Continuous Improvement - Six Sigma Process Capability (Part 5)

Written by:  Jim Gilbert, CMTC Sr. Consultant

The prior two posts stated that if a process is Capable and in Control, you will, by definition, get the outcome that the process was designed to produce.  We discussed how to measure Process Control with SPC and the importance of keeping a process in control.

According to NIST (National Institute of Standards and Technology)[1]:

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 Specification Limits relate to the process’ tolerances.  For instance, a pin could be dimensioned to be 1 inch (1”) in diameter.  But, how do we accommodate the inherent variation in the process to produce the pin?  We do that by providing tolerances.  It is determined that a pin of 1”, plus or minus three thousands of an inch (.003 inch) in diameter is good enough.  All pins within that range of diameters will work successfully for its application.

Again according to NIST, a process capability index uses both the process variability and the process specifications to determine whether the process is "capable.”

For our purposes in these blogs all we need to know is that we know how to determine the ability of a process to produce good parts.  This is the same as answering the following:

• What percentage of the output will meet the customer’s specifications?
• How many pins will be larger than the 1 inch plus the three thousands in diameter (1.003 inch)
• How many pins will be smaller than the 1 inch less the three thousands in diameter (.997 inch)?

You may remember that the three Standard Deviation measure of variation signifies a quality level of 99.7% of good work produced.  This is the equivalent of a Process Capability measure of one.  The literature is pretty much in agreement that we need a Process Capability (Cp and Cpk) measure of at least 1.33.  This is equivalent to a variation of four Standard Deviations.  Four Standard Deviations will produce a quality level of 99.9% (as compared to the 99.7% quality level of three Standard Deviations).  This allows for what is known as shift and drift where the normal variation of the process causes some defects that would not occur if there we no variation.

In summary, we know how to measure Process Control and Process Capability and monitor them.  As long as an in-control process is capable of producing the desired outcome (Process Capability Cpk of 1.33) then it must perform properly as long as it is in control.

The next question is how do we get a process to be in control and capable?  That will be what the next section of blogs will cover.

For now, let’s review:

• Blog Post 1:  Introduction to Six Sigma
• Blog Post 2:  Presentation on two projects and their outcomes
• Blog Post 3:  Define, Measure, Analyze, Improve and Control (DMAIC)
• Blog Post 4:  Process and Statistical Process Control
• Blog Post 5:  Process Capability