首页 > 论文 > 激光与光电子学进展 > 56卷 > 2期(pp:21205--1)

基于小波包分析和支持向量机的光时域反射仪光缆故障识别

Identifying Optical Cable Faults in OTDR Based on Wavelet Packet Analysis and Support Vector Machine

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对传统故障识别方法过程复杂、用时长、准确率低等问题, 提出了一种基于小波包分析和支持向量机的光纤故障自动识别方法。对光时域反射仪采集的数据进行事件点定位, 选择最优基小波和尺度完成事件信号的分解和重构, 提取归一化的小波包能量作为事件信号的特征向量; 建立支持向量机模型, 将特征向量作为输入进行训练和测试, 最终实现故障识别。实验对机载光缆中由连接器引起的反射事件和弯折引起的非反射事件进行二分类测试, 总样本数为2500。实验结果表明, 当训练样本数为1750, 测试样本数为750时, 该方法对机载光纤中反射事件和非反射事件的正确识别率为99%, 耗时3.03 s; 与基于反向传播神经网络的识别方法相比, 准确率提升了2%, 且耗时仅为其1%左右。目前已成功应用于自主研发的机载光缆组件外场检测设备。

Abstract

As traditional fault identification methods typically exhibit considerable processing complexity, are often time-consuming, and display a low degree of precision, a novel approach based on wavelet packet analysis using a support vector machine (SVM) is proposed in this study for the automatic identification of fiber defects in optical time domain reflectometry (OTDR). OTDR is initially used to acquire the original data of the fiber under test (FUT). Further, the event signs are decomposed by the optimal basic wavelet packet after the events are located, and the normalized energy features of the event signs as eigenvectors are extracted as input of training and testing based on the results of signal reconstruction. Finally, the SVM model is built, and fiber defects can be identified with the eigenvector as input. Subsequently, the SVM identification technique is used to obtain effective classification of the events as either reflection events, which are caused by connectors, or as non-reflection events, which are caused by bent events. In this study, two classification tests have been performed on a total of 2500 reflection and non-reflection events in airborne optical cable samples. The experimental results indicate that our method achieves a recognition rate of 99% in 3.03 s when the number of training samples is 1750 and when the number of testing samples is 750. Additionally, the recognition rate is increased by 2% and the recognition time is observed to be only 1% when compared to the previously proposed recognition method that is based on the backpropagation neural network. At present, the proposed method is successfully applied in the field detection equipment of airborne optical cable components independently developed.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN247

DOI:10.3788/lop56.021205

所属栏目:仪器,测量与计量

基金项目:国家自然科学基金(61705033)、教育部中央高校科研业务经费(ZYGX2016J014)

收稿日期:2018-07-20

修改稿日期:2018-07-26

网络出版日期:2018-08-02

作者单位    点击查看

李斌:电子科技大学信息与通信工程学院, 四川 成都 610054
张敏:电子科技大学信息与通信工程学院, 四川 成都 610054
周恒:电子科技大学信息与通信工程学院, 四川 成都 610054
李竣屹:航空工业成都飞机设计研究所, 四川 成都 610091
凌云:电子科技大学信息与通信工程学院, 四川 成都 610054
石林:航空工业成都飞机设计研究所, 四川 成都 610091
邱昆:电子科技大学信息与通信工程学院, 四川 成都 610054

联系人作者:周恒(zhouheng@uestc.edu.cn)

【1】Lu J H. Airborne bus technology research andsummary[J]. Electronic Test, 2017(7): 72-73.
逯计划. 机载总线技术发展研究[J]. 电子测试, 2017(7): 72-73.

【2】Huang X H, Hu Y, Zhang D Y. Testing technique and analysis of PC-OTDR applied on optical fiber linkage of civil aviation aircraft[J]. Journal of Chongqing University of Technology (Natural Science), 2014, 28(2): 106-110.
黄选红, 胡炎, 张德银. 光时域反射法在民航飞机光纤通信系统中的检测技术与分析[J]. 重庆理工大学学报(自然科学), 2014, 28(2): 106-110.

