INTRODUCTION TO

SPC (Statistical Process Control)

HEIL
1
 TRAINING AGENDA
HANDS ON LEARNING!!

Limitation of Inspection

Specification discussion

What is SPC?

Why SPC is a better?

How SPC works?

Control Chart

You may learn to like statistics.

2
 FF EXERCISE
EXERCISE

IMAGINE FOR ONE BRIEF MOMENT THAT EACH OF THE ONE HUNDRED
AND FORTY-ONE WORDS OF THIS PARAGRAPH IS A SEPARATE
COMPONENT FORM A FIRST SHIFT RUN OF FOURTEEN-INCH
FLYWHEELS. YOU ARE ONE OF FIVE INSPECTORS PERFORMING THE
FINAL INSPECTION OF THSES FINSISHED COMPONENTS WHICH WERE
PRODUCED ON FOUR FAIRLY SMALL DIAL INDEX MACHINES THAT ARE
NOT BEING CONTROLLED BY THE USE OF STATISTICAL TECHNIQUES.
AS CAN BE EXPECTED FROM AN OPERATION OF THIS NATURE, THERE
ARE A NUMBER OF DEFECTIVES COMPONENTS BEING MADE. EACH
WORD THAT CONTAINS AN F REPRESENTS A DEFECTIVE COMPONENT.
HOW MANY OF THE DEFECTIVES ARE YOU ABLE TO FIND? CHECK
AGAIN AND INSPECT FOR THE PRESENTS OF F'S. WRITE YOUR FINAL
COUNT IN THE BOTTOM LEFT HAND CORNER OF THIS PAGE. THIS
EXAMPLE SHOULD GIVE YOU A FAIR IDEA OF HOW RELIABLE 100%
INSPECTION CAN BE.
3
 INSPECTION
Draw sample

YE N
Meets spec. ?
S O

ACCEPT REJECT

How good was it? How bad was it?


Barely meet spec? 
Just outside spec?

middle of spec? 
Way out of spec?

Same as before? 
Same as before?

4
 INSPECTION

Lower Spec.

A
B

What's the difference between ball A and B?

Why is the spec there and not somewhere else?
What is the purpose of the spec? 5
 Great!!!
I'm in spec.

SPECIFICATION

6
 Hey!!!!!
But I'm in spec.

SPECIFICATION

7
 TARGET
Every specification has a TARGET.
The upper and lower specification
is meant to serve as a
guide line. What you
really want is the stuff
that hits the TARGET.

8
SCREW SPECIFICATION

SCREW TOLERANCE = +/- .02"

UPPER SPEC = .27

TARGET= .25
LOWER SPEC = .23

9
NUT SPECIFICATION

NUT TOLERANCE = +/- .02"

UPPER SPEC = .28

TARGET= .26
LOWER SPEC = .24

10
 COMBINED TOLERANCE
SCREW
UPPER SPEC = .27
TARGET= .25
SCREW = 26.8"
LOWER SPEC = .23

NUT
UPPER SPEC = .28
NUT = 24.8"
TARGET= .26
LOWER SPEC = .24
11
LEANRING 1
Meeting specification
is not enough

we need a way to
communicate more.
What ???

12
 Average
e
pl Income
m
a
Ex

Country X Country Y

10,000 Rs/Month 11000 Rs/Month

Which country is ECONOMICALLY more stable ???

13
Country X Country Y

8000 46000
12000 3000
10000 1000
9000 3000
11000 2000

Avg. 10000 11000

Std dev. 1414 17516
14
 LEANRING 2
Meeting specification is not enough
we need a way to communicate

How close to target

How spread out the results were

15
 What is SPC?


Statistical Process Control

A monitoring tool that let's us know when
a process is changing before products
become unacceptable

It is a prevention tool
– Inspection = defect detection
– SPC =detect process change
defect prevention

16
 WHY SPC?


Inspection does not assure quality

inspection is too late, its after the fact

need to detect process change before
defectives are produced

Meeting specification does not go far
enough

17
 SPC, how does it work

Quantitify the Mue and the Sigma of a

process and detects change from the
standard deviation by calculating the
control limit by estimating the Rbar over
d2 to estimate the inherent variation of
a process for a given alpha and beta
risks.
Ooopps tough to understand……
18
JUST KIDDING!
It is simple and easy to understand.

