CpK – Attribute Data
Six Sigma – iSixSigma › Forums › Old Forums › General › CpK – Attribute Data
- This topic has 5 replies, 5 voices, and was last updated 13 years, 5 months ago by
S.
-
AuthorPosts
-
April 14, 2008 at 12:20 pm #49853
Hi.
I have a task to evaluate process capability of marking (laser) process & a rubber cap insertion process (pressing) to bottle.
The production rate is 4000 parts per hour. The process runs 24 hours.
How I should collect my data – sampling freq., size, etc. ?
Best Regards,
Jim – Sg.
0April 14, 2008 at 2:03 pm #171140Jim,
What are you evaluating for?
Stevo0April 21, 2008 at 10:50 am #171344
Sandeep ThakurMember@Sandeep-ThakurInclude @Sandeep-Thakur in your post and this person will
be notified via email.Dear Jim
You can take 5-10 samples per shift for calculating process capability for any critical characteristics.
5 samples per shift will be easily managed by you or concerned operator. it is generally recommended as it will save your time or effort also.
for any further query pl feel free.
Sandeep Thakur
0April 21, 2008 at 10:50 am #171345Right. What are you evaluating for? You need to better define what it is you want to learn from the process. This will help you determine how to sample (frequency, number, and location.) How many lasers do you have? 1? 2? 20? Are you looking to determine laser to laser variation? If so, set up your sampling to gather pieces from each laser at some frequency. Is it time to time you want to understand? Over how long a duration do you expect to see a change? Sample within that duration until you see the change you are looking for. How many cappers do you have? Is it capper to capper variation you want to understand? Do you see variation over time on the cappers? How much? Set up a sampling plan to capture that variation, across cappers.
As you can probably tell from my questions, your best bet is to design the sampling strategy to answer the questions you have of the process. You must first determine what it is you want to learn, devise your strategy to learn that i.e. your sampling plan, then go execute your strategy (I recommend a trial run before you launch any large-scale study.)
Good luck!0January 13, 2009 at 2:25 pm #179673Team,
Question was simple and I guess Sandeep’s reply would have answered.0January 13, 2009 at 2:25 pm #179674Team,
Question was simple and I guess Sandeep’s reply would have answered.0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.