首页 > 论文 > 激光与光电子学进展 > 56卷 > 13期(pp:130601--1)

光纤入侵信号的特征提取与识别算法

Feature Extraction and Recognition Algorithm for Fiber Intrusion Signals

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

摘要

为了对分布式光纤上的入侵信号类型进行准确识别,提出了一种基于集合经验模态分解(EEMD)结合随机向量函数链接(RVFL)神经网络的光纤入侵信号的特征提取与识别算法。算法步骤为:对采集到的光纤入侵信号作预处理操作,包括最小-最大规范化处理和利用db3小波去除信号的低频噪声;采用EEMD方法对入侵信号进行分解,得到5组本征模态函数(IMF);计算各IMF分量的能量占比,并依据方差分析法筛选出3组特征向量;将特征向量送入RVFL神经网络进行训练并对入侵信号进行识别。实验结果显示:该方法能正确识别不同入侵信号的类型,具有较高的准确率。

Abstract

A feature extraction and recognition algorithm for fiber intrusion signals is proposed based on ensemble empirical-mode decomposition (EEMD) coupled with a random vector-function linked (RVFL) neural network to accurately identify the type of intrusion signal on a distributed optical fiber. The proposed algorithm starts with the preprocessing for the collected fiber intrusion signals,including minimum-maximum normalization processing and the removal of low frequency noise using the db3 wavelet. Then, the intrusion signals are decomposed by the EEMD to obtain five groups of intrinsic mode functions (IMF). Subsequently, the energy ratio of each component of the IMF is calculated, and three feature vectors are filtered using the analysis of variance. Finally, the feature vectors are sent into the RVFL neural network to be trained for the completion of the signal recognition. The experimental results validate that the proposed algorithm can accurately distinguish between different intrusion signals with high recognition rate.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.130601

所属栏目:光纤光学与光通信

基金项目:国家自然科学基金; 北京自然科学基金;

收稿日期:2018-12-12

修改稿日期:2019-01-24

网络出版日期:2019-07-01

作者单位    点击查看

曲洪权:北方工业大学电子信息学院, 北京 100144
宫殿君:北方工业大学电子信息学院, 北京 100144
张常年:北方工业大学电子信息学院, 北京 100144
王彦平:北方工业大学电子信息学院, 北京 100144

联系人作者:宫殿君(769353964@qq.com)

备注:国家自然科学基金; 北京自然科学基金;

【1】Bi F K, Feng C, Qu H Q et al. Harmful intrusion detection algorithm of optical fiber pre-warning system based on correlation of orthogonal polarization signals. Photonic Sensors. 7(3), 226-233(2017).

【2】Liang W, Lu L L and Zhang L B. Coupling relations and early-warning for “equipment chain” in long-distance pipeline. Mechanical Systems and Signal Processing. 41(1/2), 335-347(2013).

【3】Yang Y, Feng H, Wang Z H et al. Application and development of distributed optical fiber sensing technology in pipeline detection. Electro-Optic Technology Application. 31(6), 1-9, 76(2016).
杨洋, 封皓, 王宗和 等. 光纤传感技术在管道检测中的应用与发展. 光电技术应用. 31(6), 1-9, 76(2016).

【4】An Y, Jin S J, Feng X et al. Optical fiber pipeline security pre-warning system based on coherent Rayleigh scattering. Journal of Tianjin University. 48(1), 70-75(2015).
安阳, 靳世久, 冯欣 等. 基于相干瑞利散射的管道安全光纤预警系统. 天津大学学报. 48(1), 70-75(2015).

【5】Sheng Z Y, Zhang X Y, Wang Y P et al. Feature extraction and linear classification for fiber vibration signals. Journal of Optoelectronics·Laser. 29(7), 760-768(2018).
盛智勇, 张新燕, 王彦平 等. 光纤振动信号特征提取及线性分类方法. 光电子·激光. 29(7), 760-768(2018).

【6】Shang Y, Wang C, Wang C et al. Distributed vibration sensing of perimeter security based on space difference of Rayleigh backscattering. Infrared and Laser Engineering. 47(5), (2018).
尚盈, 王晨, 王昌 等. 采用后向瑞利散射空间差分的周界安防分布式振动监测. 红外与激光工程. 47(5), (2018).

