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.

Precision of Measurement System

Discussion in 'Gage R&R and MSA - Measurement Systems Analysis' started by YASA1, Apr 11, 2019.

Tags:
  1. YASA1

    YASA1 New Member

    Joined:
    Apr 11, 2019
    Messages:
    2
    Likes Received:
    0
    Trophy Points:
    1
    Hello everyone,

    My question relates to the task I've been given - determining the precision of a measurement system.

    At my work place we've recently installed a new bespoke end of line test machine.

    The machine tests the performance of our products (electric motors) and spits out a series of results based on our test parameters. For now, let's assume it just gives one result for each motor.

    What I've done is run a gauge R&R study and have all the usual results for repeatability and reproducibility etc, but what next?
    Is there an output from this study that I can use specifically for determining the gauge's precision?

    Our customer wants to know to how many decimal places we can meaningfully quote our results.

    We're limited by the resolution of the machine to 4 d.p. so I know that will be a maximum, but I don't know whether we're actually precisely measuring to that level.

    Forgive me if this is a question with an obvious answer, but I don't have years of MSA experience.

    Any help appreciated!

    Thanks
     
    YASA1, Apr 11, 2019
    #1
  2. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    577
    Likes Received:
    493
    Trophy Points:
    62
    Location:
    Greater Milwaukee USA
    There are two possibilities. The first would be to provide the total R&R in terms of standard deviations from the standard AIAG R&R report. The second, which I recommend, would be to use the Donald Wheeler Honest Gage Study approach and provide the Probable Measurement Error. The template may be found here. If your customer is hooked on the AIAG format, this may be a difficult sell, but would be worth the effort.
     
    Miner, Apr 11, 2019
    #2
    Andy Nichols likes this.
  3. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    577
    Likes Received:
    493
    Trophy Points:
    62
    Location:
    Greater Milwaukee USA
    I think you would be most interested in the Effective Measurement Increment below. This is the template for Wheeler's Honest Gage Study approach.

    Probable error.png
     
    Miner, Apr 11, 2019
    #3
    Andy Nichols likes this.
  4. YASA1

    YASA1 New Member

    Joined:
    Apr 11, 2019
    Messages:
    2
    Likes Received:
    0
    Trophy Points:
    1
    Yes this is very interesting thank you. I've read through most of the column and will re-read again later.

    So as I understand it, the options are:
    Following AIAG - quote the R&R in terms of standard deviation
    Following Wheeler - quote 0.675*R&R standard deviation

    I notice Wheeler uses 0.675*VarComp rather than 0.675*StDev, is there a reason?

    A final point: How can I put into practice the effective measurement increment you've highlighted, if say my measurement is 100.123456
    I can't quite get my head around how to use that resolution range in practice

    Thanks again for the help, I think I'm much closer to understanding than before.
     
    YASA1, Apr 11, 2019
    #4
  5. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    577
    Likes Received:
    493
    Trophy Points:
    62
    Location:
    Greater Milwaukee USA
    Wheeler does use 0.675*StDev. My template used 0.675*SQRT(VarComp). VarComp is the variance, so taking the SQRT converts it to a StDev.

    The template is set up to accept data from the standard 3 x 3 x 10 R&R study. If you populate the template and attach it, I can help you interpret The effective measurement increment.
     
    Miner, Apr 12, 2019
    #5