矿用5G通信信号传输的干扰监测技术

张立亚; 马征; 郝博南; 李标

doi:10.13272/j.issn.1671-251x.204090054

矿用5G通信信号传输的干扰监测技术

张立亚^{1, 2, 3, 4,},
马征^{1, 2, 3, 4},
郝博南^{1, 2, 3, 4},
李标^{1, 2, 3, 4}

1.
煤炭科学技术研究院有限公司，北京　100013
2.
煤炭智能开采与岩层控制全国重点实验室，北京　100013
3.
煤炭行业煤矿应急救援及矿井通信工程研究中心，北京　100013
4.
北京市煤矿安全工程技术研究中心，北京　100013

基金项目: 工业和信息化部2024年工业互联网创新发展工程−工业5G轻量化融合终端项目（TC240AAKM-132）；天地科技股份有限公司科技创新创业资金专项项目（2024-TD-ZD015-01，2024-TD-ZD015-03）。

详细信息

作者简介:
张立亚（1985—），男，河北定州人，研究员，博士，主要从事矿井通信技术与智能矿山技术方面的研究工作，E-mail：zhangliya@ccrise.cn

中图分类号: TD655
计量
- 文章访问数: 369
- HTML全文浏览量: 25
- PDF下载量: 13
出版历程
- 收稿日期: 2024-09-13
- 修回日期: 2024-11-22
- 刊出日期: 2024-11-24

Interference monitoring technology for mine-used 5G communication signal transmission

ZHANG Liya^{1, 2, 3, 4,},
MA Zheng^{1, 2, 3, 4},
HAO Bonan^{1, 2, 3, 4},
LI Biao^{1, 2, 3, 4}

1.
CCTEG China Coal Research Institute, Beijing 100013, China
2.
State Key Laboratory of Intelligent Coal Mining and Strata Control, Beijing 100013, China
3.
Coal Industry Mine Emergency Rescue and Mine Communication Engineering Research Center, Beijing 100013, China
4.
Beijing Engineering and Research Center of Mine Safe, Beijing 100013, China

摘要

摘要:
相比现有的干扰抑制技术（自适应滤技术、自适应干扰对消技术），盲源分离技术能够分离混合在一起的多个信号，计算复杂度低，鲁棒性强。但盲源分离技术难以全面覆盖井下复杂多变的干扰源，同时缺乏对处理后信号成分的自动分析与评估机制，不仅限制了通信效率的提升，还可能因干扰残留而引发安全隐患。针对上述问题，提出了一种基于神经网络的矿用5G通信信号传输干扰监测抑制方法。通过分析井下主运输大巷、综采工作面和变电所等区域的干扰源特点，指出毛刺干扰及串扰信号的抑制和处理是5G抗干扰问题的关键。采用盲源分离技术初步分离矿用5G通信信号中的干扰成分，利用神经网络对分离后的信号进行特征提取及深度分析，精准识别并量化其中残留的干扰信号，一旦监测到干扰信号超出预设阈值，将自动触发新一轮的干扰抑制流程，形成迭代优化的闭环控制。实验结果表明：① 在100 MHz全带宽发送的环境中，使用矿用5G通信信号干扰监测抑制方法能够对毛刺干扰与串扰信号实现13 dB的干扰抑制增益，比使用盲源分离干扰抑制方法效果提升约117%及86%。② 矿用5G通信信号干扰监测抑制方法较盲源分离等传统干扰抑制技术，信噪比平均提升了15.56%，误码率平均降低了21.88%，能够显著提升信号质量。
- 矿用5G /
- 矿用通信 /
- 干扰抑制 /
- 干扰监测 /
- 盲源分离 /
- 神经网络 /
- 毛刺干扰 /
- 串扰信号 /
- Transformer
Abstract:
Compared to conventional interference suppression techniques, such as adaptive filtering and adaptive interference cancellation, blind source separation (BSS) offers the advantage of separating multiple mixed signals with lower computational complexity and higher robustness. However, BSS has limitations in addressing the complex and dynamic interference sources found in underground mining environments. It also lacks automated mechanisms for analyzing and evaluating processed signal components, which not only hampers communication efficiency but may also lead to safety risks due to residual interference. To overcome these challenges, this study proposed a neural network-based interference monitoring and suppression method tailored for mine-used 5G communication signal transmission. By analyzing the characteristics of interference sources in key areas such as main haulage roadways, fully mechanized mining faces, and substations, the study identified the suppression and mitigation of spike interference and crosstalk signals as critical for 5G anti-interference performance. The proposed method initially employed BSS for the preliminary separation of interference components in mine-used 5G communication signals. It then leveraged a neural network for feature extraction and deep analysis of the separated signals, enabling precise identification and quantification of residual interference. If the monitored interference signal exceeded a preset threshold, the system automatically triggered a new round of suppression, forming an iterative and optimized closed-loop control process. Experimental results revealed that: In a 100 MHz full-bandwidth transmission environment, the proposed method achieved a suppression gain of 13 dB for both spike interference and crosstalk signals, showing improvements of approximately 117% and 86%, respectively, over BSS-based interference suppression alone. Compared to traditional techniques, such as BSS, the proposed method enhanced the signal-to-noise ratio (SNR) by an average of 15.56% and reduced the bit error rate (BER) by an average of 21.88%, which could significantly improve signal quality.
- mine-used 5G /
- mining communication /
- interference suppression /
- interference monitoring /
- blind source separation /
- neural network /
- spike interference /
- crosstalk signals /
- Transformer

