基于多神经网络的可展开网状天线型面调整方法  

An adjustment method for deployable mesh antenna based on multi neural network

作　　者：苏冠龙 马小飞[1] 范叶森[1] 郑士昆[1,2] 李洋 李团结[2] 李欢笑[1] 林坤阳 SU Guanlong;MA Xiaofei;FAN Yesen;ZHENG Shikun;LI Yang;LI Tuanjie;LI Huanxiao;LIN Kunyang(Xi'an Institute of Space Radio Technology,Xi'an 710100,China;School of Mechano-electronic Engineering,Xidian University,Xi'an 710071,China)

机构地区：[1]西安空间无线电技术研究所,西安710100 [2]西安电子科技大学机电工程学院,西安710071

出　　处：《中国空间科学技术（中英文）》2024年第2期51-58,共8页Chinese Space Science and Technology

基　　金：国家自然科学基金(52175242);中国博士后科学基金(2021M703492)。

摘　　要：为在提高可展开网状天线型面精度的同时减少型面调整的工作量,提出了一种基于多神经网络的型面调整方法。通过分析新型张拉网状天线型面与调整索相关性与耦合机制,首次提出了型面调整策略。以10m口径的新型张拉网状天线为例进行了数值仿真研究,调整后型面的均方根值从5.4×10^(-3)m降低到1.1×10^(-3)m,从而验证了方法的有效性。To improve the surface accuracy of the deployable mesh antenna and reduce profile adjustment,a surface adjustment method based on multiple neural networks was proposed.By analyzing the correlation and coupling mechanism of the new tension mesh antenna surface,an adjustment strategy was proposed for the first time.Taking a 10m mesh antenna as an example,the root mean square value of the surface was reduced from 5.4×10^(-3)m to 1.1×10^(-3) m,which verifies the effectiveness of this method.

关 键 词：神经网络 网状天线 型面精度 型面耦合 型面调整 

分 类 号：TH122[机械工程—机械设计及理论]