Tek-Tips is the largest IT community on the Internet today!

Members share and learn making Tek-Tips Forums the best source of peer-reviewed technical information on the Internet!

  • Congratulations cowski on being selected by the Eng-Tips community for having the most helpful posts in the forums last week. Way to Go!

Determine the Control Limits

Status
Not open for further replies.

yutaini

Mechanical
Joined
Mar 15, 2001
Messages
18
Location
SG
Hi,

I'm a fresh graduate that just join the workforce as a process engineer. Currently, I'm task to set the control limits for a drying process. A sensor will determine the basket temperature just before it depart the dryer, and the time between basket is about 3 mins. So only one data is collected at every 3 mins intervial. The question is: What control chart will best suit this application. How to calculate the upper and lower control limits? Please advise. Thanks

Best Regards,
Yutaini
 
Yutaini,

It seems to me that you need to design your experiment before you start charting results.

Certainly you have more that two variables to measure -- time and temperature. How do you measure success or failure? Whatever these factors are, they need to be represented in your chart.

Once you can measure success, systematically vary your input variables (time and temperature) and record your success values for each time-temperature set. Plot your success values in a scatter chart with temperature in the y and time in the x. If you color code your points (green for success, red for failure), their should be a region of stability around which the limits of control can be interpreted.

One other suggestion -- how you systematically vary your input variables can really save you alot of time experimenting if you do it right. Of course, you need to remain objective and try not to anticipate your results to a degree that you influence the experiment.

Good luck,
DesignControl
 
Status
Not open for further replies.

Part and Inventory Search

Sponsor

Back
Top