陈俊,陶礼兵,梁云,范晓舟,张梓平,刘子惠
CHEN Jun,TAO Libing,LIANG Yun,FAN Xiaozhou,ZHANG Ziping,LIU Zihui

• 1:国网浙江省电力有限公司衢州供电公司
• 2:中国电力科学研究院有限公司
• 3:河北省输变电设备安全防御重点实验室(华北电力大学)

摘要(Abstract)：

架空输电线路近线区域的施工活动是机械外破事件的主要隐患，为应对其难以实时监测的难题，提出一种基于DAS（分布式声波传感）技术的架空输电线路近区施工活动监测方案。该方案通过复用OPGW（光纤复合架空地线）中的光纤，捕捉架空输电线路近区施工活动产生的声音信号，从而实现机械外破隐患监测。首先开展输电线路施工活动模拟试验，探究OPGW内光纤实测信号规律，提出基于信号帧能量与谱峭度的双阈值声音信号检测方案，实现异常声学信号捕捉；随后通过提取异常信号的MFCC（梅尔频率倒谱系数）参数构建特征向量，并在VGG16-BN模型架构中引入空间注意力机制，准确识别施工机械声音信号。实验表明，针对6种常见施工机械信号，所提分布式声学检测方案识别准确率达95.33%，为架空输电线路机械外破隐患监测提供了一种新的技术方案。
Construction operations in the vicinity of overhead transmission lines are the primary hidden risk for mechanical external damage. To overcome the challenge of real-time monitoring, a monitoring method based on distributed acoustic sensing(DAS) is proposed. This method leverages the optical fibers in optical fiber composite ground wires(OPGW) to capture acoustic signals generated by nearby construction operations, thereby monitoring mechanical external damage risks. First, simulation experiments of transmission line construction operations were conducted to investigate the signal patterns measured in OPGW fibers. A dual-threshold detection method, based on signal frame energy and spectral kurtosis, was then developed to capture abnormal acoustic signals. Subsequently, Mel-frequency cepstral coefficient(MFCC) parameters were extracted from these abnormal signals to construct feature vectors. A spatial attention mechanism was introduced into the VGG16-BN model architecture to accurately identify sound signals of construction machinery. Experimental results show that, for six common sound signals of construction machinery, the proposed distributed acoustic detection method achieves an identification accuracy of 95.33%. This provides a new technical approach for monitoring mechanical external damage risks in overhead transmission lines.

关键词(KeyWords)： 架空输电线路;分布式声波传感;机械外破;施工活动;深度学习
overhead transmission lines;distributed acoustic sensing;mechanical external damage;construction operations;deep learning

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金联合基金（U24B2095）;; 国网浙江省电力有限公司科技项目（5211QZ250005）

作者(Author): 陈俊,陶礼兵,梁云,范晓舟,张梓平,刘子惠
CHEN Jun,TAO Libing,LIANG Yun,FAN Xiaozhou,ZHANG Ziping,LIU Zihui