HTML全文

图 1 井下巷道模型

Figure 1. Underground roadway model

下载: 全尺寸图片幻灯片

图 2 综采工作面设备

Figure 2. Fully mechanized mining face equipment

下载: 全尺寸图片幻灯片

图 3 盲源分离原理

Figure 3. Principle of blind source separation

下载: 全尺寸图片幻灯片

图 4 矿用5G通信信号传输干扰抑制方法的干扰监测处理流程

Figure 4. Interference monitoring processing workflow of interference suppression method for mine-used 5G communication signals

下载: 全尺寸图片幻灯片

图 5 矿用5G通信信号干扰监测的神经网络处理流程

Figure 5. Neural network-based interference monitoring processing workflow for mine-used 5G communication signals

下载: 全尺寸图片幻灯片

图 6 自注意力机制结构

Figure 6. Self-attention mechanism structure

下载: 全尺寸图片幻灯片

图 7 实验测试部署

Figure 7. Experimental setup

下载: 全尺寸图片幻灯片

图 8 毛刺干扰信号抑制对比

Figure 8. Comparison of spike interference signal suppression

下载: 全尺寸图片幻灯片

图 9 串扰信号抑制对比

Figure 9. Comparison of crosstalk signal suppression

下载: 全尺寸图片幻灯片

表 1 信号质量分析结果

Table 1 Signal quality analysis results

方法	综采工作面		井下变电所		主运输大巷
方法	信噪比/dB	误码率	信噪比/dB	误码率	信噪比/dB	误码率
盲源分离干扰抑制	30	0.12	29	0.09	31	0.11
干扰监测抑制（本文方法）	36	0.08	33	0.08	35	0.09
基于小波变换的局部放电信号干扰抑制方法	19	0.25	21	0.23	23	0.24
最小二乘均衡器	23	0.20	23	0.17	25	0.18
最小均方误差均衡器	28	0.16	27	0.13	28	0.16

下载: 导出CSV

参考文献(22)

