一种基于BP神经网络的车载通信设备性能评估方法

doi:10.16180/j.cnki.issn1007-7820.2021.05.005

电子科技 ›› 2021, Vol. 34 ›› Issue (5): 24-28.doi: 10.16180/j.cnki.issn1007-7820.2021.05.005

一种基于BP神经网络的车载通信设备性能评估方法

孟晓姣¹,张世巍²,李小健²,李敏玥¹,宋丙鑫¹,路宏敏¹

1.西安电子科技大学电子工程学院,陕西西安 710071
2.中国北方车辆研究所电磁兼容实验室,北京 100072

收稿日期:2020-01-13 出版日期:2021-05-15 发布日期:2021-05-24
作者简介:孟晓姣(1993-),女,硕士研究生。研究方向:电子与通信工程。|李敏玥(1995-),女,硕士研究生。研究方向:环境工程。|路宏敏(1961-),男,博士,教授,博士生导师。研究方向:电磁场与微波技术、工程电磁兼容、环境科学。
基金资助:
国防预研项目(JZX7X201901JY0048)

An Evaluation Method of Vehicle-Mounted Communication Equipment Performance Based on BP Neural Network

MENG Xiaojiao¹,ZHANG Shiwei²,LI Xiaojian²,LI Minyue¹,SONG Bingxin¹,LU Hongmin¹

1. School of Electronic Engineering,Xidian University,Xi’an 710071,China
2. EMC Laboratory,China North Vehicle Research Institute,Beijing 100072,China

Received:2020-01-13 Online:2021-05-15 Published:2021-05-24
Supported by:
The Defense Advanced Research Projects(JZX7X201901JY0048)

摘要/Abstract

摘要：

不断增多的车载通信设备数量导致车载通信系统面临日益严重的电磁干扰问题。针对复杂电磁环境下车载通信设备性能评估问题,文中基于神经网络非线性拟合精度高及自调节功能强的特点,提出了一种车载通信设备性能评估方法。依据车载通信设备的关键技术指标,建立了发射、传输、接收的链路评估体系,构建了基于BP神经网络的车载通信设备性能评估模型。利用MTALAB使用大量数据样本优化训练BP神经网络模型结构,提高了评估模型精度。验证结果表明,所构建神经网络评估模型归一化均方误差可达-36 dB,且评估误差较小。

关键词: 车载通信设备, 通信性能, BP神经网络, 通信距离, 评估模型, 模型训练, NMSE, 评估精度

Abstract:

With an increasing number of vehicular communication equipment, the communication system is faced with increasingly serious electromagnetic interference problem. In this study, based on the characteristics of high nonlinear fitting accuracy and strong self-tuning of BP neural network, an evaluation method is proposed to evaluate the performance of vehicular communication equipment under the complex electromagnetic environment. According to the critical technology indicators of vehicular communication equipment, an evaluation system including transmission, reception and interaction is established, and an evaluation model based on BP neural network structure is constructed. With the use of MTALAB software, large amounts of sample data are adopted to train and optimize the BP neural network model structure, and to improve the evaluating model accuracy. The validation results indicate that the normalized mean square error of the model reaches -36 dB, and the evaluation error is small.

Key words: vehicle-mounted communication equipment, communication performance, BP neural network, communication distance, evaluation model, model training, NMSE, evaluation accuracy

中图分类号:

TN92

孟晓姣,张世巍,李小健,李敏玥,宋丙鑫,路宏敏. 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,LI Minyue,SONG Bingxin,LU Hongmin. An Evaluation Method of Vehicle-Mounted Communication Equipment Performance Based on BP Neural Network[J]. Electronic Science and Technology, 2021, 34(5): 24-28.

