Genetic Optimization Design Based on Support Vector Regression Metamodeling

Aiming at the optimization design problem with implicit objective performance functions, a genetic optimization design method based on the support vector regression (SVR) metamodeling is proposed. Appropriate design parameter samples are selected by experimental design theories, and the response samples are obtained from the experiments or numerical simulations. By applying the genetic algorithm (GA) to optimize the parameters of SVR, the metamodel is constructed and treated as the objective performance functions. In combination with other constraints, the optimization model is formed and solved by GA. The structure optimization of a microwave power divider is adopted as an example to illustrate the effectiveness of this design method. The learning samples are obtained from uniform design theory and the high frequency electromagnetic field finite element analysis codes (HFSS). Three response-surface objective functions for the magnitude, phase, and VSWR of the microwave power divider model are obtained and the multi-objective optimization problem is solved.