Statistical Process Control

Metallized Ceramics Division

 Topics
 Measurement for improvement
 What is SPC?
 Introduction to variation
 What is Sigma?
 Normal Distribution
 Central Tendency
 Process Capability analysis
 Home work

Metallized Ceramics Division

 What do you know?

Your Name
What do you know about SPC?

Metallized Ceramics Division

 Ground Rules

Actively participate
Keep your mobile off
Ask question at any point of time
Specific to topic only


Avoid cross-talks
Enjoy the program

Metallized Ceramics Division

 Pilot’s Six Sigma Performance

Width of landing
strip 1/2 Width
of landing
strip

If pilot always lands

within 1/2 the landing strip
width, we say that he has
Six-sigma capability.

Metallized Ceramics Division

 *
Model for improvement
What are we trying to
accomplish?
measurement to
How will we know that a
change is an improvement? show progress in
What changes can we make
that will result in the relation to the
improvements that we seek ?
aims and targets

Act Plan But how to

demonstrate
that
Study Do improvement?

Metallized Ceramics Division

 Why Measure?
 Measurements for judgement
 to decide on accept / reject
 Measurements for diagnosis
 to show where problems are
 often temporary

 Measurements for improvement**

 a few specific measures
 to show if improvements are being made
 linked to the programme and project aims
 measure over time
Metallized Ceramics Division
 How to Measure Improvement/Change?
Compare to some arbitrary fixed point in the past
 the average waiting time of patients in Vijaya
Hospital fell slightly over the month of January
2009 (from 3 hours 14 minutes to 2 hours 30
minutes).

Show percentage change this month and to some

arbitrary fixed point in the past
 the number of people coming late fell this month by
7.4%, and is now less than 15 (5%). This is below
the peak of February 2009.

Metallized Ceramics Division

 Comparing this year to last year

Delayed Discharges (w eekly Sitreps) 2000/01

7000 2001/02
6000
No. of delayed

5000
discharges

4000
3000
2000
1000
0

W eeks from October

Metallized Ceramics Division

 Comparisons
Production in CNC1/day

230
201
201
172
No of cylinders

144 132

115
86
57
28
0
1 7
Month

Metallized Ceramics Division

 Track Progress over Time

No of setup in CNC3

ge
230

an
Ch
201
172
No of setup

144
115
86
57
28
00
1 2 3 4 5 6 7 8 9 10 11 12
Month

Metallized Ceramics Division

 Comparisons

No of tubes per tool in CNC2

70 63
60

50 45
No of tubes

40

30

20

10

0
1 7
Month

Metallized Ceramics Division

 Track Progress over Time

First Pass Yield in Green Machining

100
90
80
70
Percentage

60
50
40
30
20
Ch
an
10 ge
0
1 2 3 4 5 6 7 8 9 10 11 12
Month

Metallized Ceramics Division

 Exercises 
 List out what are you measuring at your work area?
 Mention what for you are measuring?
 List out what other parameters you can measure?

Metallized Ceramics Division

 What is SPC?

Metallized Ceramics Division

 SPC
 P is for Process
 We deliver our work through processes
 S is for Statistical
 because we use some statistical concepts to
understand our processes
 C is for Control
 this we mean predictable

Statistical Process Control

Controlling the process through the use of statistical techniques and tools
Metallized Ceramics Division
 Logic of SPC
Desired Process Capability
Output
●
Upper Control Limit

Controller ●
Lower Control Limit
Samples

Input Process Output

A B C D E L M N O P
Controllable factors Uncontrollable factors
- Assignable causes - Common causes
- Adjustable - Noise
- Special - Inherent causes

SPC is used to monitor and control the output of processes.

Metallized Ceramics Division

 What can it do for me?
 Identify if a process is sustainable over time
 Identify real change in a process
 Understand different types of variation
 normal or special to a process
 Identify appropriate action for improving a
process
 Make better predictions and improve decision
making
 Understand capability of process to meet targets

Metallized Ceramics Division

 Development of SPC

 Pre - 1924 Non - scientific sampling

 1924 First control chart devised by
Walter Shewhart
 1931 Publication of “Economic
Control of Quality of
Manufactured Product”
 1940 -1945 Courses on “Variation” run in
the U.S
 1946 Formation of the “American
Society for Quality”
Metallized Ceramics Division
 Development of SPC

 1950 Deming’s first seminar in Japan.

Commencement of wide-scale on-
going statistical training programme in
Japan.
 1981 Deming appears in American
documentary - “If Japan can, why
can’t we?”
 1982 Major world-wide SPC initiative
undertaken by the Ford Motor Co.

