levels with a specific
sampling plan
 assists management to discriminate
between good and bad lots
 exact shape and location of the
curve is
defined by the sample size (n) and
acceptance level (c) for the sampling
plan
Supplement 3-179
OC Curve (cont.)
1.00 –
 = 0.05

0.80 –

Probability of acceptance, Pa

0.60 – OC curve for n and c

0.40 –

0.20 –

 = 0.10
| | | | |
– | | | | |
0.02 0.04 0.06 0.08 0.10 0.12 0.14 0.16 0.18
AQL LTPD
0.20
Proportion defective
Supplement 3-180
 Developing a Sampling
Plan with OM Tools

ABC Company produces mugs

in lots of 10,000. Performance
measures for quality of mugs
sent to stores call for a
producer’s risk of 0.05 with an
AQL of 1% defective and a
consumer’s risk of 0.10 with a N = 10,000 n=?
LTPD of 5% defective. What α = 0.05 c=
size sample and what ?
acceptance number should
ABC use to achieve β = 0.10
performance measures AQL = 1%
called for in the sampling LTPD = 5%
plan?
Supplement 3-181
 Average Outgoing
Quality (AOQ)

Expected number of defective

items that will pass on to
customer with a sampling plan
 Average outgoing quality limit
(AOQL)
 maximum point on the curve
 worst level of outgoing quality

Supplement 3-182
AOQ Curve

Supplement 3-183
 Double-Sampling Plans

 Take small initial sample

 If # defective ≤ lower limit, accept
 If # defective > upper limit, reject
 If # defective between limits, take
second sample
 Accept or reject based on 2 samples
 Less costly than single-sampling plans

Supplement 3-184
 Multiple-Sampling Plans

 Uses smaller sample sizes

 Take initial sample
 If # defective ≤ lower limit, accept
 If # defective > upper limit, reject
 If # defective between limits, resample
 Continue sampling until accept or reject
lot based on all sample data

Supplement 3-185