7/4/2021

Process Capability Index and

Six Sigma

Dr. Abdul Shakoor

What is a Process Capability Study?

 Process capability study is a scientific

and a systematic procedure that uses
control charts to detect and eliminate
the unnatural causes of variation until a
state of statistical control is reached.
When the study is completed, you will
identify the natural variability of the
process.
2

1
 7/4/2021

Process Capability
 Process capability represents the performance
of a process in a state of statistical control.
 It measures how well the process is currently
behaving w.r.t the output or customer
specifications.
 Process capability is also the ability of the
combination of people, machine, methods,
material, and measurements to produce a
product that will consistently meet the design
requirements or customer expectation.
3

Why Process Capability is So

Important
 Because it allows one how well a process can
produce an acceptable product. As a result a
manager or engineer can prioritize needed process
improvements and identify those processes that don’t
need process improvements.
 If the process is capable then conventional
acceptance methods can be eliminated or reduced.
This not only yield great cost saving in eliminating
non value added inspection but it will also eliminate
rework, reject, and increased customer inspection.
 When the process is not capable then 100 %
inspection need to be carried out.

2
 7/4/2021

Procedure for Process

Capability
 Procedure (s – method)
1. Take subgroup size 4 for 25 subgroups
2. Calculate sample s.d., s, for each subgroup
3. Calculate avg. sample s.d. s = s/g
4. Calculate est. population s.d. 0 = s/C4
C4 is from table B and is 0.9213 for n = 4
1. Calculate Process Capability = 6 0
 R - method
1. Same as 1. above
2. Calculate R for each subgroup
3. Calculate avg. Range, = R/g
4. Calculate 0 = R/d2
d2 is from table B and is 2.059 for n = 4
1. Calculate 6 0

Process Capability Indices

 Cp is the ratio of the tolerance width to
the spread of the process
 Cp= Tolerance Width/Process spread

 Cp = USL-LSL/ 6б

Where Cp is Capability index

USL-LSL = Tolerance
6б = Process Capability
6

3
 7/4/2021

Process Capability (6) And

Tolerance
Cp - Capability Index
T = USL-LSL
Cp = 1  Case II 6 = T
Cp > 1  Case I 6 < T
Cp < 1  Case III 6 > T

Few conclusions
a) Process is highly
capable (Cp>2)
b) Process is capable
(Cp=1 to 2)
c) Process is not
capable (Cp< 1)

Cpk?
 Cpk is the ratio of the
measured distance LSL USL

between the overall

mean of the process
and the closest
specification limits to
the half of the total
process spread.
 Cpk considers the avg
centering of the process
where as Cp doesn't.
Min (USL - avg, avg - LSL)
Cpk =
8
3ST

4
 7/4/2021

Comments On Cp, Cpk

 Cp does not change when process center (avg.) changes
 Cp = Cpk when process is centered
 Cpk  Cp always this situation
 Cpk = 1.00 de facto standard. It indicates that the process
is producing products that confirms to the specifications.
 Cpk < 1.00  process producing rejects
 Cp < 1.00  process not capable
 Cpk = 0  process center is at one of spec. limit (U or L)
 Cpk < 0  i.e. – ve value, avg outside of limits

10

5
 7/4/2021

Within and Overall Capability

Within (Short Overall (Long
Term) Term)
Sample size 25 Subgroups ≥ 100 subgroups

No of lots Single lot Several lots

Period of time Hours or days Weeks or months

No of operators Single operator Different operator

Process Potential Cp Pp

Process Cpk Ppk

Performance

11

Six Sigma Defined (Low-Level)

A Process in which the Specification

Limits are Six Standard Deviations above
and below the Process Mean
Two Approaches:
•Move the Specification Limits Farther Apart
•Reduce the Standard Deviation

12

6
 7/4/2021

Approach #1

Ask the Customer to Move the

Specification Limits Farther Apart.

