iSixSigma

Sergey

Activity

  • thiyagu and Profile picture of SergeySergey are now friends 2 years, 11 months ago

  • Nice! Are there any examples or case studies relevant?

  • Hi @aufafadhli
    It might be you have an excessive reinsurance for seal strength testing. We’ve done some DOEs for that parameter to understand the whole system, based on my experience it should save time and effort. In case you have historical data, you may easily understand the possible variability in a system, take few samples from current…[Read more]

  • Simple and clear explanation how TOC and Six Sigma work, really like it!

  • Hi @Ahiru-san

    The hard but powerful way to address some problems you mentioned might be proper process description (e.g. with SIPOC) and using FMEA for it. Team effort to assess the risks and discussion of all aspects (potential failures, root cause analysis and all detection and prevention controls) might be better than any training. Having FMEA…[Read more]

  • Nice visualization, thanks!

  • @natandreis

    Maybe I’m not so pessimistic and it is not always playing with fire. It seems you found an opportunity for optimization and looking for discussion around pros and contras. I believe these conversations should be fact based. For me Ppk is the most honest parameter. The threshold depends on industry and business specific, that’s why not…[Read more]

  • It seems any software can help generate three sets of data according to your assumptions. Then you need to process it to get exact model. That’s why it is easier to do in software where you are running DOE analysis. 4 years ago

  • Nice customer’s question!

    Simple estimations show hundreds millions of tests to be conducted to demonstrate such reliability :) Confirming these numbers you will definitely lie to clients :))) 4 years, 1 month ago

  • Both systems might be used for the same processes even in the same company. It depends on regions, criteria and supporting service availability. I’m not familiar with WinSPC (I suppose for food industry it is good as well), with Infinity you get fully functional and customizable SPC solutions. 4 years, 1 month ago

  • Hi there,

    It seems like not a rule :) Have you really got all the same 200 results? I’ve got another result from first attempt.

    The explanation is following.

    When process is capable, the Observed performance (PPM out of spec) is 0,00. While expected Overall performance will be always higher than zero (due to infinite Gaussian curve).

    When…[Read more]

  • Good discussion!
    DOE for historical data sounds like a non-sense. DOE itself is about proactive controlling and setting factors to get certain output and then to analyze where there is a relationship. For historical data we just take what we have. Seems naive to organize it right order and assume all the measurements were obtained under controlled…[Read more]

  • Sample size always depends on three parameters: process behavior, granularity and risks. First is described by standard deviation or current level of defects. Granularity is how you want to be precise in measuring your characteristic. Risks we manage through alpha and beta. Taking into account your requirements (looks like “I know nothing about my…[Read more]

  • I see some ideas about experiment. But what about design of experiments in here? Are there any hypothesis?

    This is a common mistake to jump from no data to DOE. In between there are a lot of work to do… 4 years, 5 months ago

  • I have no tools by hand to confirm whether it is Poisson or not (based on data seems like it is).

    What kind of risks do you have if you choose wrong distribution? 4 years, 7 months ago

  • @Brendans14a

    Some comments regarding your guidance list
    In 3) it is important to note that CCD can go by augmenting 2k, but BBD will require completely new trials. For overall scheme in that case BBD seems not practical.

    In 4) number one you mention only R-Sqr. The target for it depends on industry, may vary from 50 to 100%. The more important…[Read more]

  • Building on what already said..
    If you run DOE on a regular basis you might suggest curvature during planning based on your experience. If it is highly expected, you may go directly to response surface designs. Box-Benhken can save you some amount of trials (for 3 factors – 15 trilas versus 20 in CCD). The big assumption here that optimal settings…[Read more]

  • In Minitab you may try General Regression. It will give a huge list of levels of your factors (you may play with order). Trying to get any value out of this data, you finally come up to all rows which have any variation (not single values). Seems like in Excel you may get close result using filters and Remove duplicates function. 4 years, 10 months ago

  • I agree with @rbutler. Six Sigma is a systematic approach for process improvement, methodology which relies on set of tools (quality, statistical, project management). Big data, machine learning, etc. could complement Six Sigma in its work. In case you found Big Data tools can help in Analyze and Improve phase to confirm root causes and develop…[Read more]

  • Load More