Chapter Six

Process Capability Analysis

Daniel Ab.

Bahir Dar Institute of Technology (BiT)

Faculty of Mechanical and Industrial Engineering

1
Process Capability Concept
Process capability is a measure of the relationship between the natural variation of the
process and the design specifications.

It refers to the performance of the process when it is operating in control and the
ability of a process to produce products or provide services capable of meeting the
specifications set by the customer or designer.

Process capability is measure of how “capable” the process is to meet customer

requirements; compares process limits to tolerance limits (Specification Limits).

 Process limits (The “Voice of the Process” or The “Voice of the Data”): Based
on natural (common cause) variation.
(Process variability: Natural variability in a process)
(Process capability: It is process variability relative to specification)
 Specification (Tolerance) limits (The “Voice of the Customer”): It is a Range of
acceptable values established by engineering design or customer requirements.

2
 Capability Vs. Stability (Control)

A process is capable if individual products consistently meet

specification.
A process is stable(in control)only if common variation is present in the
process. A process in statistical control does not necessarily meet the
design specifications.

Process capability compares the output of an in-control process to the

specification limits by using capability indices. The comparison is made
by forming the ratio of the spread between the process specifications
(the specification "width") to the spread of the process values, as
measured by 6 process standard deviation units (the process "width").

The natural variation of a process should be small enough to produce

products that meet the standards required.

3
It is customary to take the six-sigma spread in the distribution of the
product quality characteristic as a measure of process capability. A
capable process is one where almost all the measurements fall inside the
specification limits. This can be represented pictorially by the plot
below:

4
Process Capability
Three different situations can exist when specifications and process
variability are compared
(I) The process spread can be less than the spread of the
specification limits;
more acceptable

(II) The process spread can be equal to the spread of the

specification limits;
(III) The process spread can be greater than the spread of
the specification limits

5
Process capability is characterized with the normal distribution with inherent
variability only. In this case, 99.73% of a data are clustered within the control
limits of ±3σ, but the remaining distribution 0.27% is fallen outside of the
±3σ.

If

Let USL indicates the upper specification limit and LSL indicate the lower
specification limit. Then USL – LSL is the permitted variation.
The total expected variation 6σ is compared with USL-LSL to know whether
the process is capable of meeting the specifications. That is why it is called
process capability.

6
Case1: (USL-LSL) > 6σ must

 The process is capable if the process average is at the mid of the

specification limits. Increase or decrease in the process average may
result in rejections.

desirable

undesirable

7
Case 2: (USL-LSL) = 6σ satisfactory but unacceptable

 The process is just capable if the process average is at the mid of the
specification limits. Slight increase or decrease in the process average
may result in rejections.

8
Case3: (USL-LSL) < 6σ
 The process is not capable. It will always result in rejections.

9
Process Capability Indices
A process capability index is an aggregate measure of a process’s ability to
meet specification limits. The larger the value, the more capable a process is of
meeting requirements. This can be assessed using the following measures.
 Process capability ratio Cp

 Process capability index Cpk and Cpm

The Cp, Cpk and Cpm statistics assume that the population of data values is
normally distributed. Assuming a two-sided specification, if μ and σ are the
mean and standard deviation, respectively, of the normal data and USL, LSL,
and T are the upper and lower specification limits and the target value,
respectively, then the process capability indices are defined as follows:
doesent tell perfectly perfectly tells where
centered
USL  LSL USL     LSL 
Cp  >1
C pk  min  , >1
6  3 3 

USL  LSL T=target

C pm  2 
 i
( x   ) 2

6
  (x  T )
2 2
n
10
Cpk can also be calculated as:

11
 The estimated for Cpk can also be expressed as Cpk = Cp (1-k),
where k is a scaled distance between the midpoint of the
specification range, m, and the process mean, µ.
 Denote the midpoint of the specification range by m=
(USL+LSL)/2. The scaled distance between the process mean, µ,
and the optimum, m is:

m
k
USL  LSL) / 2
, 0  k 1
 To get an idea of the value of the Cp statistics for varying process
widths, consider the following plot.

12
 3Sigma

Plot showing Cp for varying process widths

13
The Cp value is a good indicator when a process is centered, otherwise, it is
misleading. In case, if a process is not centered, another alternative (Cpk)
value should be calculated and used to evaluate the process indicating the
position or location of the curve. Cpk is the ratio that reflects how the process
is performing in terms of a nominal, centre, or target value:
When Cp is <1, the process is incapable, while Cp>=1.33, it is related to high
process capability. The same is true for the Cpk value.
Critical values of Cpk
Sigma level Critical Value of Cpk
1 0.33
2 0.67
3 1.00
4 1.33
5 1.67
6 2.00
7 2.33
14
Interpreting the Process Capability Index:

Cpk < 1 Not Capable

Cpk > 1 Capable at 3
Cpk > 1.33 Capable at 4
Cpk > 1.67 Capable at 5
Cpk > 2 Capable at 6

15
This can be expressed numerically by the table below:

Translating capability into “rejects”

16
Example 1
The intensive care unit lab process has an average turnaround time of
26.2 minutes and a standard deviation of 1.35 minutes. The target value
for this service is 25 minutes with an upper specification limit of 30
minutes and a lower specification limit of 20 minutes. The administrator
of the lab wants to have four-sigma performance for her lab. Is the lab
process capable of this level of performance?

