论文部分内容阅读
为降低卫星天线的发射成本,提高天线的展开刚度,以多模块构架式空间可展开天线结构的质量和1阶固有频率为目标函数,基于误差反向传播(BP)神经网络和遗传算法对天线的结构参数进行了优化.运用ANSYS软件对支撑桁架的结构参数进行了数值模拟,得到了与设计变量对应的目标函数值;通过正交试验设计,构建了用于神经网络训练和检验的样本集;按照BP算法的基本思想,调整网络模型的参数,建立了用于优化的预测模型;采用分目标乘除法,将多目标优化问题转变成单目标优化问题;采用遗传算法进行了优化分析,得到了支撑桁架各杆件的设计参数.结果表明:该优化方法在降低天线质量的同时,使结构的刚度得到了提高,为天线的结构设计提供了参考.
In order to reduce the launch cost of the satellite antenna and improve the stiffness of the antenna, an objective function of the mass and the first-order natural frequency of the antenna structure can be deployed in a multi-module rack space. Based on the error back propagation (BP) neural network and the genetic algorithm The structural parameters of the truss are numerically simulated by ANSYS software and the objective function values corresponding to the design variables are obtained. Through the orthogonal experimental design, a sample set for neural network training and inspection is constructed ; According to the basic idea of BP algorithm, adjust the parameters of network model to establish a prediction model for optimization; using sub-target multiplication and division method, the multi-objective optimization problem is transformed into single-objective optimization problem; Genetic algorithm is used to optimize the model and obtain The results show that the optimization method can improve the stiffness of the structure while reducing the quality of the antenna and provide a reference for the structure design of the antenna.