SPC quantifies
variability and allows
you to determine if a
process changed.

19
 DISCUSSION ON VARIABILITY

First order

lower Upper
spec.
size spec.

20
 Second order

lower Upper
spec.
size spec.

21
 After 6 orders

lower Upper
spec.
size spec.

22
 After 12 orders

lower Upper
spec.
size spec.

23
lower Upper
spec.
size spec.

Over the long run a pattern begins to develop. Notice

there is a large cluster in the middle. As further from
the middle you go, there are less and less
24
 lower Upper
spec. size spec.

If the source of the material is stable, over a long

time period, a bell like shaped curve will emerge
from the inspection. The Bell shape curve is also
commonly referred to as the Normal distribution
25
What is HITOGRAM?
Why we need it to understand?
What is this BELL shape and normal distribution?

Plot HISTOGRAM for following DATA

Data
4.2 12.4 6
5.2 14.8 7.8
5.4 18 11
2.1 17 11.8
9 19 9.4
9.6 15.5 10.8
13 2 10
14 5 11
15 7 10.1
9.6 10.1 8.8
26
 LEANRING 3
CHARACTERISTICS OF A
NORMAL DISTRIBUTION
LOCATION
SPREAD:
The dispersion it is
usually expressed as
LOCATION:
SIGMA
The central tendency
it is usually
expressed as the
AVERAGE

27
SPREAD
 Distribution Patterns

Saw tooth Negatively Skewed Positively Skewed

Sharp Drop Twin Peak Bell Shape

28
Average different
Spread same

29
A B
 Average same
Spread different

A 30
B
Average different
Spread different

31
A B
 LEANRING 4
SIGMA -measure of spread

sigma

32
 +/-3 sigma

+/- 2 sigma

+/- 1 sigma

2% 2% 33
14% 32% 32% 14%
 +/-3 sigma
99.73%
+/-2 sigma
96.45%
+/-1 sigma
64.25%

2% 2% 34
14% 32% 32% 14%
 LEANRING 5
99.73%
+/-3 sigma

95.45%
+/- 2 sigma

68.26%
+/- 1 sigma

2.14% 13.6% 34.13% 34.13% 13.6% 2.14%

35
IF the upside-down bell curve could hold
100 gallons of water.....

2
14
32
gallons

64%
+/-1 sigma

+/-2 sigma 96%

+/-3 sigma 99.7%
36
 LEANRING 6
Properties of a normal model curve :-
•It is symmetrical , unimodel and bell shaped.
•It is uniquely determined by the two parameters ,
namely mean and standard deviation.
•In the family of normal curves smaller the standard
deviation , higher will be the peak.
•If the original observations follow a normal model with
mean mu and std dev sigma then the averages of random
sample of size n drawn from this distribution will also
follow a normal distribution.
•The mean of the new model is same as the original
model I.e mu but the standard deviation gets reduced to
 (sigma)/root "n" 37
 Sources of Variation
Common Cause

Special Cause

38
 LEANRING 7
If only common cause of variation are present, the
output of a process forms a distribution that is
stable over time and is
PREDICTABLE.

PREDICTION

E
M
TI 39
 SO WHAT?

That's great, we can make prediction based

on sigma, So what?

Once we know the sigma of a process then;

Process has not changed if it is inside +/- 3
sigma.
If outside +/- 3 sigma, process has changed

40
 LEANRING 8

SINCE WE CAN NOT SAMPLE 100 UNITS TO

DETERMINE IF OUR MANUFACTURING PROCESS
HAS CHANGED WE NEED A QUICK EFFECTIVE
WAY TO MEASURE THE TWO ATTRIBUTE OF
A PROCESS; THE CENTER AND THE SPREAD

CENTER = AVERAGE
SPREAD = RANGE
= (MAXIMUM - MINIMUM)

Why Average ????