The first step is to check to see if the process is capable by applying the
process capability index (centeredness):

Since at 4 sigma the critical value of is 1.33, the process is not capable.
However, by adjusting the mean, the process can become capable.

17
Example 2

For a certain process the USL = 20 and the LSL = 8. The observed
process average, X = 16, and the standard deviation, s=2. From this
we obtain:

USL  LSL 20  8
Cp    1.0
6s 6(2)

This means that the process is capable as long as it is located at the

midpoint, m = (USL+LSL)/2 = 14.

However, it doesn’t, since X =16

18
 k factor is found by

m x 2
k   0.3333
(USL  LSL) / 2 6

and C pk  C p (1  k )  0.6667

We would like to have at least 1.0, so this is not a good process. If

possible, reduce the variability or/and center the process. We can also
compute: USL  x 20  16
C pu    0.6667
3s 3(2)
x  LSL 16  8
C pl    1.3333
3s 3(2)
which is the smallest of the above indices, is 0.6667
19
Estimating Process Capability in terms of actual process performance:
 Must first have an in-control process
 Estimate the percentage of product or service within
specification.
 Assume the population of X-values is approximately normally
distributed with mean and standard deviation estimated by:

x  (i 1 x) / n USL  LSL Specification Spread

n
Cp  
6( R ) Pr ocess Speed
  Rd d2
2

X  LSL CPL (CPU) > 1 implies that the process mean is more
CPL  than 3 standard deviation away from the lower (upper)
3( R )
d2 specification limit.

USL  X
CPU  It can be used for one-sided specification limits
3( R ) –Use CPU when a characteristic only has a USL
d2 –Use CPL when a characteristic only has an LSL
20
Example 3 (For one-side Specification)

You are the manager of a 500-room hotel. You have instituted a

policy that all luggage deliveries must be completed within ten
minutes or less. For seven days, you collect data on five deliveries
per day. Compute an appropriate capability index for the delivery
process.

21
Example 4
Assume that we have conducted a capability analysis using X-bar and R charts with
subgroups of size n = 5. Also assume the process is in statistical control with an
average of 0.99832 and an average range of 0.02205. A table of d2 values gives d2 =
2.326 (for n = 5). Suppose LSL = 0.9800 and USL = 1.0200

σ = R-Bar / d2 = 0.02205/2.326 = 0.00948

Cp= (1.0200 – 0.9800) / 6(.00948) = 0.703: since this is less than 1, the process is
not regarded as being capable.
ZL= (.99832 - .98000)/(.00948) = 1.9: This should be at least +3 and this value
indicates that approximately 2.9% of product will be undersized.
ZU= (1.02000 – .99832)/(.00948) = 2.3: should be at least +3 and this value
indicates that approximately 1.1% of product will be oversized.
so that , Zmin= 1.9
Cpk = Zmin/ 3 = 1.9 / 3 = 0.63: since this is only slightly less that the value of Cp the
indication is that there is little to be gained by centring and that the need is to reduce
process variation.
22
It can be generalized respect to Cp and Cpk in the relation to a process:
 Cpk can measure nominal or target values, while Cp is not.
 A capable process must have a Cp of at least 1.0
 Does not look at how well the process is centered in the specification range
 Often a target value of Cp = 1.33 is used to allow for off-center processes
 Six Sigma quality requires a Cp = 2.0
 The Cp value does not change as the process center shifts.
 Cp=Cpk if the process is centered.
 Cpk is always equal to or less than Cp.
 A Cpk value of 1.00 is acceptable even though not appreciated; with this
value, the process is capable to produce product that conforms to
specifications.
 A Cpk value less than 1.00 is incapable of producing product that does
conform to specifications.
 A Cp value less than 1.00 indicates that the process is not capable.
 A Cpk value of zero means its average value equal to one of the specification
limits.
 A negative Cpk value means its average value is outside the specifications.

23
When a process is not capable of producing within specification
limits, the following steps can be taken:
 Assignable causes can be eliminated.
 Tolerance limits may be relaxed if they are unrealistic, which
may require the approval of design engineers.
 The process dispersion (σ) may be reduced, which may
require new technology design review and etc.
 The process average can be centered or shifted to one tail.

In general Process capability can be improved through:

 Simplify
 Standardize
 Mistake-proof
 Upgrade Equipment
 Automate

24