iSixSigma

Miguel Camargo

Forum Replies Created

Forum Replies Created

Viewing 10 posts - 1 through 10 (of 10 total)
  • Author
    Posts
  • #85273

    Miguel Camargo
    Participant

    Hi Linda,Great examples!!! I am a SSBB and most of my background is from Manufacturing projects. However, eventually my company would like to start a few projects on HR, therefore I would like to read a few succees stories about applying SS to transactional environment before starting that journey. If you would be able to provide me a few real-life examples that would be great. [email protected]

    0
    #79379

    Miguel Camargo
    Participant

    Hi folks,
    As Dave already said, “Destructive test results often follow a skewed-right distribution, having a long “tail” to the right”. Actually this is the current situation.
    On tis moment, I am not focused on the root causes of that variation. Basically, I would like to validate the method we’d been using for calculating CPK prior to go to that level, most of the books have two options:
    1) Transform data for achieving normality: This is not fine for me, because I am calculating CPK (LSL only) for a destructive test. Test data follow a skewed-right distribution, having a long “tail” to the right, so that even normalizing the data the stdev is huge resulting on a poor CPK (around 1).
    2) Utilize percentiles of the distribution instead of the mean and multiples of sigma: Using this method the CPK was much better. However, it seems like there is not any accepted standard/formula for calculating CPK using this method. As you can figure out, this is critical due to the results could be significantly different, as well as would be hard to convince to my customers if we don’t have a commonly accepted reference, therefore a ISO document about this would be excellent.
    Option A:
    Cpk = Cpl = (Median – LSL) / (Median – .005 percentile)
    Option B:
    Cpk = Cpl = (Median – LSL) / (Median – .135 percentile)

    0
    #75077

    Miguel Camargo
    Participant

    Hi,The reason for calculating PPM & DPMO by separate depends on the process that you want to monitor. Some books use PPM & DPMO as the same thing, but some others don’t, furthermore just focus on the concept not the names. If there is a rework cost that would be increased due to one single rejected unit has multiple defects then it would be better to use DPMO.For some industries re-work is not appropiate, so that DPMO is useless. BR,Miguel Camargo

    0
    #75011

    Miguel Camargo
    Participant

    Hi,PPM is used for estimating the failure rate considering each unit as a defect. No mather how many atributes each part failed (ex: One unit failing for wrong color & wrong size means only one defect).PPM (Parts per million)=
    (Defects/Total units inspected)* 1,000,000 =DPMO is used considering each single defect as a reject. The baseline changed depending on how many attributes each part has(Ex.: One unit failing for wrong color & wrong size means 2 defects, each device has two chances per unit).DPMO (Defects per million opportunities)=
    Defects/(Total units inspected*Chances per unit) * 1,000,000 =

    0
    #74739

    Miguel Camargo
    Participant

    Hi,Here is my e-mail address:[email protected]

    0
    #74427

    Miguel Camargo
    Participant

    Hi Neil,Could you please send me a [email protected],

    0
    #74004

    Miguel Camargo
    Participant

    Mike,Thanks for your comments! I am working in Mexicali, Mexico(just in the border), here in my company the 6S program is just starting and the rewarding system is one of the things that we need to clarify. We want to congratulate the teamwork & at the same time avoiding cannibalizing practices. P.D.: If you can e-mail me the slide that you talked before, that would be great! In addition, If you can share any reward system would be great.
    E-mail: [email protected]

    0
    #73998

    Miguel Camargo
    Participant

    I would like to optimize the Power out & the efficiency (Pout/Pin).

    0
    #73997

    Miguel Camargo
    Participant

    Mike,We would like to give to the people involved in the six sigma projects training programs as a reward (specially to the ones that are involved in the project as a participant, but do not receive a formal training as the core team). However, using this reward model will cause that more than 5% of the company would be trained as a Green belt & perhaps more than 1% as a Black belt.What do you think about this reward model? In other hand, could you please share the slide that you prepared? Regards,

    0
    #73943

    Miguel Camargo
    Participant

    Hi all,If anyone can share any information for a SS project tending to optimize the response from an electrical circuit will be great.BR,

    0
Viewing 10 posts - 1 through 10 (of 10 total)