【7】Pang F F, Liu H H and Wang T Y. A review of distributed fiber sensors based on phase-sensitive optical time domain reflectometer. Journal of Nanjing University of Information Science & Technology (Natural Science Edition). 9(2), 130-136(2017).
庞拂飞, 刘奂奂, 王廷云. 相位敏感光时域反射光纤传感技术的研究综述. 南京信息工程大学学报(自然科学版). 9(2), 130-136(2017).

【8】Qu H Q, Ren X C, Bi F K et al. Two-level detection algorithm of two-dimensional for vibration signals detected by optical fiber. Acta Optica Sinica. 35(10), (2015).
曲洪权, 任学丛, 毕福昆 等. 光纤振动信号的二维二级检测算法. 光学学报. 35(10), (2015).

【9】Qu H Q, Wang T Q, Bi F K et al. Harmful intrusion detection method based on two-dimensional K-S test in reconfigured background for optical fiber pre-warning system. Journal of Jishou University (Natural Science Edition). 38(1), 19-23(2017).
曲洪权, 王天琦, 毕福昆 等. 基于重构背景二维K-S检验的有害入侵光纤预警. 吉首大学学报(自然科学版). 38(1), 19-23(2017).

【10】Qu H Q, Zheng T, Bi F K et al. Vibration detection method for optical fibre pre-warning system. IET Signal Processing. 10(6), 692-698(2016).

【11】Sha Y Y, Xi L X, Zhang X G et al. Polarization mode dispersion measurement based on wavelet threshold denoising. Chinese Journal of Lasers. 45(11), (2018).
沙宇洋, 席丽霞, 张晓光 等. 基于小波阈值去噪的偏振模色散测量. 中国激光. 45(11), (2018).

【12】Pan P, Xi L X, Zhang X G et al. Experimental research on polarization mode dispersion measurement based on empirical mode decomposition. Chinese Journal of Lasers. 45(1), (2018).
潘潘, 席丽霞, 张晓光 等. 基于经验模态分解的偏振模色散测量实验研究. 中国激光. 45(1), (2018).

【13】Qu H Q, Wang X X, Bi F K et al. Optical fiber vibration recognition based on wavelet reconstruction and time-space features. Journal of Jishou University (Natural Science Edition). 38(2), 36-41(2017).
曲洪权, 王笑笑, 毕福昆 等. 基于小波重构与时空二维特征的光纤振动识别. 吉首大学学报(自然科学版). 38(2), 36-41(2017).

【14】Wang J P, Hao Z and Zhu C H. Research on vibration signal recognition of optical fiber perimeter based on phase space reconstruction. Journal of Hefei University of Technology (Natural Science). 40(5), 643-648(2017).
王建平, 郝钊, 朱程辉. 基于相空间重构的光纤周界信号识别算法研究. 合肥工业大学学报(自然科学版). 40(5), 643-648(2017).

【15】Zhang Y J, Liu W Z, Fu X H et al. An extraction and recognition method of the distributed optical fiber vibration signal based on EMD-AWPP and HOSA-SVM algorithm. Spectroscopy and Spectral Analysis. 36(2), 577-582(2016).
张燕君, 刘文哲, 付兴虎 等. 基于EMD-AWPP和HOSA-SVM算法的分布式光纤振动入侵信号的特征提取与识别. 光谱学与光谱分析. 36(2), 577-582(2016).

【16】Igelnik B and Pao Y H. Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Transactions on Neural Networks. 6(6), 1320-1329(1995).

引用该论文

Hongquan Qu,Dianjun Gong,Changnian Zhang,Yanping Wang. Feature Extraction and Recognition Algorithm for Fiber Intrusion Signals[J]. Laser & Optoelectronics Progress, 2019, 56(13): 130601

曲洪权,宫殿君,张常年,王彦平. 光纤入侵信号的特征提取与识别算法[J]. 激光与光电子学进展, 2019, 56(13): 130601

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