基于分布式声阵列的变电站无人机监测系统

肖利君; 宋玉琴

doi:10.13224/j.cnki.jasp.20250350

基于分布式声阵列的变电站无人机监测系统

doi: 10.13224/j.cnki.jasp.20250350

肖利君^1,,
宋玉琴^2,*, ,

1.
湖南工业大学交通与电气工程学院，湖南株洲 412007
2.
湖南工业大学理学院，湖南株洲 412007

基金项目: 湖南省教育厅重点研究项目（24A0419）；湖南省教育厅一般项目（23C0206）

详细信息

作者简介:
肖利君（1980-），女，讲师，硕士，研究方向为语音交互技术、信号处理及其定位应用等。E-mail：xiaolijun@hut.edu.cn

通讯作者:
宋玉琴（1981-），女，副教授，博士，研究方向为数据处理与统计。E-mail：songyuqin@hut.edu.cn

中图分类号: V279
计量
- 文章访问数: 354
- HTML浏览量: 234
- PDF量: 32
- 被引次数: 0
出版历程
- 收稿日期: 2025-07-24
- 网络出版日期: 2025-11-05

Distributed acoustic array-based substation UAV detection system

XIAO Lijun^1
,,
SONG Yuqin^{2,*
, ,}

1.
College of Transportation and Electrical Engineering，Hunan University of Technology，Zhuzhou Hunan 412007，China
2.
College of Science，Hunan University of Technology，Zhuzhou Hunan 412007，China

摘要

摘要:
变电站环境下，基于声信号的无人机监测系统，相比基于光电、无线电等类型信号的无人机探测系统，能以较低的成本实现变电站邻近空域全覆盖而受到了广泛关注。针对变电站电磁环境噪声复杂、空域覆盖要求高等特点，提出一种基于分布式声阵列的无人机监测系统。系统采用双四面体麦克风阵列获取声信号，通过设计500 Hz高通滤波与对数梅尔谱提取算法抑制电流噪声；在此基础上，构建 ResNet-18检测网络，使200 m 范围内无人机检测准确率超过90%、误检率低于4%。针对远距离声信号时延估计不稳定的问题，引入时延连续性判定与异常值剔除策略，并结合最小二乘双曲定位模型，实现实际场景中100 m内无人机定位效果提升。实测结果验证了所提方法的有效性。
- 分布式声阵列 /
- 变电站 /
- 无人机（UAV） /
- 声信号检测 /
- 到达时间差（TDOA）
Abstract:
In substation environments, acoustic-signature-based unmanned aerial vehicle (UAV) detection systems have recently attracted significant attention because, relative to electro-optical or radio-frequency solutions, they can deliver full coverage of the surrounding airspace at substantially lower cost. In view of the complex electromagnetic noise environment and high requirements for spatial coverage in substations, a drone monitoring system based on a distributed acoustic array was proposed. The system employed dual tetrahedral microphone arrays to capture acoustic signals, and a 500 Hz high-pass filter combined with a log-Mel spectrogram extraction algorithm was designed to suppress current-induced noise. On this basis, a ResNet-18 detection network was constructed, achieving a drone detection accuracy exceeding 90% and a false alarm rate below 4% within a 200 m range. To address the instability of time delay estimation for distant acoustic signals, a time delay continuity judgment and outlier rejection strategy was introduced, along with a least-squares hyperbolic localization model, thereby improving the drone localization performance within 100m in practical scenarios. Experimental results verified the effectiveness of the proposed method.
- distributed acoustic array /
- substation /
- unmanned aerial vehicle (UAV) /
- sound signal detection /
- time difference of arrival (TDOA)

