MULTI-OBJECTIVE DESIGN OPTIMIZATION USING ADAPTIVE CLASSIFICATION

摘要

PROBLEM TO BE SOLVED: To provide methods of efficiently selecting design alternatives in multi-objective design optimization of a product.SOLUTION: Definition of a design space and an objective space for conducting multi-objective design optimization of a product is received in a computer system having a design optimization application module installed thereon. The design space is defined by design variables while the objective space is defined by design objectives. A first set of designs in the design space is selected. Each of the first set is evaluated in the objective space for non-dominance. The design space is partitioned into first and second regions using a multi-dimensional space division scheme (e.g., SVM). The first region is part of the design space containing all of the non-dominated design alternatives, while the second region contains remaining of the design space. A second set of designs is selected within the first region. Each of the second set and existing non-dominated design alternatives is evaluated for non-dominance. Multi-objective optimization repeats the partition and evaluation until an end condition is reached.SELECTED DRAWING: Figure 2A