支持向量机替代模型的遗传优化设计

针对实际工程中常见的性能函数不能显式表示的优化问题，提出一种基于支持向量机替代模型的遗传优化设计方法。利用试验设计选取合适的设计参数样本点，通过实验或数值仿真获得响应输出，结合遗传算法构建具有参数优化功能的支持向量机替代模型；将支持向量机模型作为目标性能函数，结合其他约束条件完成优化模型的建立，并应用遗传算法进行优化，形成一套准确、高效、适应性强的优化方法。以典型电子装备功分器的结构尺寸优化为例，采用均匀试验设计和高频电磁场仿真软件HFSS获取替代模型训练的学习样本，建立功分器模型的幅度比、相位差和驻波3个响应面目标函数，并对该多目标优化问题进行遗传寻优。

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.