基于Kriging模型的载人航天某装置结构优化设计研究

对于处在振动环境中的载人航天某装置复杂结构,设计过程中存在最小化质量、同时最大化一阶整体振动频率的多目标优化问题,可以利用多目标遗传算法(NSGA-II)求解得到Pareto最优解集,但利用NSGA-II进行求解计算量大,对于复杂结构更甚。为了节省计算时间,提出基于Kriging代理模型的复杂结构多目标优化设计方法,首先通过拉丁超立方采样获得样本点,然后通过样本点创建Kriging模型,最后利用多目标遗传算法求解代理模型得到Pareto最优解集,方便设计师从中选择最优解,优化结果表明本文所述方法合理有效。

Study on Structural Optimization of a Manned Aerospace Assembly Based on Kriging Model

For a manned aerospace assembly under vibration environment, there are two objectives in design phase: min mass and max first integral vibration frequency. Usually it can be solved by using multi-objective genetic algorithm (NSGA-II), but the computing amount is too large, especially for complex structure. To drop the computing time of using of NSGA-II in multi-objective structural optimization, a method based on Kriging model was proposed. The method achieved the samples from Latin hypercube design firstly and created the Kriging model based on the samples. Then multi-objective optimization problem could be solved using NSGA-II on the Kriging model and got the Pareto set finally. The results verify the effectiveness and practicability of the method.