What’s the Cure?

Pick a chart, any chart

Published: Tuesday, September 19, 2006 - 22:00

In a certain operation, a part is subject to a high-temperature curing cycle. The ideal curing scan is illustrated in the chart below. The oven chamber begins at room temperature, ramps up to a conditioning temperature of about 80 degrees, dwells for four minutes, ramps up again to the curing temperature of 120 degrees, dwells for five minutes and then cools back to room temperature.To monitor the temperature profile, a thermocouple is placed on the part. There are 11 key temperature readings during the cycle marked on the illustration. There are temperature specifications for each of the key time intervals. The software that controls the oven will generate a hard-copy scan of each curing cycle, but the company wants to use statistical process control (SPC) methods to analyze the 11 key temperature points.

What chart(s) would you recommend in this case?

Choose one of the following:

1. Use 11 different IX-MR control charts—one for each key temperature reading.
2. Three charts need to be used—one for each of the three stages (condition, cure and cool down). The condition stage needs to be an Xbar-R chart, because there are three readings per cycle. The cure and cool-down stages would be best managed using a Group Xbar-R chart, because the last temperature of the cure stage is grouped with the start temperature of the cool-down stage.
3. One defectives chart can be used to monitor the cure cycle. Each plot point represents the number of times a key temperature falls out of specification. Subgroup size would be 11 because there are 11 opportunities for finding an out-of-specification reading.
4. Because each key temperature has a different target, plot the values as deviation from target. Each cycle will produce 11 plot points, but with shared control limits.
5. Calculate the difference between the actual key temperature and the ideal. Combine all 11 residuals on a Group IX-MR chart.
6. SPC can only be applied during condition and cure—when the desired temperatures are constant. Subgroup size is three—three readings are taken during these dwell periods. Keep the condition and cure data on separate Xbar-R charts.

The answer will be in the Oct. 4 issue of InsideSixSigma.

How about you? Do you have a brain teaser to share? If you do, please send it to Quality Digest’s editorial department here.

About The Author

Steve Wise

Steve Wise is the vice president of statistical methods for InfinityQS, helping companies from all industries implement real-time production for statistical process control and advanced statistical tools. He co-authored  an  industry standard, “D1-9000 Advanced Quality System” in 1991 for Boeing suppliers. Wise is co-author of the book Innovative Control Charting: Practical SPC Solutions for Today's Manufacturing Environment (ASQ Quality Press, 1997).