Feature Extraction and Identification in Distributed Optical-Fiber Vibration Sensing System for Oil Pipeline Safety Monitoring

查看全文 作　　者：Huijuan [1]WU;Ya [1]QIAN;Wei [1]ZHANG;Chenghao [1]TANG 机构地区：[1]Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Scienceand Technology of China, Chengdu, 611731, China 出　　处：《Photonic Sensors》索引2017年第7卷第4期,共6页 基　　金：The authors gratefully acknowledge the supports provided for this research by Youth Foundation (Grant No. 61301275), Major Instrument Special Program (Grant No. 41527805), the Major Program (Grant No. 61290312) of the National Science Foundation of China (NSFC), and the fund of State Grid Corporation of China: Research on distributed multi-parameter sensing and measurement control technology for electric power optical fiber communication networks (Grant No. 5455HT160014). This work is also supported by Program for Changjiang Scholars and Innovative Research Team in University (PCSIRT, IRT1218) and the 111 Project (B14039). 摘　　要：察觉到的分布式的光纤维的颤动(DOVS ) 的高敏感系统基于阶段敏感光时间域反射计(-OTDR) 技术也在真实应用程序引进高讨厌的东西警报率(NAR ) 。在这份报纸,小浪分解(WD ) 和小浪包分解(WPD ) 的特征抽取方法比较地为三个典型现场测试信号被学习,并且一个人工的神经网络(ANN ) 为事件鉴定被造。比较结果证明 WPD 监视的油管道安全地为 DOVS 信号分析和鉴定比 WD 有点好表现。鉴定率能被改进直到 94.4% ,并且讨厌的东西警报率能有效地被控制为有小浪包精力分发特征的鉴定网络象 5.6% 一样低。 关 键 词：分布式光纤 事件识别 特征提取 安全监测 传感系统 输油管道 振动 人工神经网络