41
LEANRING 9
The Central Limit Theorem

The Central Limit Theorem states that the mean values

of samples taken from ANY distribution tend towards a
normal distribution as the sample size increases.
This computer demonstration provides convincing evidence of this surprising fact. Thus, taking
samples from a distribution and averaging the observations
within the samples effectively eliminates the effect of the underlying distribution, however 'non-
normal' it may be.
This demonstration works with two symmetrical distributions: one is triangular and has some
features in common with the normal distribution while the other is a 'V'-shaped notch - almost the
total opposite of the type of distributions we see in applied statistics. Both distributions have a
mean of 50.00. We can model these distributions by supposing we have two packs containing
cards numbered 1 - 99. The first pack would have: One 1, two 2s .... fifty 50s, forty nine
51s, .... two 98s, and one 99 While the second would have:
Fifty 1s, forty nine 2s ... two 48s, one 50, two 51s, ..... fifty 99s
The computer draws cards according to these distributions for sample sizes of 1 (to verify the
concept of 'distribution'), 2, 5 and 10.
When the sample size is 1, we are really confirming that the data 'in the long run' will behave like
the distribution - which is in itself an important statistical lesson.
The case {Sample Size = 2} is particularly interesting. It is not easy to to 'outguess' the
computer and predict the shape of the lower curve; however, once the curve is seen, it can be
readily explained in terms of basic probability.
Although the second case is very extreme (literally!) compared with the first, it eventually falls42
into a 'normal' shape although it takes longer to do so.
The Arithmetic mean :
Most of the time when we refer to the average of something
we are talking about arithmetic mean only. To find out the
arithmetic mean , we sum the values and divide by the number
of observation.

Advantages : it's a good measure of central tendency.It easily

understood by most people

Disadvantages :- Although the mean is reliable in that it

reflects all the values in the data set, it may also be affected by
extreme values that are not representative of the rest of the
data.

43
 The Median :
The median is a single value from the data set that measures
the central item in the set of numbers.Half of the item lie
above this point and the other half lie below it.

We can find median even when our data are qualitative

descriptions.

For example we have five runs of the printing press the results
of which must be rated according to the sharpness of the
image.
Extremely sharp, very sharp, sharp slightly blurred, and very
blurred.

Mode :-
The mode is a value that is repeated most often in the data set.
Infect it is the value with highest frequency.
44
 How was our process behaving
over time? Let's calculate the
average and range of each set
CONTROL CHART TEMPLATE
1 23
2 23
3 24
4 26
5 27
Average
Range

average = (23+23+24+26+27)/5 Range = 27 - 23

= 24.6 =4
45
 CONTROL CHART TEMPLATE
1 23 22 23 22
2 23 25 23 24
3 24 25 24 24
4 26 26 27 25
5 27 27 27 26
avg 24.6 25.0 24.8 24.2
Min.
Max
Range
Plott the average and
4 5 4 4
the range on the control
chart template
average

Notice the center and the spread

of the process varies much like
range

when we looked at the histogram

46
 LEANRING 9
If you thought of the control charts as a stretched out
slinky, it would look like a histogram if you collapsed
it. Since the control chart is nothing more than a
histogram expressed over time, what we said about
SIGMA applies to the control chart as well.

x-bar Chart
x x
x xx
x xxx xxx
x xxx xxx x
x xxx xxx
x xx
x xx
xx
x xx

47
 Reminder, what we said about sigma

IF the upsidedown bell curve could

hold 100 gallons of water.....

2
32 14
gallons

64%
+/-1 sigma

+/-2 sigma 96%

+/-3 sigma 99.7%
48
We can calculate the sigma of all the points in the
control charts and draw lines at +/- 3 sigma. Since
99.7% of the vaules are suppose to fit in the line
we can say that a process has changed if it one of
the points are outside the +/- 3 sigma lines. We
will call the +/-3 sigma lines the CONTROL LIMIT

xx
xxx
xxxxxxxx
xxxxxxx
xxxxxxx +/- 3 sigma
xxx
xxx
xx
xxx 49
HOW DO YOU CALCULATE CONTROL LIMITS?