HTML

图 1 实际部署图

Figure 1. System deployment diagram

下载: 全尺寸图片幻灯片

图 2 声阵列结构图

Figure 2. Structure of acoustic array

下载: 全尺寸图片幻灯片

图 3 典型无人机声信号时频图

Figure 3. Time-frequency diagram of a typical UAV signal

下载: 全尺寸图片幻灯片

图 4 典型无人机声信号对数梅尔谱

Figure 4. Log-Mel diagram of a typical UAV signal

下载: 全尺寸图片幻灯片

图 5 残差连接块

Figure 5. Residual connection blocks

下载: 全尺寸图片幻灯片

图 6 Resnet18完整结构

Figure 6. Structure of Resnet18

下载: 全尺寸图片幻灯片

图 7 原始定位结果

Figure 7. Original localization results

下载: 全尺寸图片幻灯片

图 8 固定去除一组麦克风之间时延的定位结果

Figure 8. Fixed removal of the positioning result of the delay between a set of microphones

下载: 全尺寸图片幻灯片

图 9 固定去除两组麦克风之间时延的定位结果

Figure 9. Fixed removal of the positioning result of the delay between two sets of microphones

下载: 全尺寸图片幻灯片

图 10 异常值去除及错误估计点滤除结果

Figure 10. Outlier removal and misestimation point filtering localization results

下载: 全尺寸图片幻灯片

图 11 基于高斯先验的定位结果^[20]

Figure 11. Localization results with Gauss prior^[20]

下载: 全尺寸图片幻灯片

表 1 不同距离下Resnet18的正检率

Table 1. Positive detection rate of Resnet18 at different distances

距离/m 正检率/%

50 98.6
50～100 95.4
100～200 80.2

下载: 导出CSV

表 2 不同时间下Resnet18的误检率

Table 2. False detection rate of Resnet18 at different time

时间误检率/%

夜晚 0.2
白天 3.2

下载: 导出CSV

参考文献(26)

