iSixSigma

Need Help in My 6 Sigma Project (Automotive)

Six Sigma – iSixSigma Forums Old Forums General Need Help in My 6 Sigma Project (Automotive)

Viewing 6 posts - 1 through 6 (of 6 total)
  • Author
    Posts
  • #50119

    Waseem
    Member

    Hi all,
    Let me briefly describe my project outlines here:
    1- We do destructive testing (Push out test) to validate the weld integrity and weld strength.
    2- For these tests we use good parts from the welding process
    3- Project is to eliminate using good parts for destructive testing and start using scrap from stamping process for push out tests.
    4- From stamping process we get scrap in shape of little coupons and weld fasteners on the coupon.
    5- Then we do the push out test on coupons.
    6- The objective of destructive testing is to validate the welding process and that we can do by using coupons instead of good parts.
    7- I have got 2 sets of data. a) Coupon testing results b) Part testing results
    8- I applied ANOVA in order to check the variances and it shows significant variance between 2 sets of data.
    Now the question is, what tool from Minitab I can use to show that coupon testing results are better than part testing results. Both results are within the specs.
    Appreciate your comments

    0
    #172128

    Dixit
    Member

    Hi,
    Please let us know is Coupons and Good parts is having same specification or not. If Coupons are different from Good parts we cannot test Weld strength of Good parts by testing Coupons. ANOVA is applied on the product which is produced at different condition to see is there any difference in the specification based on certain factors like Men,Machine and time to identify the root cause and take corrective action on the factor which is effecting on the specification.
    Regards,
    Viijay

    0
    #172131

    Wahmed
    Member

    Thanks for your reply Viijay,
    Well, coupon & good parts have same testing specifications (UCL & LCL)and are same materials. Actually the only difference is the CP & CPk. Coupons have better CP & CPk values.
    Looking forward for your inputs.
    Thanks once again, Ws

    0
    #172135

    Glen_A
    Participant

    I think you have proved that the ‘coupons’ are not a valid substitute for testing actual parts, because they give different results. 
    You think the process for producing them is the same but some difference exists, which you need to identify. 

    0
    #172136

    Waseem
    Member

    Thanks Glen for your reply.
    I said, both coupons and actual parts have the same specs. Testing results are within their specifications for both. But when I checked the process capability of coupon testing & actual part testing, it shows the following results:
    Coupon Testing :     Cp 2.01, Cpk 1.13
    Actual Part :             Cp 1.09, Cpk 0.71

    0
    #172159

    Glen_A
    Participant

    It was a smart move to look at the Cpk values – not many people would do that.
    The coupons do not show the same variation as the actual parts.  You need to find out why – talk to the people who know the process.
    When you find out why, you may be able to improve the Cpk of the actual parts.
    Good Luck

    0
Viewing 6 posts - 1 through 6 (of 6 total)

The forum ‘General’ is closed to new topics and replies.