Control Charting
Six Sigma – iSixSigma › Forums › Old Forums › General › Control Charting
- This topic has 7 replies, 6 voices, and was last updated 18 years, 5 months ago by
Gabriel.
-
AuthorPosts
-
December 12, 2003 at 3:49 am #34089
I am currently working on a project to implement control chart for a production line. Basically the process is that the operator is required to slide 20mm metal piece over a extruded tubing, and the metal piece must be placed in between two marks on the extruded tubing. The measurement is the gap between each end of the metal piece and the mark. Hence, the process capability is somehow operator dependant (depends on where the operator places the metal piece). Is the control chart tells me anything in this case?
0December 12, 2003 at 8:37 am #93521Dear Aidan,
The fact that there is an operator doing the process doesn’t matter for the usability of the control chart. Your controll chart will show how well the result of the process is in control compared to the specs. The operator is an intrinsic part of the process that you are studying.
Obviously, the operator could be one of the factors that could play a role when the process turns out not to be in controll, based on your controll chart. If there is a signal for an out-of-control proces, you could check if operator influences is an important factor.
What might be of concern for the usability of the control chart is the quality of the measurement that you use to collect your data. Have you remembered to validate this measurements’ calibration, resolution, R&R performance? If there is for instance a too large operator dependence in your measurement, that will make your control chart unusable. At least until you improve the measurement first.
Arend
Senior Development Engineer0December 12, 2003 at 2:27 pm #93527
GabrielParticipant@GabrielInclude @Gabriel in your post and this person will
be notified via email.An SPC exam question:
What is wrong in the following sentence?
“Your controll chart will show how well the result of the process is in control compared to the specs.”0December 12, 2003 at 2:58 pm #93530
Marc RichardsonParticipant@Marc-RichardsonInclude @Marc-Richardson in your post and this person will
be notified via email.One does not normally put tolerances on a control chart. However, this is a matter of some debate. There are precontrol charts on which tolerance limits do appear. That being said, It is possible to calculate process capability metrics from control chart data without the tolerances appearing on the chart itself.
I would try to error-proof the process by using some kind of fixturing to make the process less dependent on the operator positioning the parts correctly and worry less about whether or not I could control chart the process. But that’s just me being practical again.
Marc RichardsonSr. Q.A. Eng.
0December 12, 2003 at 3:31 pm #93536
facemanParticipant@facemanInclude @faceman in your post and this person will
be notified via email.My criticism of that statement would be:
The control limits on a control chart are independant of the spec limits; therefore your control chart indicates if your process is operating ‘in control’ (within its predictable or natural range) not if it is performing to spec (fit for use). If your capability indices are very low, it might be possible to have a process in control but out of spec. You really shouldn’t rely on SPC if this is the case, maybe you should 100% inspect until you get your six sigma project done and have a capable process. On the other hand, if your process is very capable, then you might have an out of control condition but your process still yields parts that are ‘fit for use’. In this case, it might be reasonable to resolve the out of control indication, reinspect the parts made since the last in control observation, and ship the parts that meet spec even if they were made when the process was performing unpredictably.
Spec limits answer one question, control limits answer another.
Regards,
Faceman0December 12, 2003 at 3:35 pm #93538
Andy UrquhartParticipant@Andy-UrquhartInclude @Andy-Urquhart in your post and this person will
be notified via email.Gabriel,
The central limit theoren springs to mind. Mind you I have met a few process engineers who would like to use tolerances based on average!
Cheers,
Andy0December 13, 2003 at 5:19 am #93554Gabriel,You’re right. That should teach me not to post late-night replies without reading twice ;-). Of course it is Control Limits. The real message, however, is that the fact that the operator is involved in the process doesn’t matter at all for the usability of the controll chart.Thanks for pointing out the blooper; let’s continue discussing the real question of Aidan instead!Arend
0December 14, 2003 at 2:47 am #93567
GabrielParticipant@GabrielInclude @Gabriel in your post and this person will
be notified via email.Sorry, I could not resist.
Abut the original question, you’ve laready said it. The fact that the operator is involved does not make the control chart unusable at all. Rather, if the operator happen to be a special cause of variation, that will show up on the chart, and corrective actions shall be adressed in such a way that the output (process + measurement) is not operator dependant. Some of these corrective actios were mentioned in previous posts in this thread (training, fixture, …)0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.