基于径向基神经网络的波束优化方法

任笑莹; 王英民; 王奇

doi:10.11999/JEIT200793

基于径向基神经网络的波束优化方法

doi: 10.11999/JEIT200793

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: 832
- HTML全文浏览量: 377
- PDF下载量: 66
- 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

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。
- 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.
- Beamforming /
- Radial basis function neural network /
- Sidelobe control /
- Arbitrary geometry array

HTML全文

图 1 RBFNN的网络结构

下载: 全尺寸图片幻灯片

图 2 隐含层神经元模型

下载: 全尺寸图片幻灯片

图 3 Gauss函数

下载: 全尺寸图片幻灯片

图 4 扩展速度对激励函数的影响

下载: 全尺寸图片幻灯片

图 5 直线阵

下载: 全尺寸图片幻灯片

图 6 直线阵的波束图

下载: 全尺寸图片幻灯片

图 7 弧形阵

下载: 全尺寸图片幻灯片

图 8 弧形阵的波束图

下载: 全尺寸图片幻灯片

图 9 随机环形阵

下载: 全尺寸图片幻灯片

图 10 随机环形阵的波束图

下载: 全尺寸图片幻灯片

参考文献(30)

[1]	HAN Sarang, JI S, KANG I, et al. Millimeter wave beamforming receivers using A Si-based OBFN for 5G wireless communication systems[J]. Optics Communications, 2019, 430: 83–97. doi: 10.1016/j.optcom.2018.08.031
[2]	刘兴隆, 杜彪, 周建寨. 一种新型椭圆波束天线设计技术[J]. 电子与信息学报, 2019, 41(12): 2911–2918. doi: 10.11999/JEIT190142 LIU Xinglong, DU Biao, and ZHOU Jianzhai. A novel shaping design technique of the elliptical beam antenna[J]. Journal of Electronics &Information Technology, 2019, 41(12): 2911–2918. doi: 10.11999/JEIT190142
[3]	黄俊生, 苏洪涛. 二维相控阵-MIMO雷达联合发射子阵划分和波束形成设计方法[J]. 电子与信息学报, 2020, 42(7): 1557–1565. doi: 10.11999/JEIT190429 HUANG Junsheng and SU Hongtao. Joint transmitting subarray partition and beamforming design method based on two-dimensional phased-MIMO radar[J]. Journal of Electronics &Information Technology, 2020, 42(7): 1557–1565. doi: 10.11999/JEIT190429
[4]	TUNA C, JONES D L, ZHAO Shengkui, et al. Wideband compressive beamforming tomography for drive-by large-scale acoustic source mapping[J]. The Journal of the Acoustical Society of America, 2018, 143(6): 3899–3911. doi: 10.1121/1.5042214
[5]	MOZAFFARZADEH M, SADEGHI M, MAHLOOJIFAR A, et al. Double-stage delay multiply and sum beamforming algorithm applied to ultrasound medical imaging[J]. Ultrasound in Medicine & Biology, 2018, 44(3): 677–686.
[6]	DOLPH C L. A current distribution for broadside arrays which optimizes the relationship between beam width and side-lobe level[J]. Proceedings of the IRE, 1946, 34(6): 335–348. doi: 10.1109/JRPROC.1946.225956
[7]	刘福来, 陈萍萍, 汪晋宽, 等. 基于多参数二次规划的零陷展宽和旁瓣控制方法[J]. 东北大学学报:自然科学版, 2012, 33(11): 1559–1562. LIU Fulai, CHEN Pingping, WANG Jinkuan, et al. Null broadening and sidelobe control method based on multiparametric quadratic programming[J]. Journal of Northeastern University:Natural Science, 2012, 33(11): 1559–1562.
[8]	GUO Xijing, MIRON S, YANG Yixin, et al. Second-order cone programming with probabilistic regularization for robust adaptive beamforming[J]. The Journal of the Acoustical Society of America, 2017, 141(3): EL199. doi: 10.1121/1.4976846
[9]	陆必应, 梁甸农. 柔性稀疏阵的稳健波束形成[J]. 信号处理, 2007, 23(2): 169–173. LU Biying and LIANG Diannong. A robust beamforming approach with applications to flexible sparse arrays[J]. Signal Processing, 2007, 23(2): 169–173.
[10]	臧守明, 白媛, 马秀荣, 等. 一种改进的嵌套阵列波束形成算法[J]. 计算机仿真, 2016, 33(10): 221–225,380. ZANG Shouming, BAI Yuan, MA Xiurong, et al. Improved beamforming algorithm in nested array[J]. Computer Simulation, 2016, 33(10): 221–225,380.
[11]	XU Haisheng, BLUM R S, WANG Jian, et al. Colocated MIMO radar waveform design for transmit beampattern formation[J]. IEEE Transactions on Aerospace and Electronic Systems, 2015, 51(2): 1558–1568. doi: 10.1109/taes.2014.140249
[12]	李文兴, 毛晓军, 翟助群. 抗导向矢量失配的零陷展宽波束形成算法[J]. 哈尔滨工业大学学报, 2016, 48(11): 116–122. LI Wenxing, MAO Xiaojun, and ZHAI Zhuqun. Null broadening beamforming against steering vector mismatch[J]. Journal of Harbin Institute of Technology, 2016, 48(11): 116–122.
[13]	ABBASI-JANNATABAD M and KHOSHBIN H. Cooperative beamforming and relay selection in cognitive radio systems[J]. International Journal of Communication Systems, 2016, 29(2): 330–340. doi: 10.1002/dac.2834
