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.

Single Replicate DOE Help

Discussion in 'DOE - Design of Experiments' started by TLL86, Oct 19, 2017.

  1. TLL86

    TLL86 New Member

    Joined:
    Oct 19, 2017
    Messages:
    1
    Likes Received:
    0
    Trophy Points:
    1
    I am looking for help in improving my single replicate DOE's. In my position at work I use Computational Fluid Dynamics (CFD) to design and optimize product designs. I would like to utilize more DOE's, but one downside to analytical methods is I only get a single replicate because if I run the problem again I will get the same results. However when I run a fractional factorial analysis in Minitab on the data I end up with not enough degrees of freedom to get my P-values for the factors. I have tried added a center point but it doesn't seem to help my results either. I had this issue on an 2^6 8 run DOE and I am currently planning a 2^10 32 run with a center point but want to try and avoid the issues I have had in the past. I would greatly appreciate any ideas or recommendations anyone has.

    Thank you,
    Tony
     
  2. Miner

    Miner Moderator Staff Member

    Joined:
    Jul 30, 2015
    Messages:
    627
    Likes Received:
    543
    Trophy Points:
    92
    Location:
    Greater Milwaukee USA
    If I understand your post, it sounds like these are computer experiments that provide deterministic results with no variation. Is that correct? If this is correct, do you have an estimate of the variability in results that would be seen in the physical world versus in a simulation?