基于通信光缆振动监测的轨道病害实时预警技术研究  

Research on Real-Time Early Warning Technology for Track Diseases Based on Vibration Monitoring of Communication Optical Cables

作　　者：王建军[1,2] 邹聪聪 李杨 吴宇 时瑾 Wang Jianjun;Zou Congcong;Li Yang;Wu Yu;Shi Jin(School of Civil and Architectural Engineering,Beijing Jiaotong Unviersity,Beijing 100044,China;Engineering Department,China Railway Zhengzhou Group Co.,Ltd.,Zhengzhou 450000,China;Telecommunications Department,China Railway Zhengzhou Group Co.,Ltd.,Zhengzhou 450000,China;School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611730,China)

机构地区：[1]北京交通大学土木建筑工程学院,北京100044 [2]中国铁路郑州局集团有限公司工务部,郑州450000 [3]中国铁路郑州局集团有限公司电务部,郑州450000 [4]电子科技大学信息与通信工程学院,成都611730

出　　处：《微纳电子技术》2025年第1期118-126,共9页Micronanoelectronic Technology

摘　　要：铁路轨道病害的实时监测对于维护铁路基础设施、保障列车运行安全至关重要。采用光纤分布式声波传感(DAS)技术对列车作用于轨道伴行光缆的声振信号进行特征提取,利用贝叶斯优化的支持向量机(SVM)模型建立空吊伤、鱼鳞伤病害数据库,实现对铁路轨道病害在线识别及预警。现场测试结果表明,普速铁路焦柳线王庄站至洛阳北站鱼鳞伤检出准确率为83.33%,空吊伤检出准确率为50%;重载铁路侯月线盘古寺站至磨滩站鱼鳞伤检出准确率为100%,空吊伤检出准确率为72.7%。现场测试结果显示出DAS技术在轨道病害识别方面具有一定的应用及指导意义。Real time monitoring of railway track diseases is crucial for maintaining railway infrastructure and ensuring the safety of train operations.The optical fiber distributed acoustic sensing(DAS)technology was used to extract the features of the acoustic and vibration signals of the train acting on the track accompanying optical cable,Bayesian optimized support vector machine(SVM)model was used to establish a database of hollow suspension damage and fis scale damage diseases, achieving online identification and early warning of railway track diseases.The on-site test results show that the detection accuracy rate of fish scale damages fromWangzhuang station to Luoyang north station on the Jiaoliu line of the ordinary speed railway is83.33%, and the detection accuracy rate of hollow suspension damages is 50%. The detectionaccuracy rate of fish scale damages from Pangu Temple station to Motan station on the Houyueline of the heavy-duty railway is 100%, and the detection accuracy rate of hollow suspensiondamages is 72.7%. The on-site test results show that the DAS technology has certain applicationand guiding significance in track disease identification.

关 键 词：铁路轨道病害监测 信号特征提取 支持向量机(SVM) 空吊伤 鱼鳞伤 

分 类 号：TM93[电气工程—电力电子与电力传动]