Design Mode Analysis of Pareto Solution Set for Decision-Making Support

Algorithm 1

Design mode analysis.

 (1) Generate a design dataset X = () of size N.

(2) Divide the dataset into H clusters

    by using data clustering.

(3) for  i = 1 to H do

(4)   Extract the design mode = () by

   applying the PCA () on ith cluster.

(5)   Calculate and study the component loading

   = () for each using

(6)   Choose a base design b from the ith cluster,

   or calculate a mean vector instead of it.

(7)   Choose a number of design modes p

   used for generating new designs.

(8)   Generate a new design X′ based on

   .

   Coefficient is an arbitrary constant.

(9) end for