[1]	孙继平. 煤矿智能化与矿用5G[J]. 工矿自动化,2020,46(8):1-7. SUN Jiping. Coal mine intelligence and mine-used 5G[J]. Industry and Mine Automation,2020,46(8):1-7.
[2]	孙继平. 煤矿智能化与矿用5G和网络硬切片技术[J]. 工矿自动化,2021,47(8):1-6. SUN Jiping. Coal mine intelligence,mine 5G and network hard slicing technology[J]. Industry and Mine Automation,2021,47(8):1-6.
[3]	李晨鑫. 煤矿用5G关键技术研究现状与发展方向[J]. 工矿自动化,2024,50(7):79-88. LI Chenxin. Research status and development direction of 5G key technologies for coal mines[J]. Journal of Mine Automation,2024,50(7):79-88.
[4]	康辉,窦文章,文志成. 技术变革视角下移动通信代内创新和代际演进及未来发展展望[J]. 创新科技,2023,23(4):81-92. KANG Hui,DOU Wenzhang,WEN Zhicheng. Intra-generation innovation and inter-generation evolution of mobile communication and its future development prospects in the perspective of technological change[J]. Innovation Science and Technology,2023,23(4):81-92.
[5]	王子陵,高晓成,杜胜利,等. 矿用F5G架构的智能矿井建设[J]. 有色金属工程,2024,14(10):170. WANG Ziling,GAO Xiaocheng,DU Shengli,et al. Intelligent mine construction based on F5G architecture for mining[J]. Nonferrous Metals Engineering,2024,14(10):170.
[6]	徐天河,王森,代培培. UWB/INS紧组合变分贝叶斯自适应滤波算法[J/OL]. 导航定位学报:1-12[2024-09-21]. https://kns.cnki.net/kcms/detail/10.1096.P.20241121.1557.002.html. XU Tianhe,WANG Sen,DAI Peipei. UWB/INS tightly coupled integration algorithm based on variational Bayesian adaptive Kalman filter[J/OL]. Journal of Navigation and Positioning:1-12[2024-09-21]. https://kns.cnki.net/kcms/detail/10.1096.P.20241121.1557.002.html.
[7]	刘建成,全厚德,赵宏志,等. 基于迭代变步长LMS的数字域自干扰对消[J]. 电子学报,2016,44(7):1530-1538. DOI: 10.3969/j.issn.0372-2112.2016.07.002 LIU Jiancheng,QUAN Houde,ZHAO Hongzhi,et al. Digital self-interference cancellation based on iterative variable step-size LMS[J]. Acta Electronica Sinica,2016,44(7):1530-1538. DOI: 10.3969/j.issn.0372-2112.2016.07.002
[8]	李哲宇,李亚星,张嘉毫,等. 非合作干扰对消技术中空间分辨率建模与分析[J]. 国防科技大学学报,2024,46(5):45-53. DOI: 10.11887/j.cn.202405006 LI Zheyu,LI Yaxing,ZHANG Jiahao,et al. Modeling and analysis of spatial resolution in noncooperative interference cancellation technique[J]. Journal of National University of Defense Technology,2024,46(5):45-53. DOI: 10.11887/j.cn.202405006
[9]	解元,邹涛,孙为军,等. 面向卷积混叠环境下的盲源分离新方法[J]. 自动化学报,2023,49(5):1062-1072. XIE Yuan,ZOU Tao,SUN Weijun,et al. Novel blind source separation method for convolutive mixed environment[J]. Acta Automatica Sinica,2023,49(5):1062-1072.
[10]	孙玉伟,罗林根,陈敬德,等. 含噪背景下基于盲源分离与NSVDD的断路器机械故障诊断方法[J]. 高电压技术,2022,48(3):1104-1112. SUN Yuwei,LUO Lingen,CHEN Jingde,et al. Mechanical fault diagnosis method of circuit breaker based on blind source separation and NSVDD under noisy background[J]. High Voltage Engineering,2022,48(3):1104-1112.
[11]	冯平兴,张洪波,李文翔. 噪声中的复信号盲源分离算法[J]. 电子技术应用,2022,48(4):67-70,75. FENG Pingxing,ZHANG Hongbo,LI Wenxiang. Blind source separation algorithm for complex signals in noise[J]. Application of Electronic Technique,2022,48(4):67-70,75.
