基于支持向量机的分布式光纤泄漏检测定位系统及实验分析

黄悦, 王强, 韩玲娟, 朱俊

黄悦, 王强, 韩玲娟, 朱俊. 基于支持向量机的分布式光纤泄漏检测定位系统及实验分析[J]. 应用光学, 2015, 36(3): 424-429. DOI: 10.5768/JAO201536.0303004
引用本文: 黄悦, 王强, 韩玲娟, 朱俊. 基于支持向量机的分布式光纤泄漏检测定位系统及实验分析[J]. 应用光学, 2015, 36(3): 424-429. DOI: 10.5768/JAO201536.0303004
shu
Huang Yue, Wang Qiang, Han Ling-juan, Zhu Jun. Support vector machine based distributed optical fiber leakage detection system and experimental analysis[J]. Journal of Applied Optics, 2015, 36(3): 424-429. DOI: 10.5768/JAO201536.0303004
Citation: Huang Yue, Wang Qiang, Han Ling-juan, Zhu Jun. Support vector machine based distributed optical fiber leakage detection system and experimental analysis[J]. Journal of Applied Optics, 2015, 36(3): 424-429. DOI: 10.5768/JAO201536.0303004
shu

基于支持向量机的分布式光纤泄漏检测定位系统及实验分析

  • 1.

    中国计量学院 质量与安全工程学院,浙江 杭州 310018;

  • 2.

    中国计量学院 机电工程学院,浙江 杭州 310018

基金项目: 

国家自然科学基金（51374188）;浙江省自然科学基金项目（LR13E040001);质检公益性行业科研专项（201310152）

详细信息
    作者简介:

    黄悦（1988-），女，江苏南京人，硕士研究生，主要从事检测技术方面的研究。 Email：huangyue19880830@163.com

    通讯作者:

    王强（1976-），男，湖北应城人，博士，教授，主要从事结构健康检测技术研究。 Email：qiangwang@cjlu.edu.cn

  • 中图分类号: TE973

Support vector machine based distributed optical fiber leakage detection system and experimental analysis

  • 1.

    School of Quality and Safety Engineering,China Jiliang University,Hangzhou 310018,China;

  • 2.