Metallized Ceramics Division

 Variation

Metallized Ceramics Division

 Understanding Variation

When the Lord created the world and people to live in it, he
reasoned with himself as follows:

“If I make everything predictable, these human beings, whom I

have endowed with pretty good brains, will undoubtedly learn to
predict everything,

and they will thereupon have no motive to do anything at all,

because they will recognize that the future is totally determined

and cannot be influenced by any human action.

Metallized Ceramics Division

 Understanding Variation
On the other hand, if I make everything unpredictable,

they will gradually discover that there is no rational basis for any
decision whatsoever and, as in the first case, they will thereupon
have no motive to do anything at all.

Neither scheme would make sense.

I must therefore create a mixture of the two.

Let some things be predictable and let others be unpredictable.

They will then, amongst many other things, have the very
important task of finding out which is which.
Metallized Ceramics Division
 Understanding Variation

Variation is natural……
Variation is inherent to a process……

Metallized Ceramics Division

 Introduction to Variation

 Think of your normal routine for coming to

work every day. This is a process!
 How long does it take on average?
 What factors might cause you to take
longer (or shorter) than usual?

Metallized Ceramics Division

 Walter A. Shewhart
(early 1920’s, Bell Laboratories)

 While every process displays variation:

 some processes display controlled variation
(common cause)
 stable,consistent pattern of variation
 constant causes/ “chance”

 while others display uncontrolled variation

(special cause)
 pattern changes over time
 can be “assigned” to specific causes

Metallized Ceramics Division

 Journey to work

 Which are common causes of variation?

 And which are special causes?

 Tell me reasons why you come early to work?

 Tell me reasons why you come late to work?

Metallized Ceramics Division

 My trip to work
Accident on tyre had Stopped by police for
motorway puncture speeding

120

100
average
80

Min. 60

40 School holidays
20
Borrowed helicopter
0

Metallized Ceramics Division Consecutive trips

 “A phenomenon will be said to be controlled
when, through the use of past experience,
we can predict, at least within limits, how
the phenomenon may be expected to vary
in the future”

Shewart - Economic Control of Quality of Manufactured Product, 1931

Metallized Ceramics Division

 Predictable within limits

35
30
Upper
Control
Routine variation
Journey Time (hours)

Limit
25
20
Median Unless the
15 Lower
process is
10 Control
Limit
changed it will
continue to
5
0
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 operate this way
Patient number
in the future

Metallized Ceramics Division

 Signs of exceptional variation

35
Exceptional
variation
Upper

30 Control
Journey Time (hours)

Limit
25
20
Median Attributed to
15 Lower assignable causes
10 Control

5
Limit
Seek to identify
0 assignable causes -
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35
Patient number eliminate if bad,
learn from if good
Dominant cause-
and-effect
relationships
Metallized Ceramics Division
 My trip to work
Upper Process
120 Limit

100

80 Av

Min. 60
Lower
40 Process
Limit
20

COMMON CAUSE VARIATION - Consecutive trips

Points within the yellow lines is
variation you would expect - normal
variation of the process (my trip to
Metallized
work) Ceramics
E.G. traffic lights,Division
pedestrians,
rush hour
 Causes of Variation
 Common Causes:
 Random variation within predictable range (usual)
 No pattern
 Inherent in process
 Adjusting the process increases its variation

 Special Causes
 Non-random variation (unusual)
 May exhibit a pattern
 Assignable, explainable, controllable
 Adjusting the process decreases its variation

Metallized Ceramics Division

 Exercises 
 Write causes of variation for one of the defect you
have seen at your work area.

 Divide them in to common causes and special causes

Metallized Ceramics Division

 What is Sigma?

Metallized Ceramics Division

 Have you ever…
 Shot a rifle?
 Played darts?

What is the point of these sports?

What makes them hard?

Metallized Ceramics Division

 Have you ever…

 Shot a rifle?
 Played darts?
Jack

Jill

Who is the better shooter?

