Fractional factorial (FF) designs are commonly used in factorial experiments. When the levels of some factors are difficult to be changed or controlled, it may be impracti-cal or even impossible to perform the experimental runs of FF designs in a completely random order. This motivates us to use fractional factorial split-plot (FFSP) designs to meet the special demands. In factorial investigations, there are not only two level factors, but also high-level factors. If there are some two-level factor and a four-level factor and an eight-level factor in an experiment and it is difficult to change or control the four-level factor and eight-level factor, a split-plot 2(n1+n2)-(k1+k2)4W18W1 design can be used.In this paper, we study the mixed-level fractional factorial split-plot design that has a four-level factor, an eight-level factor and some two-level factors in the whole-plot, and some two-level factors in the sub-plot, denoted by 2(n1+n2)-(k1+k2)4W18W1 design. We give the conditions for the design that contains different clear effects and the construction method of all kinds of designs. It is divided into five chapters.Chapter 1 is divided into four sections. Section 1.1 introduces the definition and application of factorial design. Section 1.2 introduces the two-level factor design. Section 1.3 introduces mixed-level factor design. Section 1.4 mainly introduces the properties, application and structure of the split-plot design.Chapter 2 introduces the notation and definitions of the mixed-level fractional factorial split-plot design.Chapter 3 mainly introduces the sufficient and necessary conditions for resolution ? 2(n1+n2)-(k1+k2)4W18W1 design that contains different clear effects and the construction method of 2?(n1+n2)-(k1+k2)4W18W1 design that contains all kinds of clear effects.Chapter 4 mainly introduces conditions for resolution ? 2(n1+n2)-(k1+k2)4W18W1 design that contains different clear effects and the construction method of 2?(n1+n2)-(k1+k2)4W18W1 design that contains all kinds of clear effects.Chapter 5 gives a brief summary of the whole article. |