Process capability
Specification & Control ( tolerance) limits
:- they are often used interchangeably
Defined as :
Limits that defines conformance boundaries for
an individual unit of a manufacturing or service
operations.| (tolerance ) limit
emesis ey
They are more appropriate for generally preferred in evaluating the
categorizing materials ,products or manufacturing or service requirements
services in terms of stated requirements
They are influenced by need of the They are determined by condition of
customer process and its natural variability
Specifications includes all requirements Tolerances pertains to physical
requirements
e.g. one specification for building crane is a hoist load of S000 +300kg. to satisfy this
criterion the diameter of steel cable has to be 4 + 0.2 em
When cable is manufactured then capability of process decides the tolerances like
4.01 +0.21cm
General tolerance are of subset of specificationProcess capability
Presents
1) Performance of a process ina state of statistical
control
2) It is measure of uniformity of a quality characteristics
of interests
3) acommon measure of process capability is given by
06, which is also called the process spread
Benefits of process capability analysis:
1) Uniformity of output
2) Maintained or improved quality
3) Product or process design facilitated
4) Assistance in vendor selection and control
5) Reduction in total cost.1)
2)
3)
Process capability indices
They used to determine whether the given natural
variation is in capable of meeting standard
specification or not
It is also measure of manufacturability of the product
with the given process
They can be used to compare product /process
matches and identify poorest which can be later
targeted for improvement.Cp Index
A common measure for describing the potential
of a process to meet specifications.
It relates the allowable spread of the
specifications limits( difference between USL &
LSL ) to the measure of actual or natural
variation of process, represented by six sigma
USL — LSL
Process capability index = a6Processes are evaluated by using Cp as given
Cp <0.67
0.67 1
a | u
Measure of process potential Measure of actual process
performance
Does not change as process mean (Changes as process mean changes
change
Cp2 idesirable Cpk 2 1 desirable
Cp <1 Process is not capable Cpk <1 performance of process is
poorPok
Ppk is an index of process performance which tells how well a system is
meeting specifications . ... If Ppk is 1.0, the system is producing 99.73% of its
output within specifications. The larger the Ppk, the less the variation
between process output and specifications.
So the key takeaway is that Cpk is the potential of a process to meet a
specification (short term) while Ppk is how the process actually did (long
term). Another way to look at the difference is that Cpk is used for a subgroup
of data, while Ppk is used for the whole process.Process Mean close to USL
If your Process Mean (central tendency) is closer to the USL,
use: Ppk = [ USL—x(bar) ] / 3s, where x(bar) is the Process Mean.
Another way to look at the difference is that Cpk is used for a
subgroup of data, while Ppk is used for the whole process.
Cpk is typically used while processing in the ideal conditions to identify
if the process is capable of meeting the specifications.
If we look at the formulas for Cpk and Ppk for normal (distribution)
process capability, we can see they are nearly identical: The
only difference lies in the denominator for the Upper and Lower
statistics:
Cpk is calculated using the WITHIN standard deviation,
while Ppk uses the OVERALL standard deviationCpk is sometimes referred to as the short-term capability.
With Ppk, the calculated standard deviation is used. This
includes all the data at one time in the calculation.
Ppk is sometimes called the long-term capability.