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.

How to evaluate any significant difference using Minitab

Discussion in 'SPC - Statistical Process Control' started by essegn, Feb 5, 2016.

  1. essegn

    essegn Member

    Joined:
    Feb 5, 2016
    Messages:
    47
    Likes Received:
    5
    Trophy Points:
    7
    Hi,

    I intend to use Minitab, but before using, i would like to know the following (what i can not get from the available videos):
    My intension is to evaluate a process - how much an actual process differs from the master measurement. Every measurement has the following format:

    ------------------------------
    Measurement 1:

    x ............ ... y
    300 ............ 50
    350 ............ 55
    400 ............ 60

    ------------------------------
    Measurement 2:

    x ............ ... y
    300 ............ 52
    350 ............ 52
    400 ............ 60

    ------------------------------

    It means the the collumn X is the same all the time and i need to evaluate y range, how much differs from the master measurement, how good a repeatability is.

    My question:
    Which module (SPC, DOE ..) would be the best to observe and evaluate deviations ? The mentioned format is stored in a xls file for every measurement.

    Many thanks for the replies

    Regards

    P.
     
    Last edited: Feb 5, 2016
  2. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    578
    Likes Received:
    493
    Trophy Points:
    62
    Location:
    Greater Milwaukee USA
    You should probably start in the Quality Tools > Gage Study section.
     
  3. MCW8888

    MCW8888 Well-Known Member

    Joined:
    Aug 17, 2015
    Messages:
    642
    Likes Received:
    198
    Trophy Points:
    42
    Check the RESOURCE section of this forum. Beverly has published quite a number of Gage R&R tools.
     
  4. Bev D

    Bev D Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    606
    Likes Received:
    664
    Trophy Points:
    92
    Location:
    Maine
    Can you elaborate on the study design?
    what is the x value? is it the 'master measurement' or is it some input setting?
    is the data set in "measurement 2" a different part than the part in "Measurement 1"?
    are you making only 1 measurement of each part for every 'x value' or are you measuring 2 or 3 times at each 'x value'?
     
  5. essegn

    essegn Member

    Joined:
    Feb 5, 2016
    Messages:
    47
    Likes Received:
    5
    Trophy Points:
    7
    Please look at the attached picture - pic1.png
    All measurements are being represented by several (200 pcs) of XY coordinates. So it means that the master curve or the “W“ master (pic1.png) measurement is divided into 200 pieces and all the X,Y coordinates are written in XY format. From every following measurement exists a XY file written in xls.
    X-Values are the same in each xls file - in range from 100 to 300. Y-Values are changing and these changes i would like to check, record and evaluate.
    Every xls file looks like on the attached - pic2.png.

    In whole xls files are important the only 3 values – namely X and Y coordinates of “3 peaks“. From the picture is for example the first peak on the muster curve at X=150, Y=2, the second at X=200, Y=7,5 and the third at X=250, Y=2 - please look at the pic1.png

    But.. the first "master" peak needs to be compared with the first peak of measured curve. So it means that both coordinates (X and Y) are changeable. Not only Y coordinate, but also X coordinate. So before the evaluation, three peaks need to be found and as next to compare these peaks, whether they lie within the tolerance zone.
    I really have no idea how it could be done. Whether to find these 3 peaks in Excel with helf of MIN or MAX functions and then proceed the data to Minitab or the program itself has some appropriate feature for it.

    Many thanks for your help.
     

    Attached File(s): 1. Scan for viruses before using. 2. Report any 'bad' files by reporting this post. 3. Use at your own Risk.: