Integrating experimental design and statistical control for quality improvement

As a result of a successful case study, we advance a methodology for combining design of experiments (DOE) and cumulative score (Cuscore) charts to control and monitor an industrial process subject to a feedback control scheme. We use DOE to screen out the most important variable from a larger set of variables. We use the critical variable found in the DOE phase as a compensating factor in a feedback controller. We derive the proper Cuscore statistic that will identify spike signals in a dynamic system that is subject to feedback control. We then apply this Cuscore statistic to the output error from the control scheme. We illustrate the effectiveness of this process improvement methodology using an industrial case study where we identify and eliminate a recurring output quality problem in a pleating and gluing manufacturing operation.