车载超短波电台电波传播预测模型研究

doi:10.16180/j.cnki.issn1007-7820.2023.07.009

摘要/Abstract

摘要：

针对实战环境中车载超短波电台通信距离和质量受地面附着物和地形地貌影响的问题,文中基于射线追踪和机器学习,建立了车载超短波电台电波传播预测模型。采用装甲车辆与车载天线的一体化建模获得车载天线辐射方向图,融合电子地图,建立了基于射线追踪技术的电波传播仿真模型。利用随机森林机器学习算法和仿真模型的数据结果,建立了基于随机森林的电波传播预测模型,并与经典电波传播模型如Egli模型和Okumura-Hata模型进行对比。结果显示,基于随机森林的电波传播模型预测精度更高,均方根误差达到2.190 1 dB,决定系数达到0.960 1,可准确预测战术通信环境中的电波传播情况。

关键词: 超短波, 路径损耗, 射线追踪法, 电波传播模型, 机器学习, 随机森林, 电子地图, 车载天线

Abstract:

Given the problem that the communication distance and quality of the vehicle-mounted ultrashort wave radio are affected by ground attachments and topography in the actual combat environment, a radio wave propagation prediction model of vehicle-mounted ultrashort wave radio is established based on ray tracing and machine learning. The integrated modeling of armored combat vehicle and vehicle antenna is established to obtain the antenna radiation pattern, and combined with electronic images, the radio wave propagation simulation model based on ray tracing technology is established. Based on the machine learning algorithm of the random forest and data results for the simulation model, the radio wave propagation prediction model based on the random forest was established. Compared with traditional classical radio wave propagation models such as the Egli and Okumura-Hata models, the radio wave propagation prediction model based on the random forest has higher accuracy. The root mean square error reaches 2.190 1 dB, and the coefficient of determination reaches 0.960 1. It can accurately predict radio wave propagation in the tactical communication environment.

Key words: ultrashort wave, path loss, ray-tracing method, radio wave propagation model, machine learning, random forest, electronic images, vehicle antenna

中图分类号:

TN011

李敏,张光硕,徐至江,谢红星,路宏敏. 车载超短波电台电波传播预测模型研究[J]. 电子科技, 2023, 36(7): 64-69.

LI Min,ZHANG Guangshuo,XU Zhijiang,XIE Hongxing,LU Hongmin. Research on Radio Wave Propagation Prediction Model of Vehicle-Mounted Ultrashort Wave Radio[J]. Electronic Science and Technology, 2023, 36(7): 64-69.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

