Unsupervised learning method for events identification in φ-OTDR

被引：0
作者：
Jie Zhang
Xiaoting Zhao
Yiming Zhao
Xiang Zhong
Yidan Wang
Fanchao Meng
Jinmin Ding
Yingli Niu
Xinghua Zhang
Liang Dong
Sheng Liang
机构：
[1] Beijing Technology and Business University,School of Artificial Intelligence
[2] National Physical Experiment Teaching Demonstration Center,Key Laboratory of Education Ministry On Luminescence and Optical Information Technology, Department of Physics
[3] School of Science,School of Electronic Engineering
[4] Beijing Jiaotong University,School of Instrumentation Science and Opto
[5] Xi’an University of Posts and Telecommunications,Electronics Engineering
[6] Hefei University of Technology,School of Mechanical, Electronic and Control Engineering
[7] Beijing Jiaotong University,undefined
[8] Beijing Haidongqing Electrical and Mechanical Equipment Co.,undefined
[9] Ltd,undefined
来源：
Optical and Quantum Electronics | 2022年 / 54卷
关键词：
Fiber-optic distributed vibration sensor; Phase-sensitive optical time domain reflectometry (; -OTDR); Unsupervised learning; Clustering; Event identification;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, an unsupervised-learning method for events-identification in φ-OTDR fiber-optic distributed vibration sensor is proposed. The different vibration-events including blowing, raining, direct and indirect hitting, and noise-induced false vibration are clustered by the k-means algorithm. The equivalent classification accuracy of 99.4% has been obtained, compared with the actual classes of vibration-events in the experiment. With the cluster-number of 3, the maximal Calinski-Harabaz index and Silhouette coefficient are obtained as 2653 and 0.7206, respectively. It is found that our clustering method is effective for the events-identification of φ-OTDR without any prior labels, which provides an interesting application of unsupervised-learning in self-classification of vibration-events for φ-OTDR.
引用
收藏
相关论文
共 189 条
  • [1] Abufana SA(2020)variational mode decomposition-based threat classification for fiber optic distributed acoustic sensing IEEE Access 8 100152-100158
  • [2] Dalveren Y(2019)Partial discharge recognition based on optical fiber distributed acoustic sensing and a convolutional neural network IEEE Access 7 101758-101764
  • [3] Aghnaiya A(2019)Hybrid feature extraction of pipeline microstates based on J. Control Sci. Eng. 2019 1-10
  • [4] Kara A(2019)-OTDR sensing system IEEE Sens. J. 19 3683-3689
  • [5] Che Q(2020)A k-nearest neighbor algorithm-based near category support vector machine method for event identification of IEEE Sens. J. 20 1297-1305
  • [6] Wen H(2019)-OTDR J. Lightwave Technol. 37 4799-4807
  • [7] Li X(2020)Event identification by F-ELM Model for Sensors 20 450-2938
  • [8] Hu Y(2020)-OTDR fiber-optic distributed disturbance sensor Opt. Express 28 2925-166710
  • [9] Meng Z(2019)Coherent kramers-kronig receiver for IEEE Access 7 166704-7425
  • [10] Ai X(2019)-OTDR Opt. Express 27 7405-68980
12345678910