Authors: Tae-Yeon Cho, Connie M. Borror, Douglas C. Montgomery
Addresses: Department of Industrial Engineering, Arizona State University, Tempe, AZ 85287, USA. ' Department of Industrial Engineering, Arizona State University, Tempe, AZ 85287, USA. ' Department of Industrial Engineering, Arizona State University, Tempe, AZ 85287, USA
Abstract: In mixture-process variable experiments, the number of runs can become prohibitively large as the number of variables (process or mixture) increases. In addition, some variables can be hard-to-change due to practical or economical considerations. In these cases, the split-plot design is often used to overcome the restricted randomisation problem. In this paper, fraction of design space (FDS) plots for a mixture-process variable design within a split-plot structure are developed and demonstrated. FDS plots are used to evaluate the prediction capability of various designs. Sliced FDS plots are presented to show the influence of mixture variables and process variables on the prediction variance over the design space.
Keywords: design evaluation; fraction of design space; FDS plots; mixture-process variable experiments; MPV; split-plot design; mixture-process variable design; mixture variables; process variables; prediction variance.
International Journal of Quality Engineering and Technology, 2009 Vol.1 No.1, pp.2 - 26
Published online: 18 Dec 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article