The Elsmar Cove Wiki More Free Files The Elsmar Cove Forums Discussion Thread Index Post Attachments Listing Failure Modes Services and Solutions to Problems Elsmar cove Forums Main Page Elsmar Cove Home Page
Google
  Web Elsmar.com
*Please be aware that SOME RECENT forum threads may not yet be indexed by Google.

View Full Version : Sloping control chart to take care of tool wear - Details needed


bkarthikeyan
13th January 2009, 03:28 AM
I need to know the methodology for plotting the Sloping control chart ( to take care of tool wear )preferably with an example

thanks in advance

Bev D
13th January 2009, 06:57 AM
"Can I Have Sloping Limits" Dr. Donald Wheeler, Quality Magazine, May 1999

“Process Control and Evaluation in the Presence of Systematic Assignable Cause”, Ashok Sarkar and Surajit,Pal, Quality Engineering, Volume 10(2), 1997-1998

Also look for Bob Doering's blogs on the uniform distribution here at the cove.

bobdoering
13th January 2009, 09:55 AM
I recommend:
Statistical process control for precision machining (http://elsmar.com/Forums/blog.php?b=79)

I believe this technique is more representative than sloping control chart of precision machining as it represents total variation control, including tool wear and measurement error. It is also far easier to implement. :cool:

Darius
14th January 2009, 03:11 PM
This tread is good,check for the attachement I posted there, Its Dr Wheeler article.

http://elsmar.com/Forums/showthread.php?t=14269

bobdoering
14th January 2009, 04:15 PM
This tread is good,check for the attachment I posted there, Its Dr Wheeler article.

The attached Selden article was a particularly good use for the sloping control chart, as it expects the slope to continue. This process is not as applicable to tool wear, as adjustments are expected (or the dimension would increase infinitely). The issue is not events that are relevant to the slope, but the slope itself, as the main variation for a process affected by tool wear, and adjustment based on it. It would also miss controlling the effect measurement error, giving false process variation. That is why for tool wear I recommend the X hi/lo-R methodology, as it deals with all of these effects, as well as deals with the correct uniform distribution - which the sloping chart also misses altogether. :cool:

bobdoering
14th January 2009, 04:19 PM
“Process Control and Evaluation in the Presence of Systematic Assignable Cause”, Ashok Sarkar and Surajit,Pal, Quality Engineering, Volume 10(2), 1997-1998

The the following note for an issue that was missed in this article:
http://elsmar.com/Forums/showpost.php?p=276533&postcount=24