1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.
Dismiss Notice
You must be a registered member in order to post messages and view/download attached files in this forum.
Click here to register.

GRR for destructive test-Crimped terminal pull-out force

Discussion in 'Gage R&R and MSA - Measurement Systems Analysis' started by Plague Doctor, Jan 22, 2016.

  1. Plague Doctor

    Plague Doctor Member

    Joined:
    Jan 19, 2016
    Messages:
    13
    Likes Received:
    0
    Trophy Points:
    1
    Location:
    Ukraine
    According to customer's requirement we need to perform GRR for conductor pull-out force (wire is being pulled out of crimped terminal using the force gage).
    it is a destructive test: no chance to use the same sample for second time / split the sample and so on, in other words we can do only 1 test for each sample.
    What can we use here? Nested GRR? If yes, is there a different calculation from crossed GRR? I have only standard AIAG form for crossed GRR. Could please someone share the form for nested GRR with me?

    Or maybe we should apply another MSA study? What can you suggest?

    Thank you.
     
  2. ncwalker

    ncwalker Well-Known Member

    Joined:
    Sep 21, 2015
    Messages:
    261
    Likes Received:
    168
    Trophy Points:
    42
    Location:
    North Carolina
  3. Plague Doctor

    Plague Doctor Member

    Joined:
    Jan 19, 2016
    Messages:
    13
    Likes Received:
    0
    Trophy Points:
    1
    Location:
    Ukraine
    Thanks, but I read this article just before posting here:) I don't have Minitab so I wonder if there is any difference between calculation formulas of crossed and nested GRR or it is just difference in obtaining samples method.
    In other words can I use the same spreadsheet as for crossed GRR or do I need a new one special for nested GRR? And if I need new spreadsheet for nested GRR it would be very nice if someone send me an template:)
     
  4. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    577
    Likes Received:
    493
    Trophy Points:
    62
    Location:
    Greater Milwaukee USA
    First, read my blog on non-replicable R&R studies.

    The only option that you have is to use consecutive samples for your study. You might take 9 consecutive samples from 10 different setups/days/shifts. The 10 setups/days/shifts would reflect the parts in the R&R study while the 9 consecutive samples would reflect the 3 repeats across 3 operators. And, nested is the correct analysis.
     
    Bev D likes this.
  5. ncwalker

    ncwalker Well-Known Member

    Joined:
    Sep 21, 2015
    Messages:
    261
    Likes Received:
    168
    Trophy Points:
    42
    Location:
    North Carolina
    The concept is the same - you are checking variances between part/between operator/between trial and coming up with the conglomerate numbers. But the steps are different. Meaning, if you were to put results in Minitab, you'd get different answers running a crossed and a nested study on the SAME inputs. And I believe the nested numbers would be more conservative. I don't have ready access to it. You'd have to search around for the steps on Google.