QSB+ : capability of measurement equipment

[orlafitzgerald]

I do not have my MSA manual immediately available, so I have to go by your description above. The 10-30% range should also state something to the effect that the device may be acceptable if the characteristic measured is not critical/significant and better gaging is not economical or feasible. 27.9 would meet this criteria depending on the wording of the example. Again, these criteria do not apply to percent contribution.

Would you know if the origins of the criteria are stated anywhere or do you know of any statistical basis for them ?

 

[Miner]

I checked with my co-worker. He worked at General Motors in the 1970s. He was using the average range method in 1975 and recalled that GM had empirically derived the criteria using simulations. GM later developed the ANOVA approach as well. This matches my memories of having been exposed to the method by GM in the 1980s.

There is absolutely no statistical basis for the criteria. In fact, the entire notion of using ratios of standard deviations is mathematical nonsense because standard deviations are not additive. Dr. Donald Wheeler has many excellent articles on this topic in Quality Digest and on his own SPC Press website.

Having said that, the methodology does work despite its mathematical shortcomings. It was developed during a time when most people did not have access to computers, so it had to be simple and tradeoffs were made to make it simple. Today, we have better alternatives (see Wheeler's An Honest Gauge R&R Study), but AIAG has firmly entrenched the original method into most industries.

 

[Bev D]

More historical trivia: I have two papers written in 1959 that discuss the method that most people use. The two articles do not address the ANOVA method although the later article does discuss how to properly calculate the contribution of repeatability to the overall variation.
The first paper was published in 1959: Let’s take the guesswork out of inspection by Jack Gantt of GE Aircraft Engines (Evendale OH plant), published in the March 9th edition of “American Machinist”. The second paper was presented at the 1962 ASQC Convention by Robert Traver of GE Power Transformers (Pittsfield MA plant): The Rubber Ruler. It references Gantt’s article. These two papers only mention the 10% requirement (simple ratio of repeatability to the tolerance). They both include forms that will look familiar to many although they only require 2 repeat measurements of each part.

interestingly, Jack Youden’s paper on measurement error including the now infamous Youden plot was published in May of 1959. Seems like measurement error was quite the hot topic back then!

 

[Johnnymo62]

See table II-D 1 on page 78.

 

[Bev D]

For those of us without access to that document could you let us know what it says?

 

[Miner]

It is the criteria we were discussing. The following is the exact wording:

• Under 10% Generally considered to be an acceptable measurement system
  • Recommended, especially useful when trying to sort or classify parts or when tightened process control is required
• 10% - 30% May be acceptable for some applications
  • Decision should be based upon, for example, importance of application of measurement, cost of measurement device, cost of rework or repair
  • Should be approved by the customer
• Over 30% Considered to be unacceptable
  • Every effort should be made to improve the measurement system
  • This condition may be addressed by the use of an appropriate measurement strategy; for example, using the average result of several readings of the same part characteristic in order to reduce the final measurement variation