【3】Yang W K. Measuring joint loss with optical time domain reflectometry (five-point method)[J].Optical Fiber & Electric Cable and Their Application, 1984(3): 25-28.
杨文奎. 用光时域反射计测接头损耗(五点法)[J]. 光纤与电缆及其应用技术, 1984(3): 25-28.

【4】Hu Q. Effect of unreal peaks on measurement of fiber splicing loss with ODTR at least square method mode[J]. Optical Communication Technology, 2003, 27(10): 29-30.
胡庆. 在最小二乘法模式下幻峰对OTDR测试光纤接头损耗的影响[J]. 光通信技术, 2003, 27(10): 29-30.

【5】Ma S W. Application of Haar wavelet and least square estimation tofiber monitoring online system[J]. Railway Computer Application, 2007, 16(9): 32-35.
马少伟. Haar小波和最小二乘法在光纤监测系统的应用[J]. 铁路计算机应用, 2007, 16(9): 32-35.

【6】Man X J, Dong Y, He H, et al. Analysis of connection splice events in OTDR data using short Fourier transform method[J]. Chinese Journal of Scientific Instrument, 2010, 31(9): 2121-2125.
满晓晶, 董毅, 何浩, 等. 基于短时傅里叶变换的光时域反射计(OTDR)事件分析[J]. 仪器仪表学报, 2010, 31(9): 2121-2125.

【7】Zhou H S. The application study on fiber monitoring system based on wavelet transform[D]. Beijing: Beijing Jiaotong University, 2008.
周宏晟. 小波变换在光缆监测系统中的研究与应用[D]. 北京: 北京交通大学, 2008.

【8】Liao M M, Chen W. Positioning and detecting of fault points in optical communication cable lines[J]. Study on Optical Communications, 201, 41(1): 26-27.
廖敏敏, 陈伟. 通信光缆线路中故障点的定位与检测[J]. 光通信研究, 2015, 41(1): 26-27.

【9】Kong H. Research on events analysis algorithms in optical time domain reflectometry[D]. Shanghai: Shanghai Jiao Tong University, 2015.
孔衡. 光时域反射的事件分析算法研究[D]. 上海: 上海交通大学, 2015.

【10】Li J. The applied research of OTDR curve analytic technique in optical fiber fault diagnosis[D]. Baoding: North China Electric Power University, 2011.
李俊. OTDR曲线分析技术在光纤故障诊断中的应用研究[D]. 保定: 华北电力大学, 2011.

【11】Zhu X X. Research on rotating machine fault diagnosis and prediction method based on support vector machine[D]. Baoding: North China Electric Power University, 2013.
朱霄珣. 基于支持向量机的旋转机械故障诊断与预测方法研究[D]. 保定: 华北电力大学, 2013.

【12】Zhang J L, Zhao Y. Based on the improved neural network of fiber optic fault monitoring and optimization[J]. Laser Journal, 2016, 37(6): 131-134.
张景璐, 赵妍. 基于改进神经网络的光纤故障监测优化[J]. 激光杂志, 2016, 37(6): 131-134.

【13】Chen C, Xiao Y, Li A D, et al. OTDR events analysis algorithm based on wavelet transform and RBF neural network[J]. Optical Communication Technology, 2017, 41(2): 25-28.
陈诚, 肖逸, 李爱东, 等. 基于RBF神经网络的OTDR小波分析算法[J]. 光通信技术, 2017, 41(2): 25-28.

【14】Shi Q L, Lin J. Correlation analysis method based on wavelet packet decomposition and energy feature extraction[J]. Acoustics and Electronics Engineering, 2010(4): 18-20, 24.
史秋亮, 林江. 基于小波包分解与能量特征提取的相关分析法[J]. 声学与电子工程, 2010(4): 18-20, 24.

【15】Gui Z H, Han F Q. Neural network based on wavelet packet-characteristic entropy for fault diagnosis of draft tube[J]. Proceedings of the CSEE, 2005, 25(4): 99-102.
桂中华, 韩凤琴. 小波包特征熵神经网络在尾水管故障诊断中的应用[J]. 中国电机工程学报, 2005, 25(4): 99-102.

