Statistical Process Control Statistical Process Control
Chapter 3 Chapter 3
Operations Management - 6
thEdition Operations Management - 6
thEdition
Roberta Russell & Bernard W. Taylor, III
Roberta Russell & Bernard W. Taylor, III
Lecture Outline Lecture Outline
Basics of Statistical Process Control Basics of Statistical Process Control
Control Charts Control Charts
Control Charts for Attributes Control Charts for Attributes
Control Charts for Variables Control Charts for Variables
Control Chart Patterns Control Chart Patterns
SPC with Excel and OM Tools SPC with Excel and OM Tools
Process Capability Process Capability
Basics of Statistical Basics of Statistical Process Control
Process Control
Statistical Process Control Statistical Process Control (SPC)
(SPC)
monitoring production monitoring production process to detect and
process to detect and
UCLUCLprocess to detect and
process to detect and prevent poor quality prevent poor quality
Sample Sample
subset of items produced to subset of items produced to use for inspection
use for inspection
Control Charts Control Charts
process is within statistical process is within statistical control limits
control limits
UCL UCL
LCL LCL
Basics of Statistical Basics of Statistical Process Control
Process Control (cont.) (cont.)
Random Random
inherent in a process inherent in a process
depends on depends on
equipment and equipment and
Non Non- -Random Random
special causes special causes
identifiable and identifiable and correctable
correctable equipment and
equipment and machinery,
machinery,
engineering, operator, engineering, operator, and system of
and system of measurement measurement
natural occurrences natural occurrences
correctable correctable
include equipment out of include equipment out of adjustment, defective
adjustment, defective materials, changes in materials, changes in parts or materials,
parts or materials,
broken machinery or
broken machinery or
equipment, operator
equipment, operator
fatigue or poor work
fatigue or poor work
methods, or errors due
methods, or errors due
SPC in Quality Management SPC in Quality Management
SPC SPC
tool for identifying problems in tool for identifying problems in order to make improvements
order to make improvements order to make improvements order to make improvements
contributes to the TQM goal of contributes to the TQM goal of continuous improvements
continuous improvements
Quality Measures:
Quality Measures:
Attributes and Variables Attributes and Variables
Attribute Attribute
a product characteristic that can be a product characteristic that can be evaluated with a discrete response evaluated with a discrete response evaluated with a discrete response evaluated with a discrete response
good good –– bad; yes bad; yes - - no no
Variable measure Variable measure
a product characteristic that is a product characteristic that is continuous and can be measured continuous and can be measured
weight weight - - length length
Nature of defect is different in Nature of defect is different in services
services
SPC Applied to SPC Applied to Services
Services
services services
Service defect is a failure to meet Service defect is a failure to meet customer requirements
customer requirements
Monitor time and customer Monitor time and customer satisfaction
satisfaction
SPC Applied to SPC Applied to Services (cont.) Services (cont.)
Hospitals Hospitals
timeliness and quickness of care, staff responses to timeliness and quickness of care, staff responses to requests, accuracy of lab tests, cleanliness, courtesy, requests, accuracy of lab tests, cleanliness, courtesy, accuracy of paperwork, speed of admittance and
accuracy of paperwork, speed of admittance and checkouts
checkouts checkouts checkouts
Grocery stores Grocery stores
waiting time to check out, frequency of out waiting time to check out, frequency of out- -of of- -stock stock items, quality of food items, cleanliness, customer items, quality of food items, cleanliness, customer complaints, checkout register errors
complaints, checkout register errors
Airlines Airlines
flight delays, lost luggage and luggage handling, waiting flight delays, lost luggage and luggage handling, waiting time at ticket counters and check
time at ticket counters and check- -in, agent and flight in, agent and flight
attendant courtesy, accurate flight information, passenger attendant courtesy, accurate flight information, passenger cabin cleanliness and maintenance
cabin cleanliness and maintenance
SPC Applied to SPC Applied to Services (cont.) Services (cont.)