In the past it was important for operators and auditors

to be able to calculate the control limit. Today, in most
manufacturing plants the computer calculates the
control limits and people interpret them.

This makes sense because computers are excellent

at calculating number. However, computers are not
too intelligent. They can not reason and make good
decisions. People are very capable of reasoning and
making good decision. However, people need good
information. SPC is a tool that converts process data to
information allowing people to focus on what they do best.

50
 LEANRING 10
Control Limits for
Average and Range Chart
X+X+X+…X R+R+R+…R
1 2 3 n 1 2 3 n
X = R =
n n

UCL = X + A2R UCL = D4R

CL =X CL =R
LCL = X - A2R LCL = D3R

51
 WE USE STATISTICS EVERYDAY

HOW LONG DOES IT TAKE TO GET TO WORK?

52
 TYPES OF VARIABILITY
Common cause= normal, Inherent
Arrive work between 7:55 to 8:01due to number traffics lights
that you stopped at on your way to work.

Special cause = assignable

Arrived to work today at 8:45 because;
a) flat tire on the way to work
b) Accident on the interstate
c) I met up with an old drinking buddy and
I stayed out later than I should have.

53
 PROCESS CAPABILITY ANALOGY

Bill, Nice guy. works in the accounting Judge Lance Ito. Nice guy. Works in Los
department. He lives 10 miles away from Angeles. He lives 5 miles from work. In orde
work. In order to get to work he takes the to get to work he has to get through 5 traffic
interstate I-95 and gets off at exit 23 and light onto interstate I-5(which is frequently
zips right into work. He never hits any backed up) to downtown Los Angeles. There
trafficand there is no traffic light between he has to find parking and then fight the
his home and work. reporters on his way into the court to preside
He's never late to work. over the O.J. Simpson trial. 54
He is late to work quite frequently.
 PROCESS CAPABILITY ANALOGY

Bill Judge Lance Ito

Arrives to work between Arrives to work between 7:48 to 8:06 AM
7:48 to 7:56 AM.

Late to work
Early
to
work

7:42 7:48 7:54 8:00 8:06 8:12

Arrival time at work 55

 PROCESS CAPABILITY ANALOGY
If we thought of being early or late to work as our
specification, then we can say that Bill IS capable
meeting the specification. Judge Ito IS NOT capable
of meeting the specification.

Bill
Late to work
Early
to Judge Ito
work

7:42 7:48 7:54 8:00 8:06 8:12

Arrival time at work

56
 PROCESS CAPABILITY ANALOGY
Bill Judge Lance Ito
Arrives to work between Arrives to work between 7:48 to
7:48 to 7:56 AM 99.7% of time. 8:06 AM 99.7% of time.
6 sigma = 7:56 -7:48 = 8 min. 6 sigma = 8:06 - 7:48 = 18 min.

Tolerance = late - early = 8:00 - 7:46 = 14 minutes

Capability = tolerance if greater than 1 we say it
6 sigma is capable of meeting spec.

Bill's Capability = 14 / 8 = 1.75 (Bill is capable)

Ito's Capability = 14/18 = .78 (Ito IS NOT capable)
57
 LEANRING 11

Cp = Tol band / 6 sigma

Cpk = Min of (Avg - LSL) or (USL - Avg) / 3 sigma

_ _ 2 _

 √
2 2
(x-x1 ) + (x-x2) + … (x-x )
= n
(n-1)
(n - 1)

 (R abr) =
R
d2
58
 The control limits can be drawn around both the
average (x-bar) and the Range chart. Therefore,
you can detect several different types of change.
X-bar chart
xx
xxx
xxxxxxx
xxxxxxxx
xxxxxxx
xxx +/- 3 sigma
xxx
xx
xxx

Range chart
xxx
xx
xxx
xxx
xxxxxxxx
xxxxxxx +/- 3 sigma
xxxxxxx
xxx
xx
59
 LOCATION SHIFTS

Process spread
remains same
let's see what
while center
that looks like
increases
in a control chart

60
 Spread remains same
Center shifts up
X-bar chart

+/- 3 sigma

Range chart

+/- 3 sigma

61
 SPREAD CHANGE

Process spread
increase while
center remain
same let's see what
that looks like
in a control chart

62
 Spread increased
Center remain same
X-bar chart

+/- 3 sigma ?
Range chart

+/- 3 sigma

63
 Spread increased
Center remain same
X-bar chart

+/- 3 sigma

Range chart

+/- 3 sigma

64
 LEANRING 12
Note that when the process variation increased
the Range chart points shifted to a higher level.
However, the process center (X-bar) seems to
swing wildly going out of both Upper and Lower
control limit while the average is still the same.