13

2-sigma Process Spec Limits

Cp = 0.667
Cpk = 0.667
45,500 ppm

14

7
 7/4/2021

3-sigma Process Spec Limits

Cp = 1.0
Cpk = 1.0
2,700 ppm

15

4-sigma Process Spec Limits

Cp = 1.333
Cpk = 1.333
63 ppm

16

8
 7/4/2021

5-sigma Process Spec Limits

Cp = 1.667
Cpk = 1.667
0.57 ppm

17

6-sigma Process Spec Limits

Cp = 2.0
Cpk = 2.0
0.002 ppm

18

9
 7/4/2021

Approach #2

Reduce the Standard Deviation.

19

2-sigma Process Spec Limits

Cp = 0.667
Cpk = 0.667
45,500 ppm

20

10
 7/4/2021

3-sigma Process Spec Limits

Cp = 1.0
Cpk = 1.0
2,700 ppm

21

4-sigma Process Spec Limits

Cp = 1.333
Cpk = 1.333
63 ppm

22

11
 7/4/2021

5-sigma Process Spec Limits

Cp = 1.667
Cpk = 1.667
0.57 ppm

23

6-sigma Process Spec Limits

Cp = 2.0
Cpk = 2.0
0.002 ppm

24

12
 7/4/2021

Process Drift
What Happens when the Process
Mean Is Not Centered between
the Specification Limits?

25

3-sigma Process Spec Limits

(centered)
Cp = 1.0
Cpk = 1.0
2,700 ppm

26

13
 7/4/2021

3-sigma Process Spec Limits

(shifted 0.5 std. dev.)
Cp = 1.0
Cpk = 0.833
ppm = 6,442
(about 2.72-sigma)

27

3-sigma Process Spec Limits

(shifted 1.0 std. dev.)
Cp = 1.0
Cpk = 0.667
ppm = 22,782
(about 2.28-sigma)

28

14
 7/4/2021

3-sigma Process Spec Limits

(shifted 1.5 std. dev.)
Cp = 1.0
Cpk = 0.5
ppm = 66,811
(about 1.83-sigma)

29

Six Sigma: Many Meanings

 A Symbol
 A Measure
 A Benchmark or Goal
 A Philosophy
 A Method

30

15
 7/4/2021

Six Sigma: A Symbol

  is a Statistical Symbol for

Standard Deviation
 Standard Deviation is a Measure
of Dispersion, Volatility, or
Variability

31

Six Sigma: A Measure

 The ―Sigma Level‖ of a process
can be used to express its
capability — how well it performs
with respect to customer
requirements.
 Percent Defects, Cp, Cpk, PPM

32

16
 7/4/2021

Six Sigma: A Benchmark or Goal

 The specific value of 6 Sigma (as
opposed to 5 or 4 Sigma) is a
benchmark for process excellence.
 Adopted by leading organizations as a
goal for process capability.

33

Six Sigma: A Philosophy

 A vision of process performance
 Tantamount to ―zero defects‖
 A ―Management Mantra‖

34

17
 7/4/2021

Six Sigma: A Method

 Really a Collection of Methods:

 Product/Service Design
 Quality Control
 Quality Improvement
 Strategic Planning

35

Where Does ―3.4 PPM‖ Come From?

 Six Sigma is commonly defined to be

equivalent to 3.4 defective parts per
million.
 Juran says that a Six Sigma process will
produce only 0.002 defective parts per
million.
 What gives?

36

18
 7/4/2021

37

Normal Curve Probabilities

±1 Sigma 68.3% of Data
±2 Sigmas 95.4%
±3 Sigmas 99.73%
±4 Sigmas 99.994%
±5 Sigmas 99.99994%
±6 Sigmas 99.9999998%
38

19
 7/4/2021

68.3% of Data Fall within 1 Standard Deviation of the Mean

39

95.4% of Data Fall within 2 Standard Deviations of the Mean

40

20
 7/4/2021

99.73% of Data Fall within 3 Standard Deviations of the Mean

41

99.9999998% of Data Fall within 6 Standard Deviations of the Mean

42

21
 7/4/2021

Process Centered
between Spec Limits

Sigma Level Cp Cpk PPM

1 0.333 0.333 317,310
2 0.667 0.667 45,500
3 1.000 1.000 2,700
4 1.333 1.333 63.4
5 1.667 1.667 0.57
6 2.000 2.000 0.002

43

The End

Questions

44

22