Alternatives to GR&R (Gage R&R) - Only 4 sample parts and one operator

[Kalpol92]

I am interested to hear if anyone else has come across this situation.

I have a number of measurement methods and i would like to understand the amount of error being generated from the method. GR&R you say?

However i only have 4 sample parts and one operator. This is non destructive so i can carry out replicates.

A method i have been thinking about using is calculating the COV or coefficient of variation and calculating this as a Ratio to my tolerance.

However would this give me a good idea of my measurement error???

I think i'm on the right lines....

Help would be appreciated

 

[trainerbob]

Re: Alternatives to GR&R (Gage R&R)

I find it hard to believe that your organization has only produced four parts and will never produce any more. What do/did you make?

 

[Kalpol92]

Re: Alternatives to GR&R (Gage R&R)

The reason we have a small number of parts is because i am in an R&D facility not production. However when we complete product design validation/verification any studies/investigation reports that the results are used in we have to have evidence that the level of precision we have within the method is acceptable.

Also the reason for one operator is i need a simple method as we have to develop methods quickly prove they are precise for the job in hand and report on the results of the testing. In most instances never do the testing again!!!

 

[Stijloor]

Re: Alternatives to GR&R (Gage R&R)

The reason we have a small number of parts is because i am in an R&D facility not production. However when we complete product design validation/verification any studies/investigation reports that the results are used in we have to have evidence that the level of precision we have within the method is acceptable.

Also the reason for one operator is i need a simple method as we have to develop methods quickly prove they are precise for the job in hand and report on the results of the testing. In most instances never do the testing again!!!

Studies on such a small sample will not be accepted; at least not in the industries (automotive) that I work with. Such studies must be conducted with larger quantities of parts taken from a manufacturing process that works under normal operating conditions.

Stijloor.

 

[Kalpol92]

Re: Alternatives to GR&R (Gage R&R)

Yes i agree it is a tricky one. I am in the Medical Device industry and for production parts its very easy...... create parts across my tolerance range and a few just above and below my spec and carry out a GR&R.

However this is not a production environment therefore parts are not readily available. But i still have to have an idea of the precision within my method.

 

[Stijloor]

Re: Alternatives to GR&R (Gage R&R)

Yes i agree it is a tricky one. I am in the Medical Device industry and for production parts its very easy...... create parts across my tolerance range and a few just above and below my spec and carry out a GR&R.

However this is not a production environment therefore parts are not readily available. But i still have to have an idea of the precision within my method.

Great question....

We have a few MSA (GR&R) experts here at The Cove Forums. Because it is a Thanksgiving Holiday weekend, they may not visit today. But I am sure that you will get a response.

Stijloor.

 

[Kalpol92]

Re: Alternatives to GR&R (Gage R&R)

I'll check back later.

I'm sure there is a way think COV gives me some idea of repeatability but i would like to be able to put it into context with our proposed specs ie a PT ratio and i'm not sure if doing this makes sense.

i wish i had a long weekend !!!!

 

[Miner]

Re: Alternatives to GR&R (Gage R&R)

I would not use COV for several reasons. First, it is not well understood by people that are somewhat familiar with MSA. Second, it is only appropriate for ratio scale measurements where zero means total absence of something such as temperature measured in Kelvin, weight or length.

I recommend performing a stability study and using the estimate of repeatability provided by that study. See my blog on Stability studies. You can use the Stability tab in the Excel file in this blog to calculate the estimated Repeatability.

 

[brahmaiah]

Re: Alternatives to GR&R (Gage R&R)

The reason we have a small number of parts is because i am in an R&D facility not production. However when we complete product design validation/verification any studies/investigation reports that the results are used in we have to have evidence that the level of precision we have within the method is acceptable.

Also the reason for one operator is i need a simple method as we have to develop methods quickly prove they are precise for the job in hand and report on the results of the testing. In most instances never do the testing again!!!

The GR&R method is basically designed to meet the large quantity production.If you cannot follow the method prescribed in the MSA manual you have to judge the suitability of a gauge/instrument by experience and on the basis of its design and least the count.
Adopting GRR for 4 parts and 1 operator is an exercise in futility.
V.J.Brahmaiah

 

[Bev D]

Re: Alternatives to GR&R (Gage R&R)

Actually there are ways to apply MSA methodology to both destruct testing and small sample sizes that can provide information that is usefull - especially given the situtation that the OP describes: early in the design process.


To the OP: the coefficient of variation can be a useful alternative to the standard R&R approach. However, you do NOT have sufficient sample size to use it at this time. There is also a very special experimental approach to using the CV.

Can you tell us what the product is and the nature of the test? this will enable us to provide more useful help - instead of simply telling you what can't be done...