[1]	SHI Xiufang, YANG Chaoqun, XIE Weige, et al. Anti-drone system with multiple surveillance technologies: architecture, implementation, and challenges[J]. IEEE Communications Magazine, 2018, 56(4): 68-74. doi: 10.1109/MCOM.2018.1700430
[2]	陈新颖, 盛敏, 李博, 等. 面向6G的无人机通信综述[J]. 电子与信息学报, 2022, 44(3): 781-789. CHEN Xinying, SHENG Min, LI Bo, et al. Survey on unmanned aerial vehicle communications for 6G[J]. Journal of Electronics & Information Technology, 2022, 44(3): 781-789. (in Chinese CHEN Xinying, SHENG Min, LI Bo, et al. Survey on unmanned aerial vehicle communications for 6G[J]. Journal of Electronics & Information Technology, 2022, 44(3): 781-789. (in Chinese)
[3]	KAUFMANN E, BAUERSFELD L, LOQUERCIO A, et al. Champion-level drone racing using deep reinforcement learning[J]. Nature, 2023, 620(7976): 982-987. doi: 10.1038/s41586-023-06419-4
[4]	KUNERTOVA D. The war in Ukraine shows the game-changing effect of drones depends on the game[J]. Bulletin of the Atomic Scientists, 2023, 79(2): 95-102. doi: 10.1080/00963402.2023.2178180
[5]	国务院、中央军委. 无人驾驶航空器飞行管理暂行条例[EB/OL]. (2023-06-28)[2024-12-24]. https://www.gov.cn/zhengce/content/202306/content_6888799.htm The State Council of the People’s Repulic of China, The Central Military Commission of the Comunist Party of China. Interim regulations on the management of unmannedaicraft flights [EB/OL]. (2023-06-28)[2024-12-24]. https://www.gov.cn/zhengce/content/ 202306/content_6888799.htm. (in Chinese The State Council of the People’s Repulic of China, The Central Military Commission of the Comunist Party of China. Interim regulations on the management of unmannedaicraft flights [EB/OL]. (2023-06-28)[2024-12-24]. https://www.gov.cn/zhengce/content/ 202306/content_6888799.htm. (in Chinese)
[6]	任俊宇, 俞宁宁, 周成伟, 等. DroneRFb-DIR: 用于非合作无人机个体识别的射频信号数据集[J]. 电子与信息学报, 2025, 47(3): 573-581. REN Junyu, YU Ningning, ZHOU Chengwei, et al. DroneRFb-DIR: an RF signal dataset for non-cooperative drone individual identification[J]. Journal of Electronics & Information Technology, 2025, 47(3): 573-581. (in Chinese REN Junyu, YU Ningning, ZHOU Chengwei, et al. DroneRFb-DIR: an RF signal dataset for non-cooperative drone individual identification[J]. Journal of Electronics & Information Technology, 2025, 47(3): 573-581. (in Chinese)
[7]	管康萍, 冯正康, 马小艳, 等. 一种基于航迹特征的无人机与飞鸟目标雷达识别方法[J]. 上海航天, 2024, 41(1): 130-136. GUAN Kangping, FENG Zhengkang, MA Xiaoyan, et al. A radar recognition method for UAV and flying bird targets based on track characteristics[J]. Aerospace Shanghai, 2024, 41(1): 130-136. (in Chinese GUAN Kangping, FENG Zhengkang, MA Xiaoyan, et al. A radar recognition method for UAV and flying bird targets based on track characteristics[J]. Aerospace Shanghai, 2024, 41(1): 130-136. (in Chinese)
[8]	马显龙, 郭晨鋆, 曹占国, 等. 基于视频联动的变电站无人机入侵监测技术[J]. 电子设计工程, 2024, 32(23): 89-93. MA Xianlong, GUO Chenyun, CAO Zhanguo, et al. Monitoring technology of the Unmanned Aerial Vehicle intruding substation based on video linkage[J]. Electronic Design Engineering, 2024, 32(23): 89-93. (in Chinese MA Xianlong, GUO Chenyun, CAO Zhanguo, et al. Monitoring technology of the Unmanned Aerial Vehicle intruding substation based on video linkage[J]. Electronic Design Engineering, 2024, 32(23): 89-93. (in Chinese)
[9]	YU Ningning, WU Jiajun, ZHOU Chengwei, et al. SMNet: multi-drone detection and classification via monitoring flight control signals on spectrograms[J]. IEEE Transactions on Cognitive Communications and Networking, 2025, 11(5): 3245-3259. doi: 10.1109/TCCN.2025.3537100
[10]	常先宇. 基于声阵列的无人机检测及定位系统[D]. 杭州: 浙江大学, 2019. CHANG Xianyu. Drone detection and localization using acoustic arrays: algorithm design and implementation[D]. Hangzhou: Zhejiang University, 2019. (in Chinese CHANG Xianyu. Drone detection and localization using acoustic arrays: algorithm design and implementation[D]. Hangzhou: Zhejiang University, 2019. (in Chinese)
[11]	陈鹏, 陈洋, 王威. 无人机声学定位技术综述[J]. 华南理工大学学报(自然科学版), 2022, 50(12): 109-123. CHEN Peng, CHEN Yang, WANG Wei. Review for UAV acoustic positioning[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(12): 109-123. (in Chinese CHEN Peng, CHEN Yang, WANG Wei. Review for UAV acoustic positioning[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(12): 109-123. (in Chinese)
