| Split-plot designs are commonly used in industrial experiments when there are hard-to-change and easy-to-change factors. Due to the number of factors and resource limitations, it is more practical to run a fractional factorial split-plot (FFSP) design. These designs are variations of the fractional factorial (FF) design, with the restricted randomization structure to account for the whole plots and subplots. This paper begins by discussing the formulation of FFSP designs using integer programming (IP) to achieve various design criteria. Specifically, the design criterion looks at the maximum number of clear two-factor interactions and variations on this criterion. By making restrictions on some of the general linear constraints, the experimenter can customize the alias structure of these FFSP designs. Additional constraints allow for the generation of blocked FFSP designs that are shown to meet performance standards shown in today's literature. By augmenting the model formulation, FFSP designs are generated for sequential processes with three and four stages. In addition, initial exploration is presented using genetic algorithm heuristic to search for split-plot designs from a candidate matrix of factor effects generated using the Kronecker product. |