Fast Fast- -food restaurants food restaurants
waiting time for service, customer complaints, waiting time for service, customer complaints, cleanliness, food quality, order accuracy,
cleanliness, food quality, order accuracy, employee courtesy
employee courtesy employee courtesy employee courtesy
Catalogue Catalogue- -order companies order companies
order accuracy, operator knowledge and courtesy, order accuracy, operator knowledge and courtesy, packaging, delivery time, phone order waiting time packaging, delivery time, phone order waiting time
Insurance companies Insurance companies
billing accuracy, timeliness of claims processing, billing accuracy, timeliness of claims processing, agent availability and response time
agent availability and response time
Where to Use Control Charts Where to Use Control Charts
Process has a tendency to go out of control Process has a tendency to go out of control
Process is particularly harmful and costly if it Process is particularly harmful and costly if it goes out of control
goes out of control
Examples Examples
Examples Examples
at the beginning of a process because it is a waste at the beginning of a process because it is a waste of time and money to begin production process of time and money to begin production process with bad supplies
with bad supplies
before a costly or irreversible point, after which before a costly or irreversible point, after which product is difficult to rework or correct
product is difficult to rework or correct
before and after assembly or painting operations before and after assembly or painting operations that might cover defects
that might cover defects
before the outgoing final product or service is before the outgoing final product or service is delivered
delivered
Control Charts Control Charts
A graph that A graph that
establishes control establishes control limits of a process limits of a process
Control limits Control limits
Types of charts Types of charts
Attributes Attributes
p p- -chart chart
Control limits Control limits
upper and lower bands upper and lower bands of a control chart
of a control chart
p p- -chart chart
c c- -chart chart
Variables Variables
mean (x bar mean (x bar –– chart) chart)
range (R range (R- -chart) chart)
Process Control Chart Process Control Chart
Upper Upper control control limit limit
Process Process
Out of control Out of control
1
1 22 33 44 55 66 77 88 99 1010
Sample number Sample number Process
Process average average
Lower
Lower
control
control
limit
limit
Normal Distribution Normal Distribution
µ
µ=0 =0 1 1σ σ 2 2σ σ 3 3σ σ --1 1σ σ
--2 2σ σ --3 3σ σ
95%
99.74%
A Process Is in A Process Is in Control If …
Control If …
1. … no sample points outside limits
2. … most points near process average 2. … most points near process average 3. … about equal number of points above
and below centerline
4. … points appear randomly distributed
Control Charts for Control Charts for Attributes
Attributes
p-chart
uses portion defective in a sample
uses portion defective in a sample
c-chart
uses number of defective items in
a sample
p
p--Chart Chart
UCL = p + zσ p LCL = p - zσ p
z = number of standard deviations from process average
p = sample proportion defective; an estimate of process average
σ
p= standard deviation of sample proportion
σ σ
pp= =
p
p(1 (1 -- p p))
n
n
Construction of p
Construction of p--Chart Chart
NUMBER OF
NUMBER OF PROPORTION PROPORTION SAMPLE
SAMPLE DEFECTIVES DEFECTIVES DEFECTIVE DEFECTIVE
1
1 6 6 .06 .06
2
2 0 0 .00 .00
20 samples of 100 pairs of jeans 20 samples of 100 pairs of jeans
2
2 0 0 .00 .00
3
3 4 4 .04 .04
:: :: ::
:: :: ::
20
20 18 18 .18 .18
200
200
Construction of p
Construction of p--Chart (cont.) Chart (cont.)
p(1 - p) 0.10(1 - 0.10)
= 200 / 20(100) = 0.10 total defectives
total sample observations
p =
UCL = p + z p(1 - p) = 0.10 + 3 n
0.10(1 - 0.10) 100
UCL = 0.190
LCL = 0.010
LCL = p - z p(1 - p) = 0.10 - 3 n
0.10(1 - 0.10)
100
0.10 0.10 0.12 0.12 0.14 0.14 0.16 0.16 0.18 0.18 0.20 0.20
Proportion defectiveProportion defective
UCL = 0.190
p = 0.10
Construction Construction of p
of p--Chart Chart (cont.)
(cont.)
0.02 0.02 0.04 0.04 0.06 0.06 0.08 0.08 0.10 0.10
Proportion defectiveProportion defective
2
2 44 66 88 1010 1212 1414 1616 1818 2020 LCL = 0.010
(cont.)
(cont.)
cc--Chart Chart
UCL =
UCL = c c + + z zσ σ c c LCL =
LCL = c c -- z zσ σ σ σ c c = = c c LCL =
LCL = c c -- z zσ σ c c
where
c = number of defects per sample
σ
σ c c = = c c
cc--Chart (cont.) Chart (cont.)
Number of defects in 15 sample rooms Number of defects in 15 sample rooms
1 12
1 12
SAMPLE SAMPLE c c = = 12.67 = = 12.67 190 190 15 15 NUMBER OF DEFECTS 2 8
2 8
3 16
3 16
: : : : : : : : 15 15
15 15 190 190
15 15 UCL
UCL = = c c + + z zσ σ
cc= 12.67 + 3 12.67
= 12.67 + 3 12.67
= 23.35
= 23.35 LCL
LCL = = c c -- z zσ σ
cc= 12.67
= 12.67 -- 3 12.67 3 12.67
= 1.99
= 1.99
12 12 15 15 18 18 21 21 24 24
Number of defectsNumber of defects
UCL = 23.35
c = 12.67
cc--Chart Chart (cont.) (cont.)
