Study of pattern recognition based on SVM algorithm for φ-OTDR distributed optical fiber disturbance sensing system

Zhang Junnan; Lou Shuqin; Liang Sheng

doi:10.3788/IRLA201746.0422003

Currently, phase sensitive optical time-domain reflectometer (-OTDR) distributed optical fiber sensing system is difficult to accurately determine current position of disturbance and distinguish the model of disturbance effectively. A method was proposed based on support vector machine (SVM) which can accurately distinguish disturbance and the model of disturbance. With the technique of the binary tree, a categorizer based on SVM was set up by extracting the various signal characteristics of the mean, the variance, the mean square deviation and energy of the time-domain and frequency-domain. Thus the disturbance and disturbance mode can be distinguished. In terms of the sensing signal feature, the categorizer I was determined if the sensing signals was disturbance signals or not firstly. Then, mode of disturbance can be recognized by the following categorizers. Experiments were carried out to validate the proposed method by 600 groups of data. The correct discrimination rate is better than 96%. The rate of missing report and the rate of false positives is less than 4%. The rate of correct pattern recognition is greater than 94%.

Study of pattern recognition based on SVM algorithm for φ-OTDR distributed optical fiber disturbance sensing system

1. School of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China;

2. School of Science,Beijing Jiaotong University,Beijing 100044,China

Received Date: 2016-08-05

Rev Recd Date: 2016-09-03

Publish Date: 2017-04-25

Key words:

distributed fiber disturbance sensing system /
φ-OTDR /
SVM algorithm /
disturbance discrimination /
pattern recognition

Abstract: Currently, phase sensitive optical time-domain reflectometer (-OTDR) distributed optical fiber sensing system is difficult to accurately determine current position of disturbance and distinguish the model of disturbance effectively. A method was proposed based on support vector machine (SVM) which can accurately distinguish disturbance and the model of disturbance. With the technique of the binary tree, a categorizer based on SVM was set up by extracting the various signal characteristics of the mean, the variance, the mean square deviation and energy of the time-domain and frequency-domain. Thus the disturbance and disturbance mode can be distinguished. In terms of the sensing signal feature, the categorizer I was determined if the sensing signals was disturbance signals or not firstly. Then, mode of disturbance can be recognized by the following categorizers. Experiments were carried out to validate the proposed method by 600 groups of data. The correct discrimination rate is better than 96%. The rate of missing report and the rate of false positives is less than 4%. The rate of correct pattern recognition is greater than 94%.

HTML

Reference (12)

[1]	Li X, Sun Q, Wo J. Hybrid TDM/WDM-based fiber-optic sensor network for perimeter intrusion detection[J]. Journal of Lightwave Technology, 2012, 30(8):1113-1120. (in Chinese)
[2]	Wang Siyuan, Lou Shuqin, Liang Sheng, et al. Pattern recognition method for distributed disturbance sensing system based on MZ interferometer[J]. Infrared and Laser Engineering, 2014, 43(8):2613-2618. (in Chinese)
[3]	Zhang Chunxi, Zhong Xiang, Li Lijing, et al. Long-distance intrusion detection system based on phase sensitive light time domain reflectometer[J]. Infrared and Laser Engineering, 2015, 44(2):742-746.
[4]	Wang Peng, Lou Shuqin, Liang Sheng, et al. Threshold algorithm for selective average -OTDR distributed fiber perturbation sensing system[J]. Infrared and Laser Engineering, 2016, 45(3):1003-1007. (in Chinese)
[5]	Lin Wentai, Liang Sheng, Lou Shuqin, et al. A new type of optical fiber distributed vibration sensing system with low false alarm rate[J]. Infrared and Laser Engineering, 2016, 45(4):1845-1848. (in Chinese)
[6]	Liu Jianxia. Research on -OTDR distributed optical fiber sensing monitoring technology[J]. Progress in Laser and Optoelectronics, 2013, 50(8):080021. (in Chinese)
[7]	Wang He, Sun Qizhen, Li Xiaolei. Research progress of interferometric distributed fiber vibration sensing technology[J]. Progress in Laser and Optoelectronics, 2013, 50(2):020004. (in Chinese)
[8]	Li Qin, Zhang Chunxi, Li Lijing. Effect of frequency drift of laser on the accuracy of phase-sensitive optical time-domain reflectometer disturbance[J]. Chinese Journal of Lasers, 2014, 41(3):0305003. (in Chinese)
[9]	Zhao Enming, Li Entao, Teng Pingping, et al. Integrated nitrite microfluidic fluorescence sensor based on surface open fiber[J]. Optical Precision Engineering, 2015, 23(8):2158-2163. (in Chinese)
[10]	Xu Ning, Dai Ming. Distributed optical fiber temperature and pressure sensor design[J]. Chinese Optics, 2015, 8(4):629-635. (in Chinese)
[11]	Wang Jie, Jia Xinhong. Phase-sensitive time-domain reflectometry based on bidirectional Raman amplification[J]. Acta Physica Sinica, 2013, 62(4):044212.
[12]	Fan Qi. Study on the toxicity of mushrooms based on support vector machine[J]. Chinese Agricultural Science Bulletin, 2015, 31(19):232-236. (in Chinese)

Study of pattern recognition based on SVM algorithm for φ-OTDR distributed optical fiber disturbance sensing system

doi: 10.3788/IRLA201746.0422003

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views