[14]	HU Bin, WU Xiaochuan, ZHANG Xin, et al. Adaptive beamforming for sparse array based on semi-definite programming[J]. IEEE Access, 2018, 6: 64525–64532. doi: 10.1109/access.2018.2878153
[15]	鄢社锋, 马远良, 孙超. 任意几何形状和阵元指向性的传感器阵列优化波束形成方法[J]. 声学学报, 2005, 30(3): 264–270. YAN Shefeng, MA Yuanliang, and SUN Chao. Beampattern optimization for sensor arrays of arbitrary geometry and element directivity[J]. Acta Acustica, 2005, 30(3): 264–270.
[16]	马远良. 任意结构形状传感器阵方向图的最佳化[J]. 中国造船, 1984(4): 80–87. MA Yuanliang. Pattern optimisation for sensor arrays of arbitrary geometry[J]. Shipbuilding of China, 1984(4): 80–87.
[17]	OLEN C A and COMPTON R T. A numerical pattern synthesis algorithm for arrays[J]. IEEE Transactions on Antennas and Propagation, 1990, 38(10): 1666–1676. doi: 10.1109/8.59781
[18]	ZHOU P Y, INGRAM M A, and ANDERSON P D. Synthesis of minimax sidelobes for arbitrary arrays[J]. IEEE Transactions on Antennas and Propagation, 1998, 46(11): 1759–1760. doi: 10.1109/8.736644
[19]	WU Renbiao, BAO Zheng, and MA Yuanliang. Control of peak sidelobe level in adaptive arrays[J]. IEEE Transactions on Antennas and Propagation, 1996, 44(10): 1341–1347. doi: 10.1109/8.537328
[20]	钱鹏, 陆金桂, 朱正权. 基于径向基神经网络的液压支架前连杆可靠性评估研究[J]. 矿业研究与开发, 2019, 39(1): 110–113. QIAN Peng, LU Jingui, and ZHU Zhengquan. Reliability evaluation of front connecting rod of hydraulic support based on RBF neural network[J]. Mining Research and Development, 2019, 39(1): 110–113.
[21]	ZHANG Liwei, LIU Xiaotian, and ZHANG Jingbiao. Regulation capability evaluation of individual electric heating load based on radial basis function neural network[J]. Thermal Science, 2019, 23(5A): 2821–2829. doi: 10.2298/tsci190104196z
[22]	LIN Hongjun, DAI Qunyun, ZHENG Lili, et al. Radial basis function artificial neural network able to accurately predict disinfection by-product levels in tap water: Taking haloacetic acids as a case study[J]. Chemosphere, 2020, 248: 125999. doi: 10.1016/j.chemosphere.2020.125999
[23]	PANDEESWARI B, SUTHA J, and PARVATHY M. A novel synthetic aperture radar image change detection system using radial basis function-based deep convolutional neural network[J]. Journal of Ambient Intelligence and Humanized Computing, 2021, 12(1): 897–910. doi: 10.1007/s12652-020-02091-y
[24]	CHAO Zhen and KIM H J. Removal of computed tomography ring artifacts via radial basis function artificial neural networks[J]. Physics in Medicine & Biology, 2019, 64(23): 235015. doi: 10.1088/1361-6560/ab5035
[25]	HUANG Chao, WANG Xiangyu, LI Liang, et al. Multistructure radial basis function neural-networks-based extended model predictive control: Application to clutch control[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(6): 2519–2530. doi: 10.1109/tmech.2019.2949001
[26]	李艳东, 朱玲, 郭媛, 等. 基于径向基函数神经网络的移动机器人多变量固定时间编队控制[J]. 信息与控制, 2019, 48(6): 649–657. LI Yandong, ZHU Ling, GUO Yuan, et al. Radial basis function neural network-based multivariable fixed-time formation control of mobile robots[J]. Information and Control, 2019, 48(6): 649–657.
[27]	KUMAR R, AGRAWAL H P, SHAH A, et al. Maximum power point tracking in wind energy conversion system using radial basis function based neural network control strategy[J]. Sustainable Energy Technologies and Assessments, 2019, 36: 100533. doi: 10.1016/j.seta.2019.100533
[28]	冯晓宇, 谢军伟, 张晶, 等. 低快拍下模糊径向基神经网络波束形成算法[J]. 火力与指挥控制, 2018, 43(4): 132–135,140. FENG Xiaoyu, XIE Junwei, ZHANG Jing, et al. Beamforming algorithm based on fuzzy RBF neural network in the situation of limited snapshots[J]. Fire Control &Command Control, 2018, 43(4): 132–135,140.
[29]	ENRICONI M P, DE CASTRO F C C, MÜLLER C, et al. Phase transmittance RBF neural network beamforming for static and dynamic channels[J]. IEEE Antennas and Wireless Propagation Letters, 2020, 19(2): 243–247. doi: 10.1109/lawp.2019.2958682
[30]	MAYER K S, SOARES J A, and ARANTES D S. Complex MIMO RBF neural networks for transmitter beamforming over nonlinear channels[J]. Sensors, 2020, 20(2): 378. doi: 10.3390/s20020378