3 3 6 6 9 Number of defectsNumber of defects 9
Sample number Sample number 2
2 44 66 88 1010 1212 1414 1616 LCL = 1.99
(cont.)
(cont.)
Control Charts for Control Charts for Variables
Variables
Range chart ( R-Chart )
uses amount of dispersion in a
uses amount of dispersion in a sample
Mean chart ( x -Chart )
uses process average of a
sample
x
x--bar Chart: bar Chart:
Standard Deviation Known Standard Deviation Known
UCL =
UCL = xx + + zzσσ
xxLCL = LCL = xx -- zzσσ
xxUCL =
UCL = xx + + zzσσ
xxLCL = LCL = xx -- zzσσ
xxxx + + xx + ... + ... xx xx + + xx + ... + ... xx
==== ====
xx 11 + + xx 22 + ... + ... xx nn xx 11 + + xx 22 nn + ... + ... xx nn xx == nn
xx ==== ==
where where
x
x = average of sample means = average of sample means where
where
x
x ==== = average of sample means = average of sample means
x
x--bar Chart Example: bar Chart Example:
Standard Deviation Known (cont.)
Standard Deviation Known (cont.)
x
x--bar Chart Example: bar Chart Example:
Standard Deviation Known (cont.)
Standard Deviation Known (cont.)
x
x--bar Chart Example: bar Chart Example:
Standard Deviation Unknown Standard Deviation Unknown
UCL =
UCL = xx + + AA 22 RR LCL = LCL = xx -- AA 22 RR
UCL =
UCL = xx == + + AA 22 RR LCL = LCL = xx == -- AA 22 RR
where where
xx = average of sample means = average of sample means where
where
xx = average of sample means = average of sample means
Control
Control
Limits
Limits
x
x--bar Chart Example: bar Chart Example:
Standard Deviation Unknown 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
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
50.09 1.15
x
x--bar Chart Example: bar Chart Example:
Standard Deviation Unknown (cont.) Standard Deviation Unknown (cont.)
R = = = 0.115
R = ∑ R = = 0.115
k
∑ R k
1.15 10 1.15
10
UCL = x + A
2R = 5.01 + (0.58)(0.115) = 5.08 LCL = x - A
2R = 5.01 - (0.58)(0.115) = 4.94
=
=
x = = = 5.01 cm = ∑x k
50.09 10
Retrieve Factor Value A
2UCL = 5.08
Mean
5.10 – 5.08 – 5.06 – 5.04 – 5.02 – 5.00 –
x = 5.01=
x
x-- bar bar Chart Chart
Example Example (cont.) (cont.)
LCL = 4.94
Sample number
| 1
| 2
| 3
| 4
| 5
| 6
| 7
| 8
| 9
| 10 4.98 –
4.96 – 4.94 – 4.92 –
R
R-- Chart Chart
UCL =
UCL = D D 4 4 R R LCL = LCL = D D 3 3 R R
R
R = = ∑ ∑R R R
R = = ∑ ∑R R k k
where where
R
R = range of each sample = range of each sample k
k = number of samples = number of samples
R
R--Chart Example Chart Example
OBSERVATIONS (SLIP
OBSERVATIONS (SLIP--RING DIAMETER, CM) RING DIAMETER, CM) SAMPLE
SAMPLE k k 1 1 2 2 3 3 4 4 5 5 x x R R 1
1 5.02 5.02 5.01 5.01 4.94 4.94 4.99 4.99 4.96 4.96 4.98 4.98 0.08 0.08 2
2 5.01 5.01 5.03 5.03 5.07 5.07 4.95 4.95 4.96 4.96 5.00 5.00 0.12 0.12 3
3 4.99 4.99 5.00 5.00 4.93 4.93 4.92 4.92 4.99 4.99 4.97 4.97 0.08 0.08 4
4 5.03 5.03 4.91 4.91 5.01 5.01 4.98 4.98 4.89 4.89 4.96 4.96 0.14 0.14 4
4 5.03 5.03 4.91 4.91 5.01 5.01 4.98 4.98 4.89 4.89 4.96 4.96 0.14 0.14 5
5 4.95 4.95 4.92 4.92 5.03 5.03 5.05 5.05 5.01 5.01 4.99 4.99 0.13 0.13 6
6 4.97 4.97 5.06 5.06 5.06 5.06 4.96 4.96 5.03 5.03 5.01 5.01 0.10 0.10 7
7 5.05 5.05 5.01 5.01 5.10 5.10 4.96 4.96 4.99 4.99 5.02 5.02 0.14 0.14 8
8 5.09 5.09 5.10 5.10 5.00 5.00 4.99 4.99 5.08 5.08 5.05 5.05 0.11 0.11 9
9 5.14 5.14 5.10 5.10 4.99 4.99 5.08 5.08 5.09 5.09 5.08 5.08 0.15 0.15 10
10 5.01 5.01 4.98 4.98 5.08 5.08 5.07 5.07 4.99 4.99 5.03 5.03 0.10 0.10 50.09
50.09 1.15 1.15
R
R--Chart Example (cont.) Chart Example (cont.)