Because of the tendency of the X-bar chart to

swing with increase variability, the Range chart
must be reviewed first to determine if the process
variability increased prior to looking at the X-bar
chart to determine if the process shifted.

65
 TREND

target
+/- 3 sigma

Rule of thumb, if there are 7 points in a row all higher or lower

than the preceeding point. In this case from the start of the
trend to the time a point went outside the control limit there were
12 samples. An experinced operator/auditor would begin looking
for assignable cause much sooner. 66
 SHIFT

target
+/- 3 sigma

Rule of thumb, if there are 6 consequetive points above or below the

target line, a process shift has occurred. In this case, because the
process shifted to somewhere between the target and the upper control
limit, there is a good chance that a point will be outside the control limit
soon. In the above example, it took about 11 points to go outside the
control limit. An experienced operator/auditor would have looked for
assignable cause sooner. 67
Summary.. Process changes

Small shift .. in Center while Spread same

in Spread while Center same

Large shift in Center up or down while Spread same

Spread increase while Center same

Center slowly trending up or down while spead same

Center shift up or down at the same time the spread

increase 68
 PROCESS CAPABILITY

So you now know how to detect change in a

process. You even know how to detect different
type of change to the process distribution. Up to
now we have not talked about the QUALITY of the
products being produced while the process is
controlled using SPC methods.

If we control the process the process will produce

parts with variation as the equipment is CAPABLE
of producing. We call this PROCESS CAPABILITY.

69
 Cp Cpk..... Say what?

TARGET
Cpk Cp
Lower Upper
spec. spec.

7:42 7:48 7:54 8:00 8:06 8:12

70
 Cpk = Target - lower spec or Upper spec - Target
3 sigma 3 sigma

Cpk looks at the likelihood of making product outside

either lower or upper specification

Cpk Cpk

TARGET
Lower Upper
spec. spec.

7:42 7:48 7:54 8:00 8:06 8:12

71
 LEANRING
IT IS IMPORTANT TO KNOW
WHAT YOUR MACHINE IS
CAPABLE OF PRODUCING.
OTHERWISE YOU MAY BE
CHASING YOUR TAIL
TRYING TO GET THE
MACHINE TO DO WHAT IT IS
NOT CAPABLE OF DOING.
72
 Each red x represents five individual
reading (blue x) that are spread out
more than the average (red x)

x UPPER SPEC X-bar chart

x x
x
xxx UpperControl Limit
x xx x x
xx x x xx x xx xx
x
xx x xx xxx x x x xxx
x x x xx xxxxxxx = x xxxxxxxx
x x
x x x xx xxxxxxx
xx x xxxxxxx
x x x xx xxxxxxx x x xxxxxxx
xxxxxxx xxx
x x xxx xx
x xxx
xx xxx xxx
x xx
xx xxxxxxx xx x
x
xxx
x xxx
xx LowerControl Limit
x
x LOWER SPEC Each point is an average
x of five indivdual points

Control chart will not differentiate a capable and

a not capable process. it will only signal change.
The control chart does not care what the spec 73is.
 LEANRING
If your process is not capable, then there is a good
chance that some of your sample will have values
outside the specification. Chances are if you are not
running SPC control chart, you may be tempted to
x make an adjustment. Let's see what would happen.
x Upper spec
x
xxx
machine capability

x xx x
xx x xxx xxx
xx x
x xx xxxxx
x x xx xxxxxxx
x x
x x x xx xxxxxxx
xx x
x x x xx xxxxxxx x
xxxxxxx
x x xxx xx
x xxx
xx xxx
x
xx xxxxxxxxx x
x xxx
xx
x
x Lower spec
x
74
 LEANRING
If by the luck of the draw you get a reading below the
lower specification even though the process has not
changed, and adjusted the machine up.
The distribution will shift up.