DOI: 10.19585/j.zjdl.202605012

参考文献(References)：

• [1]陆佳政，周特军，吴传平，等.某省级电网220 kV及以上输电线路故障统计与分析[J].高电压技术，2016,42(1):200-207.LU Jiazheng,ZHOU Tejun,WU Chuanping,et al. Fault statistics and analysis of 220 kV and above power transmission line in province-level power grid[J].High Voltage Engineering,2016,42(1):200-207.
• [2]GONG Y L,CHEN H Y,ZHAO S S,et al.CPF detector for object detection of transmission line external force damage[J].IEEE Sensors Journal,2025,25(7):11471-11479.
• [3]刘波.面向复杂输电线路区域的外破隐患识别[D].济南：山东大学，2022.LIU Bo.Wire region-oriented hazard detection in the complex transmission line[D]. Jinan:Shandong University,2022.
• [4]刘恒.基于电力视觉理解的输电线路外力破坏隐患精细化辨识方法研究[D].西安：西安理工大学，2024.LIU Heng. Research on refined identification method of transmission line external damage hidden dangers based on power visual understanding[D].Xi'an:Xi'an University of Technology,2024.
• [5]杜迎春，王少杰，侯婷婷，等.基于多尺度序列视觉特征融合模型的输电线路防外破红外感应预警技术[J].电子器件，2025,48(2):426-431.DU Yingchun,WANG Shaojie,HOU Tingting,et al.Infrared induction early warning technology for transmission line breaking prevention based on multi-scale sequence visual feature fusion model[J].Chinese Journal of Electron Devices,2025,48(2):426-431.
• [6]张延响，陈健琦，刘强，等.基于深度学习与毫米波雷达的输电线路防外破系统研究[J].电力大数据，2024(5):89-96.ZHANG Yanxiang,CHEN Jianqi,LIU Qiang,et al. Research on transmission line anti-external damage system based on deep learning and millimeter-wave radar[J].Power Systems and Big Data,2024(5):89-96.
• [7]廖如超，刘高，汪皓，等.输电线路外破隐患空间距离三维点云测量方法[J].沈阳工业大学学报，2025,47(1):14-20.LIAO Ruchao,LIU Gao,WANG Hao,et al. 3D point cloud measurement method for space distance of hidden dangers from external damage to transmission lines[J].Journal of Shenyang University of Technology,2025,47(1):14-20.
• [8]刘敏，陈明，武明虎，等.GAE-YOLO：全局感知增强的输电线路外破隐患目标检测方法[J].仪器仪表学报，2025,46(2):267-278.LIU Min,CHEN Ming,WU Minghu,et al.GAE-YOLO:Global awareness enhanced method for detecting external force damage in power transmission lines[J].Chinese Journal of Scientific Instrument,2025,46(2):267-278.
• [9]龙乐云，周腊吾，刘淑琴，等.改进YOLOv5算法下的输电线路外破隐患目标检测研究[J].电子测量与仪器学报，2022,36(11):245-253.LONG Leyun,ZHOU Lawu,LIU Shuqin,et al.Identification of hidden damage targets by external forces based on domain adaptation and attention mechanism[J].Journal of Electronic Measurement and Instrumentation,2022,36(11):245-253.
• [10]魏贤哲，卢武，赵文彬，等.基于改进Mask R-CNN的输电线路防外破目标检测方法研究[J].电力系统保护与控制，2021,49(23):155-162.WEI Xianzhe,LU Wu,ZHAO Wenbin,et al.Target detection method for external damage of a transmission line based on an improved Mask R-CNN algorithm[J].Power System Protection and Control,2021,49(23):155-162.
• [11]谢修成.面向输电线的非接触式吊车防碰撞检测方法研究[D].南京：南京信息工程大学，2023.
• [12]沈聪，冯晨，邴超，等.基于OPGW技术的输电线路外破灾害监测系统设计[J].自动化技术与应用，2024,43(6):181-184.SHEN Cong,FENG Chen,BING Chao,et al.Design of monitoring system for outbreaking disaster of transmission line based on OPGW technology[J].Techniques of Automation and Applications,2024,43(6):181-184.
• [13]李晓楠.声纹识别算法在光纤分布式声波传感系统信号识别中的应用研究[D].成都：电子科技大学，2025.LI Xiaonan. Research on the Application of Voiceprint RecognitionAlgorithm in Signal Recognition of Fiber OpticDistributed Acoustic Sensing Systems[D]. Chengdu:University of Electronic Science and Technology of China,2025.
• [14]LIU M,LI Z,SHENG G H,et al.A deep learning algorithm for power transformer voiceprint recognition in strong-noise and small-sample scenarios[J].IEEE Transactions on Instrumentation and Measurement,2025,74:3540911.
• [15]曹力潭，魏华兵，黄智，等.基于LSTM神经网络的电抗器故障声纹识别方法[J].浙江电力，2023,42(4):114-120.CAO Litan,WEI Huabing,HUANG Zhi,et al.Research on voiceprint recognition of reactor fault based on LSTM neural network[J].Zhejiang Electric Power,2023,42(4):114-120.
• [16]林浩凡，张世杰，赵建永，等.基于多试验工况的低频变压器声纹特性分析[J].浙江电力，2025,44(6):100-108.LIN Haofan,ZHANG Shijie,ZHAO Jianyong,et al.Analysis of acoustic fingerprint characteristics of a lowfrequency transformer underdiverse test conditions[J].Zhejiang Electric Power,2025,44(6):100-108.