    School of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China

摘要

    摘要
  • 摘要: 针对基于Sagnac和Mach-Zehnder混合干涉仪的分布式光纤管道泄漏检测定位系统进行了泄漏实验，采用在1 km~9 km之间的20组泄漏点样本，依据支持向量机建立样本数据的回归模型，对支持向量机的相关调整参数进行了优化，对系统的灵敏度进行了分析。实验结果表明，经SVM回归分析可得，处理后样本比实验所得泄漏点位置更接近实际泄漏点位置，传统定位方法得到的泄漏点位置平均绝对误差为118.85 m，经过回归分析后样本的平均绝对误差为92.01 m，定位精确度达99.85%，定位精度提高；当泄漏点距法拉第旋转镜的距离越远，检测系统的灵敏度越小，当泄漏点位置超过10 km时，系统的灵敏度低于0.5 Hz/m。
    Abstract: Leakage experiments were performed on the distributed optical fiber pipeline leakage detection system. The system was based on a mixed interference principle of Mach-Zehnder and Sagnac. 20 groups of leakage point samples were gained between 1km to 9km from the leakage experiments. Support vector machines(SVMs) were used to build the sample of data model, the related parameters of SVM were optimized , and the sensitivity of the system was analyzed. The results show that the processed samples are significantly closer to the actual leakage points than the experimental leakage points through regression analysis. The mean absolute error of experimental leakage points is 118.85m while that of the regression samples is 92.01m. The accuracy rate of positioning improves to 99.85%. The sensitivity of the detection system is lower when the leakage points are farther away from the Faraday rotation mirror. The sensitivity of the system is less than 0.5 Hz / m when the leakage points are over 10 km.
    • HTML全文
    • 参考文献(1)
  • [1]Jiang Qi. Application of fiber-optic distributed temperature sensor to tunnel monitoring system［J］.Journal of Applied Optics, 2005, 26(3):20-22.
    蒋奇. 分布式光纤温度传感技术在隧道监测中的应用［J］. 应用光学, 2005, 26(3): 20-22.
    [2]Spammer S J, Swart P L, Chtcherbakov A A. Merged Sagnac-Michelson interferometer for distributed disturbance detection［J］. Journal of Light Wave Technology, 1997, 15(6): 972-976.
    [3]Huang Shihchu, Lin Wuuwen, Tsai Mengtsan. Fiber optic in-line distributed sensor for detection and localization of the pipeline leaks［J］. Sensors and Actuators A: Physical, 2007, 135(2): 570-579.
    [4]Hu Zhengsong, Yang Qihua, Qiao Bo. The design of interference distributed fiber-optic underwater long gas pipeline leakage detection system［J］. Laser﹠Optoelectronics Progress, 2012, 49(7): 69-73.
    胡正松,杨其华,乔波.干涉型分布式光纤水下长输气管道泄漏检测系统设计［J］. 激光与光电子学进展, 2012, 49(7): 69-73.
    [5]Su C T, Yang C H. Feature selection for the SVM: anapplication to hypertension diagnosis［J］. Expert Systems with Application, 2008, 34(1): 754-763.
    [6]Pan Rui, Li Lijing, Zhang Wenhui. Compound SVM algorithm for restraining false alarm of distributed fiber optic sensor ［J］.Infrared and Laser Engineering, 2013, 42(S2):431-439.
    潘锐, 李立京, 张文慧. 抑制分布式光纤光学传感器错误警报的混合支持向量机算法［J］. 红外与激光工程, 2013, 42(增刊2): 431-439.
    [7]Li Yan, Liang Zhengtao, Li Lijing, et al. Pattern recognition of fiber-optic micro vibration sensor based on wavelet and SVM ［J］. Transducer and Microsystem Technologies, 2013, 32(2): 43-49.
    李彦, 梁正桃, 李立京, 等. 基于小波和支持向量机的光纤微振动传感器模式识别［J］. 传感器与微系统, 2013, 32(2): 43-49.
    [8]Lu Jiyun, Wang Bangfeng, Liang Dakai. Identification of impact location by using FBG based on wavelet packet feature extraction and SVR［J］. Optics and Precision Engineering, 2012, 20(4):712-718.
    芦吉云, 王帮峰, 梁大开. 基于小波包特征提取及支持向量回归机的光纤布拉格光栅冲击定位系统［J］.光学精密工程, 2012, 20(4):712-718.
    [9]Huang Yue, Wang Qiang, Yang Qihua, et al. The experimental analysis of distributed fiber optic underwater natural gas pipeline leakage detection system ［J］. Laser﹠Optoelectronics Progress, 2014, 51（11):110602-1-6.
    黄悦, 王强, 杨其华,等. 水下天然气管道分布式光纤泄漏检测系统实验分析［J］. 激光与光电子学进展, 2014, 51（11): 110602-1-6.
    [10]Zhang Renjie. The design of fiber-optic sensor natural gas pipeline leakage detection device based on PGC demodulation [D].Zhejiang: China Jiliang University, 2014.
    章仁杰. 基于PGC解调的光纤传感器天然气管道泄漏检测装置设计[D]. 浙江: 中国计量学院, 2014.
    [11]Keerthi S S, Lin C J. Asymptotic behaviors of support vector machines with Gaussian kernel ［J］. Neural Computation, 2003, 15(7): 1667-1689.
    [12]Liu Xianglou, Jia Dongxu, Li Hui. Research on Kernel parameter optimization of support vector machine in speaker recognition ［J］. Science Technology and Engineering, 2010, 10(7): 1669-1673.
    [13]Wang Jianfeng, Zhang Lei, Chen Guoxing, et al. A parameter optimization method for an SVM based on improved grid search algorithm ［J］. Applied Science and Technology, 2012, 39(3): 28-31.
    王健峰, 张磊, 陈国兴, 等. 基于改进的网格搜索法的SVM参数优化［J］. 应用科技, 2012, 39(3): 28-31.
    • 相关文章
    • 施引文献(3)

  • 期刊类型引用(2)

    1. 闫保军，刘术林. 大长径比微通道板电子清刷实验研究. 真空电子技术. 2024(06): 1-9 . 百度学术
    2. 顾运厅，林焱剑，闫保军，刘术林，杨玉真，余洋，温凯乐，王玉漫. 产生大面积均匀面电子源的电子枪设计. 真空科学与技术学报. 2019(12): 1109-1113 . 百度学术

    其他类型引用(1)

    • 资源附件(0)
计量
  • 文章访问数:  1348
  • HTML全文浏览量:  70
  • PDF下载量:  94
  • 被引次数: 3
出版历程

目录

摘要
HTML全文
    参考文献(1)
    相关文章
    施引文献(3)
    资源附件(0)

    /

    返回文章
    返回

    相关数据库

    广告合作

    友情链接

    帮助中心

    扫描关注本刊微信平台

    您是第  2900212位访问者，欢迎！

    地址: 西安市电子三路西段9号 邮政编码: 710065 联系电话: 029-88288172

    版权所有 © 《应用光学》编辑部

    陕公网安备 61011302001501号       陕ICP备19002862号-1

    北京仁和汇智信息技术有限公司 开发  技术支持: info@rhhz.net   百度统计