x Upper spec Sample

machine capability

x
x
xx
x
xx xx x
xx x
x xxx
xxxxxxx
x x x
x x x xx xxxxxxx x
x x x xx xxxxxxxxx x
x x x x x xxxxxxx
x x x xx xxxxxxx xx = x up
x x xxxx x
x xxx
xx
x xxx
ne
x xxxxxxx x
x x hi
xx
x
xxx
xx Lower spec
x ac
x t m
x us
dj
A 75
 LEANRING
After the distribution shifted up, there is now a
much greater chance of getting a value outside
upper specification. So the machine is adjusted
down, slightly more than it was adjusted up.
Chance of out of
spec was = 10%
x
x Chance of out of
xx
x spec is now = 40%
xxxxx x
machine capability

x Upper spec xx x xxx

xxxxxxx
x x x x x
x x x xx xxxxxxx
x
xx x x x xx xxxxxxxxx Ad
x x x x
xx xx x
x x xxx xxx xxxxxxx
xxxxxxx ju
st
xxx x xxx
xxxxxxxx x x x xxx x xxxxxx m
x x x xx xxxxxxx x x
x xxxxxxx xxx
x ac
x x x xx xxxxxxxx x x x
x x
x xxxx xxxxx hi
xxx xxxxxxx
xxxxxxx xx ne
x x xxx x x
x xxx
xx xxx x do
x xxxxxxxx x x x wn
x
xx x x
xxx
xx Lower spec
x
x 76
x
 LEANRING 13
The adjustments continues until, the actual products
produced varies much more than the capability of the
machine.

Actual range of product produced

x
x x
xx x
xx x
x x xxxx xxx
machine capability

x x
xx xx x xxx x xx x
xx Upper spec x x x
x xxx x xxx x xx x x xx x xx
x
xx x x x xx
x
x
xxxxxxxx
xxxxxxxx xx x xx xxx x x
x xx x
xx x x xx x xx x x x
x xxx x xxxxxxx x x xx
x
x xx xxxxxxxx
x x xx xxxxxxx x x xxx x xxxxxxxx
x
x xxx x xxx x x x
x xxxxxxxx x x xxxx
x xxx xxx xx x x x xx
x xxxxxxx
x xxxxxxx
x xxx xx xxxxxxx x x xx
x xx x xx xx x x xxx x xxxxxx
x x x xx xxxxxxxx x x
x x x xx xxxxxxx x xxxxx x x xx x
xx x x xx x xx
x x xx
x
x x xxx xx x
xx x
x x xxx x xxx x xx x x x
xx x xx xxx x x x xxxx
x x xxxxxxxxx x x x x xx xxxxxxx x
x xxx x
x x xxx x x
xx x
x xx xxxxxxxx
x xx xxxxxxxx xx
xx Lower spec x x x x xx xxxxxxx x
x x x xxx x xxxxxx x
x x x xx
x
xxx xx x
xxx
x x x
x x xxx
xx
x
x
x 77
 LEANRING 14
If you are controlling your process using SPC Method,
even if your process is not capable, no adjustment
would take place. Therefore, the product you produced
is what the machine is capable of and not more.

x x
machine capability

x
xxx Upper spec
x x
UpperControl Limit
xx xx x xx
xx x
x xxx
xxxxxxx x xxx
x x x
x x x xx xxxxxxx = x xxxxxxx
x x x xx xxxxxxxxx xxxxxxxx
x x x x x xxxxxxx
x x x xx xxxxxxx
x xxxxxxx
xxx
x x xxx x xxxxxx xxx
xx
x x x
xxxxx x
xxx xx
x x
x x xxx
x xxx
x LowerControl Limit
xx Lower spec
x
x

78
 ATTRIBUTE CONTROL CHARTS

Defectives Defects

Variable
Sample
p-Chart c - Chart
Fixed
Sample np-Chart u - Chart

79
Measurement
System
Analysis
(MSA) 80