【16】Wang B J, Pi S H, Sun Q, et al. Improved wavelet packet classification algorithm for vibrational intrusions in distributed fiber-optic monitoring systems[J]. Optical Engineering, 2015, 54(5): 055104.

【17】Li Q H. Introduction to sonar signal processing[M]. Beijing: Science Press, 2012
李启虎. 声呐信号处理引论[M]. 北京: 科学出版社, 2012.

【18】Zeng Y, Wu H L. The energy characteristics on the frequency bands extracted eased on the wavelet packet and intelligent diagnosis[J]. Computing Technology & Automation, 2008, 27(4): 115-117.
曾芸, 武和雷. 基于小波包的频带能量特征提取及智能诊断[J]. 计算技术与自动化, 2008, 27(4): 115-117.

【19】Gu X H, Zhang G X, Hou D B, et al. Detection of water pipe leak location using wavelet packet decomposition and power feature extraction[J]. Journal of Sichuan University (Engineering Science Edition), 2005, 37(6): 145-149.
谷小红, 张光新, 侯迪波, 等. 小波包分解与能量特征提取相结合的水管泄漏位置的确定[J]. 四川大学学报(工程科学版), 2005, 37(6): 145-149.

【20】Wang S T, Zhang C X, Wang Z F, et al. Application of least squares support vector machine in fluorescence detection of sodium methylparaben[J]. Laser & Optoelectronics Progress, 2017, 54(7): 073001.
王书涛, 张彩霞, 王志芳, 等. 最小二乘支持向量机在对羟基苯甲酸甲酯钠荧光检测中的应用[J]. 激光与光电子学进展, 2017, 54(7): 073001.

【21】Zhang Y J, Wang H M, Fu X H, et al. Identification of steel plate damage position based on particle swarm support vector machine[J]. Chinese Journal of Lasers, 2017, 44(10): 1006006.
张燕君, 王会敏, 付兴虎, 等. 基于粒子群支持向量机的钢板损伤位置识别[J]. 中国激光, 2017, 44(10): 1006006.

【22】Li D, Zhou K F, Sun W D, et al. Application of BP neural network and SVM in mine environmental assessment[J]. Arid Land Geography, 2015, 38(1): 128-134.
李东, 周可法, 孙卫东, 等. BP神经网络和SVM在矿山环境评价中的应用分析[J]. 干旱区地理, 2015, 38(1): 128-134.

【23】Zhan Y, Cheng H Z, Ding Y F, et al. S-transform-based classification of power quality disturbance signals by support vector machines[J]. Proceedings of the CSEE, 2005. 25(4): 51-56.
占勇, 程浩忠, 丁屹峰, 等. 基于S变换的电能质量扰动支持向量机分类识别[J]. 中国电机工程学报, 2005, 25(4): 51-56.

【24】Li Y M. The study of BP learning algorithm of artificial neural network and its application in face recognition[D]. Jinan: Shandong University, 2012.
李永明. 人工神经网络BP学习算法的研究及在人脸识别中的应用[D]. 济南: 山东大学, 2012.

【25】Han L. The Classification model of RS images based on artificial neural network: MLP[J]. Bulletin of Surveying & Mapping, 2004(9): 29-30.
韩玲. 基于人工神经网络: 多层感知器(MLP)的遥感影像分类模型[J]. 测绘通报, 2004(9): 29-30.

【26】Ha Z Q, Yu H. Neural network control[M]. Xi′an: Xidian University Press, 2009.
哈宗泉, 喻晗. 神经网络控制[M]. 西安: 西安电子科技大学出版社, 2009.

引用该论文

Li Bin,Zhang Min,Zhou Heng,Li Junyi,Ling Yun,Shi Lin,Qiu Kun. Identifying Optical Cable Faults in OTDR Based on Wavelet Packet Analysis and Support Vector Machine[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021205

李斌,张敏,周恒,李竣屹,凌云,石林,邱昆. 基于小波包分析和支持向量机的光时域反射仪光缆故障识别[J]. 激光与光电子学进展, 2019, 56(2): 021205

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF