nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

Cpk and Ppk

RNANADHA

Hi all,

Pp (New process or process not under statistical control) and

Cp (Exist process under statistical control)

I would like to ask what is process under statistical control?

And some documents said that Cp, Cpk (short term) and Pp, Ppk (long term) it is correct?

Accepted answers

ThuongLe

Here is a quick and simple explanation for Cpk, Ppk:
---Cpk: capacity of a process (maximum achievable capacity by the tool/process itself) calculated by data (collected short term, usually in 1 day/shift, etc)
---Ppk: stability of a process, included other variations (operators, season, time, etc), calculated by data collected long term, at different time frames

All comments

statman

I'll let others chime in about what the different capability indices are and how (or whether) they are useful...short term and long term (These terms are not operationally defined) depend on how the data was acquired and whether that data is representative of future conditions.

As far as control goes:

Shewhart: "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 expect to vary in the future." Shewhart, Walter A. (1931) “Economic Control of Quality of Manufactured Product”, D. Van Nostrand Co., NY, p. 6

Deming: "A stable process, one with no indication of a special cause of variation, is said to be, following Shewhart, in statistical control, or stable. It is a random process. Its behavior in the near future is predictable." Deming, W. Edwards (1986) “Out of the Crisis”, M.I.T. Center for Advanced Engineering Study, Cambridge, MA, p.321

David_Burnham

More quotes ...

The following is quoted from the book Introduction to Statistical Quality Control written by Douglas C. Montgomery.

"In 1991, the Automotive Industry Action Group (AIAG) was formed and consists of representatives of the 'big three' (Ford, General Motors, and Chrysler) and the American Society for Quality Control (now the American Society for Quality). One of their objectives was to standardize the reporting requirements from suppliers and in general of their industry.

The AIAG recommends using the process capability indices C_p and C_pk when the process is in control. When the process is not in control, the AIAG recommends using the process performance indices P_p and P_pk.

Now it is clear that when the process is normally distributed and in control, P_k is essentially C_p and P_pk is essentially C_pk because the difference between the two methods of calculating sigma is minimal.

However, please note that if the process is not in control, the indices P_p and P_pk have no meaningful interpretation ...

Kotz and Lovelace (19988) strongly recommend against the use of P_p and P_pk. indicating that these indices are actually a step backwards. They refer to the their mandated use as undiluted 'statistical terrorism' ...

The author (Montgomery) agrees completely with Kotz and Lovelace. The process performance indices Pp and Ppk are actually more than a step backward. They are a waste of engineering and management effort - they tell you nothing.

Unless a process is stable (in control). no index is going to carry useful predictive information about process capability or convey any information about future performance. Instead of imposing the use of meaningless indices, organizations should devote effort to developing and implementing an effective process characterization, control, and improvement plan. This is a much more reasonable and effective approach to process improvement."

ThuongLe

statman

The only difference is how the standard deviation is estimated:
Cpk uses R-bar/d2 (based on rational subgrouping strategies) and Ppk uses typical equation for standard deviation. Both are entirely dependent on how the data was collected and their usefulness on how representative they are of future conditions.

RNANADHA

Do agree with your response.

Now, need to know how to calculate stability of process, is there any equation for it? And acceptance criteria?

Example, I have 100 data points, now which tool I apply Cpk or PPk? As you said, in case no stable process, Cpk is correct one.