Getting Operators To Really Use SPC; MCPs Can Help


Foster, Robert D.; Zirk, Wayne E.   (1992, ASQC)   Union Carbide Chemicals and Plastics Company, Inc., South Charleston, WV

Annual Quality Congress, Nashville TN    Vol. 46    No. 0
QICID: 9806    May 1992    pp. 201-207
List $10.00
Member $5.00

This article is not available online. Contact us to receive a scan of the archive, in PDF format.

Article Abstract

Continuous quality improvement in the chemical industry requires simplicity and focus. Complicated process models and contour maps, although truly effective research and development tools, must be made simple if they are to be used by operators to control a production unit. This is made possible by employing multiple curve plots (MCPs) to convert information into usable, simplified pictures which an average operator can decipher. MCPs graphically represent the effects of two selected significant inputs on the output. All the effects over the range of operations and the stipulations required to achieve any desired production rate can be obtained in seconds. Since MCP graphs are based on actual plant data, they quickly show the direction and relative importance of each effect. The difference between observed and predicted responses can be used as the basis for SPC charts, plotted to detect any unusual process upsets. MCPs are convincing enough to coax the operators to change their operating techniques. If the number of significant variables exceed 5 or so, the MCPs tend to lose their simplicity. In that case, the two most significant variables are plotted against each other on the vertical and horizontal axes and scales are chosen for both axes that will accommodate the fixed conditions of the remaining variables. The graph boundaries can be adjusted to correspond to the various constraint lines built into the graph for better results. Operators should be taught to interpret the graphs with an emphasis on variation in repeated experimentation. To make the MCPs more effective and to avoid frequent unexpected revisions, a long term plan should be in place to keep the models current. Multiple curve plots provide a powerful tool to help operators to control production units.


Continuous improvement (CI),Control charts,Operating Characteristic (OC) curve,Statistical process control (SPC),Statistics,Chemical and process industries,Union Carbide

Browse QIC Articles Chronologically:     Previous Article     Next Article

New Search

Featured advertisers

ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.