UCL = D 4 R = 2.11(0.115) = 0.243 UCL = D 4 R = 2.11(0.115) = 0.243
Retrieve Factor Values D
Retrieve Factor Values D
33and D and D
44LCL = D 3 R = 0(0.115) = 0
LCL = D 3 R = 0(0.115) = 0
R
R--Chart Example (cont.) Chart Example (cont.)
UCL = 0.243 0.28 –
0.24 – 0.20 –
LCL = 0
R a n g e
R = 0.115
| 1
| 2
| 3
| 4
| 5
| 6
| 7
| 8
| 9
| 10 0.16 –
0.12 –
0.08 –
0.04 –
0 –
Using x
Using x-- bar and R bar and R--Charts Charts Together
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
Control Chart Patterns 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
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)
Control Chart Patterns (cont.) Control Chart Patterns (cont.)
UCL UCL UCL
UCL
LCL LCL
Sample observations Sample observations consistently above the consistently above the center line
center line LCL
LCL
Sample observations Sample observations consistently below the consistently below the center line
center line
Control Chart Patterns (cont.) Control Chart Patterns (cont.)
UCL UCL
UCL UCL
LCL LCL
Sample observations Sample observations consistently increasing
consistently increasing LCL LCL
Sample observations
Sample observations
consistently decreasing
consistently decreasing
Zones for Pattern Tests Zones for Pattern Tests
UCL
Zone A
Zone B
Zone C Process
3 sigma = x + A= 2R
2 sigma = x + (A= 2 2R) 3
1 sigma = x + (A= 1 2R) 3
=
LCL
Zone C
Zone B
Zone A Process
average
3 sigma = x - A= 2R 2 sigma = x -= 2 (A2R)
3
1 sigma = x -= 1 (A2R) 3
x=
| 1
| 2
| 3
| 4
| 5
| 6
| 7
| 8
| 9
| 10
| 11
| 12
| 13
Performing a Pattern Test Performing a Pattern Test
1
1 4.98 4.98 B B — — B B
2
2 5.00 5.00 B B U U C C
3
3 4.95 4.95 B B D D A A
4
4 4.96 4.96 B B D D A A
SAMPLE
SAMPLE x x ABOVE/BELOW ABOVE/BELOW UP/DOWN UP/DOWN ZONE ZONE
4
4 4.96 4.96 B B D D A A
5
5 4.99 4.99 B B U U C C
6
6 5.01 5.01 — — U U C C
7
7 5.02 5.02 A A U U C C
8
8 5.05 5.05 A A U U B B
9
9 5.08 5.08 A A U U A A
10
10 5.03 5.03 A A D D B B
Sample Size Determination Sample Size Determination
Attribute charts require larger sample sizes
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
SPC with Excel
SPC with Excel
SPC with Excel and OM Tools
SPC with Excel and OM Tools
Process Capability Process Capability
Tolerances Tolerances
design specifications reflecting product design specifications reflecting product requirements
requirements requirements requirements
Process capability Process capability
range of natural variability in a process range of natural variability in a process— — what we measure with control charts
what we measure with control charts
Process Capability (cont.) Process Capability (cont.)
(a) Natural variation (a) Natural variation exceeds design exceeds design
specifications; process specifications; process is not capable of
is not capable of
meeting specifications meeting specifications all the time.
all the time.
Design Design Specifications Specifications
(b) Design specifications (b) Design specifications and natural variation the and natural variation the same; process is capable same; process is capable of meeting specifications of meeting specifications most of the time.
most of the time.
Design Design Specifications Specifications
Process Process all the time.
all the time.
Process Process
Process Capability (cont.) Process Capability (cont.)
(c) Design specifications (c) Design specifications greater than natural
greater than natural variation; process is variation; process is capable of always capable of always conforming to conforming to specifications.
specifications.
Design Design Specifications Specifications
specifications.
specifications.
Process Process
(d) Specifications greater (d) Specifications greater than natural variation, than natural variation, but process off center;
but process off center;
capable but some output capable but some output will not meet upper
will not meet upper specification.
specification.
Design Design Specifications Specifications