[12]	张延良,张玉,张伟涛. 改进的带参考信号盲源分离算法[J]. 科学技术与工程,2022,22(6):2311-2316. DOI: 10.3969/j.issn.1671-1815.2022.06.021 ZHANG Yanliang,ZHANG Yu,ZHANG Weitao. Improved blind source separation algorithm with reference signal[J]. Science Technology and Engineering,2022,22(6):2311-2316. DOI: 10.3969/j.issn.1671-1815.2022.06.021
[13]	陈明虎, 李程, 涂刚毅, 等. 通信干扰信号分类识别方法综述[J]. 电子信息对抗技术,2024,39(3):86-94. CHEN Minghu, LI Cheng, TU Gangyi, et al. An overview of classification and recognition method of communication jamming signals[J]. Electronic Information Warfare Technology,2024,39(3):86-94.
[14]	张立亚,杨维,李晋豫. 矿用5G通信系统射频能量损耗模型[J]. 华中科技大学学报(自然科学版),2021,49(9):6-10,29. ZHANG Liya,YANG Wei,LI Jinyu. Radio frequency energy loss model of mine 5G communication system[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition),2021,49(9):6-10,29.
[15]	李俊卿,刘静. 结合卷积神经网络和迁移学习的电机轴承故障诊断方法[J]. 华北电力大学学报(自然科学版),2023,50(1):76-83,91. DOI: 10.3969/j.ISSN.1007-2691.2023.01.09 LI Junqing,LIU Jing. Fault diagnosis method of motor bearing based on CNN and transfer learning[J]. Journal of North China Electric Power University (Natural Science Edition),2023,50(1):76-83,91. DOI: 10.3969/j.ISSN.1007-2691.2023.01.09
[16]	周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6):1229-1251. DOI: 10.11897/SP.J.1016.2017.01229 ZHOU Feiyan,JIN Linpeng,DONG Jun. Review of convolutional neural network[J]. Chinese Journal of Computers,2017,40(6):1229-1251. DOI: 10.11897/SP.J.1016.2017.01229
[17]	林景栋,吴欣怡,柴毅,等. 卷积神经网络结构优化综述[J]. 自动化学报,2020,46(1):24-37. LIN Jingdong,WU Xinyi,CHAI Yi,et al. Structure optimization of convolutional neural networks:a survey[J]. Acta Automatica Sinica,2020,46(1):24-37.
[18]	刘赟. ReLU激活函数下卷积神经网络的不同类型噪声增益研究[D]. 南京:南京邮电大学,2023. LIU Yun. Research on different types of noise gains of convolutional neural networks under ReLU activation function[D]. Nanjing:Nanjing University of Posts and Telecommunications,2023.
[19]	靳晶晶,王佩. 基于卷积神经网络的图像识别算法研究[J]. 通信与信息技术,2022(2):76-81. JIN Jingjing,WANG Pei. Research on image recognition algorithm based on convolutional neural network[J]. Communication & Information Technology,2022(2):76-81.
[20]	张立亚. 基于动目标特征提取的矿井目标监测[J]. 煤炭学报,2017,42(增刊2):603-610. ZHANG Liya. Mine target monitoring based on feature extraction of moving target[J]. Journal of China Coal Society,2017,42(S2):603-610.
[21]	张立亚. 全矿井融合通信系统研究[J]. 工矿自动化,2018,44(3):12-16. ZHANG Liya. Research on mine integrated communication system[J]. Industry and Mine Automation,2018,44(3):12-16.
[22]	冯登国,徐静,兰晓. 5G移动通信网络安全研究[J]. 软件学报,2018,29(6):1813-1825. FENG Dengguo,XU Jing,LAN Xiao. Study on 5G mobile communication network security[J]. Journal of Software,2018,29(6):1813-1825.

施引文献(8)

期刊类型引用(6)

1.	张明杰，邓文博，谭志宏，李旭泽，刘操，袁帅. 高位定向钻孔抽采瓦斯搭接部位研究与应用. 煤矿安全. 2024(05): 93-99 . 百度学术
2.	张明杰，邓文博，谭志宏，唐开敏，江山，尚志坚. 煤层顶板裂隙带空间网状结构滤纯甲烷研究. 煤炭科学技术. 2023(S1): 96-103 . 百度学术
3.	张育磊. 高瓦斯煤层群顶板定向长钻孔抽采技术研究. 矿业安全与环保. 2022(01): 59-64 . 百度学术
4.	白刚，杨忠，段会军. 定向高位长钻孔上隅角瓦斯治理技术. 工矿自动化. 2020(03): 84-88 . 本站查看
5.	周银波，黄继磊，王思琪，赵周，许静心，陈亮. 下伏被保护层双重采动影响下覆岩瓦斯富集规律. 工矿自动化. 2020(04): 23-27+33 . 本站查看
6.	闫保永，曹柳，张家贵. 煤层顶板裂隙带瓦斯抽采技术与装备探索. 煤炭科学技术. 2020(10): 60-66 . 百度学术