Reducing Within Part Variation during a Gage R&R Study

D

Dhandley

It was recommended that to reduce within part variation during a gage R&R study the parts should be marked to indicate where to take the readings during the study. My concern is that you would then have to indicate the same measurement location for production as well.

Your thoughts,
 

WCHorn

Rubber, Too Glamorous?
Trusted Information Resource
Re: Within Part variation

I always mark parts to be measured for a GR&R to eliminate within part variation from the GR&R calculations. The goal is to assess the gage; eliminating other variables that inflate the study results is important. Reducing within-part variation in production or assessing part conformance is an issue separate from gage assessment.:2cents:
 

Jim Wynne

Leader
Admin
Re: Within Part variation

It was recommended that to reduce within part variation during a gage R&R study the parts should be marked to indicate where to take the readings during the study. My concern is that you would then have to indicate the same measurement location for production as well.

Your thoughts,

I always mark parts to be measured for a GR&R to eliminate within part variation from the GR&R calculations. The goal is to assess the gage; eliminating other variables that inflate the study results is important. Reducing within-part variation in production or assessing part conformance is an issue separate from gage assessment.:2cents:


The goal is to assess the measurement system, not just the gage. The part and the operator are both part of the system. The measurements taken during the gage study should replicate what's being done, or what is intended to be done, in production. Masking within-part variation during the study defeats part of the purpose of doing the study. If the parts are to be measured at a certain position, or as held in a jig or fixture in production, that's the way it should be done for the MSA.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
Re: Within Part variation

The goal is to assess the measurement system, not just the gage. The part and the operator are both part of the system. The measurements taken during the gage study should replicate what's being done, or what is intended to be done, in production. Masking within-part variation during the study defeats part of the purpose of doing the study. If the parts are to be measured at a certain position, or as held in a jig or fixture in production, that's the way it should be done for the MSA.

It is true you want to see the results of the gage system - the interaction of the operator, gage, and part geometry. THat is why we use a part and not a gage pin or gage block. However, variation within-in the part should be analyzed in another venue - process capability, control, etc. Adding every possible error to the gage R&R will never allow you to do what the test intended to do - answer the question if the gage the correct gage for the measurement. I recommend measuring in the same spot to answer that question. It includes the factors of the total variance equation that are related to the gage, and not the process.

However, if there is significant within-part variation, then when you measure the part in production you can not measure "one spot" - it will not represent the geometry of the feature being analyzed. You need to measure about the feature and report the high and low value. The only time you can measure one point if it is know that the within- part variation is statistically insignificant (generally in relation to the tolerance, or control limits, if charting is employed.)

Gage R&R is to determine gage system error. Using a good gage (passed gage R&R) and not determining if the feature has within-part variation as a process measurement is using a perfectly good gage the wrong way. That is measurement error. Different thing.
 

Jim Wynne

Leader
Admin
Re: Within Part variation

It is true you want to see the results of the gage system - the interaction of the operator, gage, and part geometry. THat is why we use a part and not a gage pin or gage block. However, variation within-in the part should be analyzed in another venue - process capability, control, etc. Adding every possible error to the gage R&R will never allow you to do what the test intended to do - answer the question if the gage the correct gage for the measurement. I recommend measuring in the same spot to answer that question. It includes the factors of the total variance equation that are related to the gage, and not the process.

However, if there is significant within-part variation, then when you measure the part in production you can not measure "one spot" - it will not represent the geometry of the feature being analyzed. You need to measure about the feature and report the high and low value. The only time you can measure one point if it is know that the within- part variation is statistically insignificant (generally in relation to the tolerance, or control limits, if charting is employed.)

Gage R&R is to determine gage system error. Using a good gage (passed gage R&R) and not determining if the feature has within-part variation as a process measurement is using a perfectly good gage the wrong way. That is measurement error. Different thing.

In most cases we'll already know what device is appropriate for the measurement in question. In cases where which device to use is in question, it's a different story. For example, I might have to measure the depth of a blind hole and want to know whether to use a caliper depth rod or a depth mic. The way a gage study is conducted often depends on what we're trying to learn. I still say that in most cases, measuring a part in a marked position is not a good idea unless the part is going to measured that way in production, but it might be fine if it doesn't matter in terms of what you expect the analysis to tell you.
 

WCHorn

Rubber, Too Glamorous?
Trusted Information Resource
Re: Within Part variation

Masking within-part variation during the study defeats part of the purpose of doing the study.

From MSA Fourth Edition Chapter III, Section A, "The procedures are appropriate to use when: ? The effect of the variability within each part is negligible ?"
and from Chapter IV, Section D, "Recognition and analysis of these additional sources of variation (types of within-part variation which may be encountered) during a measurement system study is paramount to understanding the actual measurement system variation."

I understand your concern, Jim, but given the quotes from the MSA Reference Manual, I think it is clear that within-part variation must be known and accounted for.
 

Jim Wynne

Leader
Admin
Re: Within Part variation

I understand your concern, Jim, but given the quotes from the MSA Reference Manual, I think it is clear that within-part variation must be known and accounted for.
If it is known and accounted for, what is the point in marking the parts if the parts aren't going to measured in the same spot in production?
 
H

Hodgepodge

I understand your concern, Jim, but given the quotes from the MSA Reference Manual, I think it is clear that within-part variation must be known and accounted for.
The real answer is, ?It depends?. Within-part variation may not have an impact on or have anything to do with a gage?s repeatability or reproducibility. Yes, in part variation should be known and accounted for. Accounting for it would mean deciding when to add the variant data to the study.

My concern is that you would then have to indicate the same measurement location for production as well.

Your thoughts,

Restricting measurement options at the time of production would not be a good idea. Use the data that is available to you to make decisions.
 

Bev D

Heretical Statistician
Leader
Super Moderator
Re: Within Part variation

If it is known and accounted for, what is the point in marking the parts if the parts aren't going to measured in the same spot in production?

I think the point is to mark the parts during the MSA to understand the within part variation. Then if the within part variation is large enough to matter you would adjust your measurement process to measure in different locations on the part to capture the true dimensions of the part.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
Re: Within Part variation

Actually, there is no way of knowing if the device is appropriate until you do a gage r&r with:

-The appropriate variation in operator experience the gage will experience
-The appropriate historical variation in the dimension the gage will experience
-The appropriate variation in handling the operator and gage will experience (fixtured vs in hand, cantilevered loads, etc.)


and from that determine if the system variation for those inputs result in an output with statistically insignificant variation to either the tolerance or total supplied variation - depending on its use. My recommendation is always mark the parts - and one can choose whichever approach they can best justify (hopefully to correctly answer the question they are trying to answer).

The variation about the part is process - not gage - variation. That is addressed in process capability and process control not gage capability.

Now, the funny thing about a gage R&R as a tool is that it is not a single tool, but a toolbox. If you chose to determine the overall process variation, including the gage and part variation, you can do that with the tool. It simply will not give you any idea what the gage participation is - it will be buried in that mess. It also answers a totally different question. You can also use one operator and three gages to determine if the variation between three gages is significant - again, answering a different question than the common usage of the tool. Just have to use the tool a specific way to answer a specifc question.
 
Top Bottom