王英民,,
王奇
西北工业大学航海学院 西安 710072
基金项目:国家自然科学基金(51879221)
详细信息
作者简介:任笑莹:女,1989年生,博士生,主要研究方向为信号处理、人工智能算法
王英民:男,1963年生,教授,主要研究方向为信号处理、水声通信、声呐系统设计
王奇:男,1983年生,副研究员,主要研究方向为信号处理、目标检测与跟踪
通讯作者:王英民 ywang@nwpu.edu.cn
中图分类号:TN911.7计量
文章访问数:92
HTML全文浏览量:27
PDF下载量:23
被引次数:0
出版历程
收稿日期:2020-09-08
修回日期:2021-09-21
网络出版日期:2021-10-27
刊出日期:2021-12-21
Beam Pattern Optimization Method Based on Radial Basis Function Neural Network
Xiaoying REN,Yingmin WANG,,
Qi WANG
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
Funds:The National Natural Science Foundation of China (51879221)
摘要
摘要:针对不规则结构阵列的波束图容易出现旁瓣升高的问题,该文提出了一种基于径向基神经网络(RBFNN)的波束设计方法。该方法根据Olen波束形成中阵元位置和阵列加权向量之间的非线性关系,利用径向基神经网络输入和输出之间的非线性映射特性,以任意结构阵列的实际阵元位置为基准,构造带有误差的阵元位置样本集。之后利用Olen法计算阵列加权向量并进行波束形成,当波束图满足设计要求时,记录对应的位置和阵列加权向量作为径向基神经网络训练数据的输入样本和输出样本,并使用训练后的网络得到实际阵列的加权向量。最后,对直线阵、弧形阵、随机环形阵进行了波束优化设计,结果这几种阵形的波束都可以满足设计要求,证明了所提方法的有效性。
关键词:波束形成/
径向基神经网络/
旁瓣控制/
任意结构阵列
Abstract:In this paper, a method of beam pattern optimization based on Radial Basis Function Neural Network (RBFNN) is proposed for controlling sidelobe level of arbitrary geometry array. The proposed method takes advantage of the nonlinear mapping between the input and output of the radial basis function neural network, because of the nonlinear relationship between the position of the elements and the weighted vector of array in the Olen beamforming method. Many positions with errors centered on the real element positions are generated, when the beam pattern obtained by Olen beamforming method meet the design requirements, the corresponding positions and weighted vector are recorded as the input and output of training data. The beam patterns of uniform linear array, uniform arc array and random circular array are designed by using the trained neural networks. The results show that the proposed method is effective.
Key words:Beamforming/
Radial basis function neural network/
Sidelobe control/
Arbitrary geometry array
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=e54f1257-4730-4802-b1fe-90a21d1033e3