Metallized Ceramics Division
 Variability
8
 Deviation = distance between 7
observations and the mean (or 10
8
average) 9

Observations Deviations
Jack

10 10 - 8.4 = 1.6

9 9 - 8.4 = 0.6

8 8 - 8.4 = -0.4

8 8 - 8.4 = -0.4

7 7 - 8.4 = -1.4 Jill

averages 8.4 0.0

Metallized Ceramics Division

 Variability
 Deviation = distance between
observations and the mean (or average)

Observations Deviations
Jack
7 7 - 6.6 = 0.4
7 7 - 6.6 = 0.4
7 7 - 6.6 = 0.4
7
6 6 - 6.6 = -0.6
6
6 6 - 6.6 = -0.6 7
averages 6.6 0.0 7
6 Jill
Metallized Ceramics Division
 Variability
8
 Variance = average distance 7
between observations and the mean 10
8
squared 9

Jack
Observations Deviations Squared Deviations
10 10 - 8.4 = 1.6 2.56
9 9 – 8.4 = 0.6 0.36
8 8 – 8.4 = -0.4 0.16
8 8 – 8.4 = -0.4 0.16
7 7 – 8.4 = -1.4 1.96
averages 8.4 0.0 1.0 Jill

Metallized Ceramics Division Variance

 Variability
 Variance = average distance
between observations and the mean
squared
Jack

Observations Deviations Squared Deviations

7 7 - 6.6 = 0.4 0.16
7
7 7 - 6.6 = 0.4 0.16
6
7 7 - 6.6 = 0.4 0.16 7
6 6 – 6.6 = -0.6 0.36 7
6 Jill
6 6 – 6.6 = -0.6 0.36
averages 6.6 0.0 0.24
Variance
Metallized Ceramics Division
 Variability
 Standard deviation =
square root of variance

Jack
Average Variance Standard
Deviation
Jack 8.4 1.0 1.0
Jill 6.6 0.24 0.4898979

Jill

But what good is a standard deviation

Metallized Ceramics Division

 Normal Distribution

If we take the height of all the people of India and draw a distribution
Of frequencies it will tend to follow a normal distribution

Metallized Ceramics Division

 Normal Distribution

Mean
X-bar

Metallized Ceramics Division

 Normal Distribution

Mean
X-bar USL
LSL

LSL and USL are those specification limits beyond which your
product doesn’t have a salable value in the market
Metallized Ceramics Division
 Normal Distribution

Mean
X-bar USL
LSL

Metallized Ceramics Division

 Normal Distribution
68.26% Fall Within +\- 1 Sigma
95.46% Fall Within +\- 2 Sigma SIGMA=s
99.73% Fall Within +\- 3 Sigma

34.13% 34.13%

13.60% 13.60%
2.14% 2.14%

0.13% 0.13%

-3s -2s -1s X +1s +2s +3s

68.26%

95.46%

99.73%

And that is what a standard deviation

is good for
Metallized Ceramics Division
 Normal Distribution

y
1SD= 68% DATA

2SD = 95% DATA

3SD = 99%DATA

0
x
Metallized Ceramics Division
 Normal Curve – Yield/Rejection

The Percentage 68.3 %

1
Acceptable Area under 95.45 %

the Curve Increases as 99.73 %
the Z Value ( the Number 
of Standard Deviations 99.9936 %

Increases .
99.99 99 4 %

99.99 99 99 8 %

USL x LSL

The Area Under the Curve represents the Acceptance or Yield,

whereas the Area outside the Curve represents the Rejection

Metallized Ceramics Division

 Normal Curve
Normal Distribution Curve is known as Density
Curve meaning the area under the curve is
equal to one.
A.) The Normal curve is a bell shaped curve and it
has single peak (Mode ) at the center.
B) The mean & median of the distribution are equal
and are located at the peak.
USL x
C) The Normal distribution curve is symmetrical
about the mean.
D) The curve is asymptotic i.e the curve gets close
to X-Axis but it never touches it

Metallized Ceramics Division

 Measures of Central Tendency of Data
A.) Mean : The mean of a set of Observations is their average. It is equal to the sum of all
Observations divided by the number of Observations in the set. E.g Consider the data set
given below

1 , 2 , 3 , 4 , 5 ; Mean = 1+ 2 + 3 + 4 + 5 = 15/5 = 3

X = X =
n
Mean of Sample, i x1 +x2 +x3 +x4+……..xn
I=1

n
b.) Median : The Median term of the given data is given by
Median = n + 1 th term, where n is the number of
2
Observations in the given data(arranged in increasing order).

E.g 3, 5 , 1 , 8 , 2 , 7 , 1 , 4 . No. of Terms = 8, Arrange data in Increasing Order = 1 , 1 , 2 , 3 , 4 , 5 , 7,

8

Median Term = 4.5th Term = 4th Term + 0.5 ( 5th - 4th Term ) = 3 + 0.5 ( 4- 3) = 3.5
Metallized Ceramics Division
 Measures of Central Tendency of Data

C) Mode : The value Occurring maximum number of times

E.g 3, 4 , 3, 6, 5, 3, 7, 4 , Mode = 3

E.g Calculate the Median of the Following data :

2, 4, 6, 8, 12, 15, 10
Sol. Arrange the data in Increasing Order
2, 4, 6 , 8 , 10 , 12 , 15
[Link] Observations = (7 + 1 ) / 2 = 4th Term = 8

Metallized Ceramics Division

 Measures of Spread/Dispersion of Data
a.) Range : The Difference between Maximum & Minimum value.
b) Standard Deviation (  : It gives tells us about the variation in data .
c ) Variance ( It is defined as the square of the standard deviation to
account for the total variation observed in the data.