图/表 8

图1

图2

图3

图4

图5

图6

表1

图7

参考文献 17

[1]	路宏敏, 余志勇, 李万玉. 工程电磁兼容[M].3版. 西安: 西安电子科技大学出版社, 2019.
	Lu Hongmin, Yu Zhiyong, Li Wanyu. Engineering electromagnetic compatibility[M].3rd ed. Xi’an: Xidian University Press, 2019.
[2]	Zhou P, Lü Y H, Chen Z H. System-level EMC assessment for military vehicular communication systems based on a modified four-level assessment model[J]. China Communications, 2018,15(8):39-53.
[3]	田锦, 谢拥军, 辛红全, 等. 复杂系统电磁兼容评估的改进TOPSIS方法[J]. 电子学报, 2013,41(1):105-109.
	Tian Jin, Xie Yongjun, Xin Hongquan, et al. A synthetical EMC evaluation method for a complicated system based on a novel TOPSIS approach[J]. Acta Electronica Sinica, 2013,41(1):105-109.
[4]	郭艳飞, 任雪桂, 鞠力, 等. 基于层次分析法的综合能源系统能效评估方法研究及应用[J]. 电力科学与技术学报, 2018,33(4):121-128.
	Guo Yanfei, Ren Xuegui, Ju Li, et al. The comprehensive efficiency evaluation method for integrated energy system based on AHP[J]. Journal of Electric Power Science and Technology, 2018,33(4):121-128.
[5]	成科平. 基于改进ADC模型的电子对抗系统作战效能评估[J]. 电子科技, 2013,26(1):30-33.
	Cheng Keping. The combat-effectiveness appraisal of ECM system based on the modified ADC model[J]. Electronic Science and Technology, 2013,26(1):30-33.
[6]	Rumelhart D E, Hinton G E, Williams R J. Learning representations by back propagating errors[J]. Nature, 1986,323(6088):533-536. doi: 10.1038/323533a0
[7]	Cui K, Jing X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing and Applications, 2019,31(12):8205-8215. doi: 10.1007/s00521-018-3902-6
[8]	Ma C, Zhao L, Mei X S, et al. Thermal error compensation of high-speed spindle system based on a modified BP neural network[J]. The International Journal of Advanced Manufacturing Technology, 2017,89(9-12):3071-3085. doi: 10.1007/s00170-016-9254-4
[9]	曾泉, 谭北海. 基于SVM和BP神经网络的车牌识别系统[J]. 电子科技, 2016,29(1):98-101.
	Zeng Quan, Tan Beihai. Plate recognition system based on SVM and BP neural network[J]. Electronic Science and Technology, 2016,29(1):98-101.
[10]	Shan Y, Liu Y J, Guan F J. The application of BP neural network algorithm in optical fiber fault diagnosis[C]. Guiyang:The Fourteenth International Symposium on Distributed Computing and Applications for Business Engineering and Science, 2015.
[11]	陈邦媛. 射频通信电路[M]. 北京: 科学出版社, 2002.
	Chen Bangyuan. RF communication circuit[M]. Beijing: Science Press, 2002.
[12]	焦李成. 神经网络系统理论[M]. 西安: 西安电子科技大学出版社, 1996.
	Jiao Licheng. Neural network system theory[M]. Xi’an: Xidian University Press, 1996.
[13]	呙润华, 苏婷婷, 马晓伟. BP神经网络联合模板匹配的车牌识别系统[J]. 清华大学学报(自然科学版), 2013,53(9):1221-1226.
	Guo Runhua, Su Tingting, Ma Xiaowei. BP neural network combined with template matching for license plate recognition system[J]. Journal of Tsinghua University (Science and Technology), 2013,53(9):1221-1226.
[14]	Fu J X, Huang L F, Yao Y. Application of BP neural network in wireless network security evaluation[C]. Beijing:IEEE International Conference on Wireless Communications,Networking and Information Security, 2010.
[15]	Yang A M, Zhuansun Y, Liu C S, et al. Design of intrusion detection system for internet of things based on improved BP neural network[J]. Computers, Networks and Communications, 2019,7(19):106043-106052.
[16]	Choudhary A, Rishi R. Improving the character recognition efficiency of feed forward BP neural network[J]. International Journal of Computer Science & Information Technology, 2011,3(1):85-95.
[17]	Peter H. Understanding normalized mean squared error in power amplifier linearization[J]. IEEE Microwave and Wireless Components Letters, 2018,28(11):1047-1049. doi: 10.1109/LMWC.2018.2869299

样本	样本数据	模型输出	误差
1	0.317	0.314 4	0.002 6
2	0.235	0.230 2	0.004 8
3	0.254	0.273 4	0.019 4
4	0.441	0.439 9	0.001 1
5	0.414	0.410 6	0.003 4
6	0.493	0.490 4	0.002 6
7	0.539	0.540 0	0.001 0
8	0.360	0.361 0	0.001 0
9	0.426	0.430 1	0.004 1
10	0.677	0.680 1	0.003 1

一种基于BP神经网络的车载通信设备性能评估方法

An Evaluation Method of Vehicle-Mounted Communication Equipment Performance Based on BP Neural Network

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 17

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	宋丙鑫,路宏敏,李敏玥,孟晓姣,万健鹏. 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.
[2]	朱轶峰. 基于WiFi-BP的室内定位算法[J]. 电子科技, 2020, 33(8): 74-79.
[3]	张长青,杨楠. 基于混合神经网络的车牌字符识别技术[J]. 电子科技, 2019, 32(9): 51-54.
[4]	管胜,阮方鸣,周奎,苏明,王珩,邓迪,李佳. BP神经网络预测电极速度影响放电参数分析[J]. 电子科技, 2019, 32(6): 43-48.
[5]	王康,邬春学. 基于繁忙因子的WSN自适应双簇头分簇算法研究[J]. 电子科技, 2019, 32(2): 56-60.
[6]	杨加一. 基于BP神经网络的导弹故障自动诊断研究[J]. , 2018, 31(4): 48-.
[7]	魏爽. 基于BP神经网络的嘴型分类算法[J]. , 2016, 29(8): 89-.
[8]	金焱飞，张会林，张松，史超然，李荣伟. 基于GABPNN的MPPT控制方法与P&O的比较[J]. , 2016, 29(8): 145-.
[9]	邓玉梅. 基于蚁群优化的BP神经网络目标威胁估计方法[J]. , 2016, 29(7): 33-.
[10]	闫驰. 基于PSO-BP神经网络的无线传感器网络定位算法[J]. , 2016, 29(4): 56-.
[11]	曾泉,谭北海. 基于SVM和BP神经网络的车牌识别系统[J]. , 2016, 29(1): 98-.
[12]	苏宇逍. 基于GA的BP神经网络在多目标优化中的应用[J]. , 2015, 28(6): 51-.
[13]	高丽媛,董甲. 基于改进BP神经网络的洪峰预测模型[J]. , 2015, 28(3): 41-.
[14]	邹孔雨,佟国香. PM2.5测量系统中改进神经网络控制算法优化补偿[J]. , 2015, 27(11): 25-.
[15]	邹孔雨,佟国香. PM2.5测量系统中改进神经网络控制算法优化补偿[J]. , 2015, 28(11): 25-.