图8

表2

参考文献 19

[1]	金慧琴, 王正磊, 周新力. PE模型三维电磁环境计算方法研究[J]. 电子科技, 2018, 31(3):39-43.
	Jin Huiqin, Wang Zhenglei, Zhou Xinli. Research on PE model three-dimensional electromagnetic environment calculation method[J]. Electronic Science and Technology, 2018, 31(3):39-43.
[2]	宋丙鑫, 路宏敏, 李敏玥, 等. 一种车载通信设备电磁兼容性预测方法[J]. 电子科技, 2021, 34(5):7-12.
	Song Bingxin, Lu Hongmin, Li Minyue, et al. An EMC prediction method of vehicular communication equipment[J]. Electronic Science and Technology, 2021, 34(5):7-12.
[3]	Bedeer E, Pugh J, Brown C, et al. Measurement-based path loss and delay spread propagation models in VHF/UHF bands for IoT communications[C].Toronto: Proceedings of the IEEE Eighty-sixth Vehicular Technology Conference, 2017:1-5.
[4]	兰田, 全厚德, 崔佩璋, 等. 起伏地形下超短波电波传播模型修正方法[J]. 计算机仿真, 2019, 36(10):148-152.
	Lan Tian, Quan Houde, Cui Peizhang, et al. Correction methods of VHF propagation models around irregularterrain[J]. Computer Integrated Manufacturing Systems, 2019, 36(10):148-152.
[5]	Maloku H, Fazliu Z L, Sela E, et al. Path loss model fitting for TV bands based on experimental measurements for urban environments in Kosovo[C].Opatija: Proceedings of the Forty-second International Convention on Information and Communication Technology,Electronics and Microelectronics, 2019:480-485.
[6]	Celik G, Aitalieva A, Celebi H. Comparison of empirical and ray-traced based channel modeling on VHF band[C]. Sivas: Proceedings of the Twenty-seventh Signal Processing and Communications Applications Conference, 2019:1-4.
[7]	He D, Ai B, Guan K, et al. The design and applications of high-performance ray-tracing simulation platform for 5G and beyond wireless communications: A tutorial[J]. IEEE Communications Surveys & Tutorials, 2018, 21(1):10-27.
[8]	Popoola S I, Jefia A, Atayero A A, et al. Determination of neural network parameters for path loss prediction in very high frequency wireless channel[J]. IEEE Access, 2019(7):150462-150483.
[9]	Cheng H, Ma S, Lee H, et al. Millimeter wave path loss modeling for 5G communications using deep learning with dilated convolution and attention[J]. IEEE Access, 2021(9):62867-62879.
[10]	Moreta C, Acosta M, Koo I. Prediction of digital terrestrial television coverage using machine learning regression[J]. IEEE Transactions on Broadcasting, 2019, 65(4):702-712. doi: 10.1109/TBC.11
[11]	Goudos S K, Athanasiadou G, Tsoulos G V, et al. Modelling ray tracing propagation data using different machine learning algorithms[C].Copenhagen: Proceedings of the Fourteenth European Conference on Antennas and Propagation, 2020:1-4.
[12]	Aldossari S, Chen K C. Predicting the path loss of wireless channel models using machine learning techniques in mmWave urban communications[C].Lisbon: Proceedings of the Twenty-second International Symposium on Wireless Personal Multimedia Communications, 2020:1-6.
[13]	Jo H S, Park C, Lee E, et al. Path loss prediction based on machine learning techniques:Principal component analysis, artificial neural network,and gaussian process[J]. Sensors, 2020, 20(7):1927-1932. doi: 10.3390/s20071927
[14]	孟晓姣, 张世巍, 李小健, 等. 一种基于BP神经网络的车载通信设备性能评估方法[J]. 电子科技, 2021, 34(5):24-28.
	Meng Xiaojiao, Zhang Shiwei, Li Xiaojian, et al. An evaluation method of vehicle-mounted communication equipment performance based on BP neural network[J]. Electronic Science and Technology, 2021, 34(5):24-28.
[15]	肖景明. 电波传播工程计算[M]. 西安: beoplay体育提现出版社, 1989:79-80.
	Xiao Jingming. Engineering calculation of radio wave propagation[M]. Xi'an: Xidian University Press, 1989:79-80.
[16]	Egli J J. Radio propagation above 40 mc over irregular terrain[J]. Proceedings of the IRE, 1957, 45(10):1383-1391. doi: 10.1109/JRPROC.1957.278224
[17]	International Telecommunication Union. Recommendation ITU-R P.1546-5 method for point-to-area predictions for terrestrial services in the frequency range 30 MHz to 3000 MHz[S]. Geneva:ITU, 2013.
[18]	Hata M. Empirical formula for propagation loss in land mobile radio services[J]. IEEE Transactions on Vehicular Technology, 1980, 29(3):317-325. doi: 10.1109/T-VT.1980.23859
[19]	Kreyszig E. Advanced engineering mathematics[M]. 7th ed. New York: Wiley, 1993:198-217.

模型	参数名称	参数取值
随机森林	决策树个数	180
	内部节点分裂的最小样本数	2
	叶子节点的最小样本数	1
	叶子节点中样本的最小权重	0
	树的最大深度	10
k近邻	所选用的近邻数	3
	预测的权函数	权重是距离的倒数
	向量距离算法	欧氏距离
BP神经网络	隐藏层神经元个数	11

模型	RMSE/dB	R²
随机森林	2.190 1	0.960 1
k近邻	3.703 9	0.885 9
BP神经网络	5.927 5	0.707 8
线性回归	8.555 1	0.391 4
自由空间	15.266 8	-0.938 2
Egli	22.634 8	-3.260 4
Okumura-Hata	24.405 2	-3.952 9
ITU-R P.1546	25.742 2	-8.196 0