E.g : The Process Specification = 10 ± 2

Sol. USL = 12 , LSL =8 Range = USL - LSL = 12 - 8 = 4 M ean = 3
2
Consider the data set 3, 2, 5, 1, 4 D a ta V a ria t io n V a ria t io n
1 -2 4
Mean = 3 2 -1 1
Standard Deviation (  ) = (10/4 )1/2 = 1. 5 3 0 0
4 1 1
Variation (  ) = 2.25 5 2 4
0 10

Metallized Ceramics Division

 Standard Deviation (Sigma)
2
X X–X (X-X)
1 130 –20 400
2 166 16 256
3 178 28 784
4 131 –19 361
5 140 –10 100
n

X
6 125 –25 625
7 127 –23 529 Sample Mean i

8 145 –5 25
X= i =1

9 110 –40 1600

n
10 184 34 1156
11 161 11 121 n

 (X - X )
2

12 194 44 1936 Sample i

13 171 21 441 Standard Deviation s= i 1

14 125 –25 625 n 1

15 163 13 169 n

 (X - X )
2

Sum 2250 9128 i

n
150  (X - X )
2
Mean
i
i 1
652
S2
n 1
S1 25.53
n

 (X - X )
2

i
i 1

n 1
Metallized Ceramics Division
 Exercises 
 Calculate Mean, Standard Deviation for the data given
in the Exercise 1

 Plot Normal distribution curve

Metallized Ceramics Division

 Process Capability Analysis - Cp
Cp = Specification
Process Width width
LSL Process USL
Width

Process variability
SPECIFICATION WIDTH
Metallized Ceramics Division
 Process Capability Analysis - Cp
Process Capability Ratios

The greater the design margin, the lower the Total Defects Per Unit

Design margin is measured by the Process Capability Index (Cp)

Specification Width

Cp = USL - LSL
Process width X Cp =
-3 +3 

Process Width

Specification Width
CP > 1 (Traditional)
CP >= 2 (Six sigma)
Metallized Ceramics Division
 Process Capability Analysis - CpK

LSL USL

Process variability
SPECIFICATION WIDTH
Metallized Ceramics Division
 Process Capability Analysis - CpK
From a statistics perspective, There are only two problems.

Problem with Spread Problem with Centering

Desired
Desired
Current
Current situation
situation

LSL T USL LSL T USL

Shift

Accurate but not Precise Precise but not Accurate

Metallized Ceramics Division

 Process Capability Analysis - CpK

Good quality: Poor quality: defects

defects are rare are common (Cpk<1)
(Cpk>1)

μ
μ target
target

Cpk measures “Process Capability”

If process limits and control limits are at the same location, C pk = 1. Cpk ≥ 2 is exceptional.

Metallized Ceramics Division

 Process capability
Good quality: defects are rare (Cpk>1)
Poor quality: defects are common (Cpk<1)
= Mean
USL – x
= 24 – 20 =.667
3σ 3(2)
Cpk = min
=
x - LSL
= 20 – 15 =.833
3σ 3(2)

CpK > 1.33 (Traditional)

CpK > 1.67 (CTQ)
CpK >= 2.00 (Six sigma) 14 20 26
15 24
Metallized Ceramics Division
 Exercises 
 Calculate Cp, CpK for the data given in Exercise 1

 Give your judgement

Metallized Ceramics Division

 Home Work 
 Identify the process parameters which you can study
for improvement at your work area….

 For at least one parameter collect 50 – 100 data in the

process and study the following –

• Mean, Median, Mode, Standard Deviation, Cp, CpK

• Plot Normal distribution curve for the data
• Write your judgement

Metallized Ceramics Division

 Pilot’s Six Sigma Performance

Width of landing
strip 1/2 Width
of landing
strip

If pilot always lands

within 1/2 the landing strip
width, we say that he has
Six-sigma capability.

Metallized Ceramics Division

 Next Session

Metallized Ceramics Division

 Topics
 Recap
 Interpreting SPC charts
 Constructing an SPC charts
 Capability of process to meet targets
 Decision making using SPC charts

Metallized Ceramics Division

 Thank You Very Much

Metallized Ceramics Division