[12]	曹盛. 小型无人机声阵列探测系统设计与实现[D]. 重庆: 重庆理工大学, 2024. CAO Sheng. Design and realisation of acoustic array detection system for small UAVs[D]. Chongqing: Chongqing University of Technology, 2024. (in Chinese CAO Sheng. Design and realisation of acoustic array detection system for small UAVs[D]. Chongqing: Chongqing University of Technology, 2024. (in Chinese)
[13]	DAVIS S, MERMELSTEIN P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1980, 28(4): 357-366. doi: 10.1109/TASSP.1980.1163420
[14]	李广青. 无人机多维度智能识别关键技术研究[D]. 长春: 长春理工大学, 2021. LI Guangqing. Research on key technologies of UAV multidimensional intelligent recognition[D]. Changchun: Changchun University of Science and Technology, 2021. (in Chinese LI Guangqing. Research on key technologies of UAV multidimensional intelligent recognition[D]. Changchun: Changchun University of Science and Technology, 2021. (in Chinese)
[15]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, US: IEEE, 2016: 770-778.
[16]	AL-EMADI S A, AL-ALI A K, MOHAMMED A. Audio-based drone detection and identification using deep learning techniques with dataset enhancement through generative adversarial networks[J]. Sensors, 2021, 21(15): 4953. doi: 10.3390/s21154953
[17]	吴桐. 基于分布式声阵列的无人机检测定位系统[D]. 杭州: 浙江大学, 2022. WU Tong. Drone detection and localization system using distributed acoustic arrays[D]. Hangzhou: Zhejiang University, 2022. (in Chinese WU Tong. Drone detection and localization system using distributed acoustic arrays[D]. Hangzhou: Zhejiang University, 2022. (in Chinese)
[18]	夏伟, 罗明, 赵美霞. 无源时差定位系统最优布站方法研究[J]. 雷达科学与技术, 2020, 18(1): 34-38. XIA Wei, LUO Ming, ZHAO Meixia. Study on optimal station distribution and performance of passive time difference localization system[J]. Radar Science and Technology, 2020, 18(1): 34-38. (in Chinese XIA Wei, LUO Ming, ZHAO Meixia. Study on optimal station distribution and performance of passive time difference localization system[J]. Radar Science and Technology, 2020, 18(1): 34-38. (in Chinese)
[19]	KNAPP C, CARTER G. The generalized correlation method for estimation of time delay[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1976, 24(4): 320-327. doi: 10.1109/TASSP.1976.1162830
[20]	SHI Zhiguo, CHANG Xianyu, YANG Chaoqun, et al. An acoustic-based surveillance system for amateur drones detection and localization[J]. IEEE Transactions on Vehicular Technology, 2020, 69(3): 2731-2739. doi: 10.1109/TVT.2020.2964110
[21]	蔡卫平, 黄印君, 陆泽橼. 基于分布式麦克风阵列的声源定位算法[J]. 计算机应用与软件, 2014, 31(5): 132-135. CAI Weiping, HUANG Yinjun, LU Zeyuan. Sound source localisation algorithm based on distributed microphone arrays[J]. Computer Applications and Software, 2014, 31(5): 132-135. (in Chinese CAI Weiping, HUANG Yinjun, LU Zeyuan. Sound source localisation algorithm based on distributed microphone arrays[J]. Computer Applications and Software, 2014, 31(5): 132-135. (in Chinese)
[22]	卢艳美. 基于分布式麦克风阵列的声源定位方法研究[D]. 辽宁大连: 大连理工大学, 2017. LU Yanmei. Research on sound source localization based on distributed microphone array[D]. Dalian Liaoning: Dalian University of Technology, 2017. (in Chinese LU Yanmei. Research on sound source localization based on distributed microphone array[D]. Dalian Liaoning: Dalian University of Technology, 2017. (in Chinese)
[23]	王舒文. 分布式麦克风阵列定位方法研究[D]. 辽宁大连: 大连理工大学, 2013. WANG Shuwen. Study on distributed microphone array localization method[D]. Dalian Liaoning: Dalian University of Technology, 2013. (in Chinese WANG Shuwen. Study on distributed microphone array localization method[D]. Dalian Liaoning: Dalian University of Technology, 2013. (in Chinese)
[24]	CHAN Y T, HO K C. A simple and efficient estimator for hyperbolic location[J]. IEEE Transactions on Signal Processing, 1994, 42(8): 1905-1915. doi: 10.1109/78.301830
[25]	王同庆. 基于小型麦克风阵列的旋翼式无人机检测与定位系统研究[D]. 南京: 南京理工大学, 2023. WANG Tongqing. Research on detection and localization system for rotor-type UAVs based on a small microphone array. Nanjing: Nanjing University of Science and Technology, 2023. (in Chinese WANG Tongqing. Research on detection and localization system for rotor-type UAVs based on a small microphone array. Nanjing: Nanjing University of Science and Technology, 2023. (in Chinese)
[26]	SEDUNOV A, SALLOUM H, SUTIN A, et al. UAV passive acoustic detection[C]//Proceedings of IEEE International Symposium on Technologies for Homeland Security. Piscataway, US: IEEE, 2018: 1-6.