Chinese Journal of Lasers, Volume. 42, Issue 11, 1105005(2015)

Study of Pattern Recognition Based on Multi-Characteristic Parameters for φ-OTDR Distributed Optical Fiber Sensing System

Zhang Yan1、*, Lou Shuqin1, Liang Sheng2, and Wang Peng1
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • show less

    In view of the present phase sensitive optical time-domain reflectometer (φ-OTDR) distributed optical fiber sensing system is difficult to distinguish the disturbance effectively. A disturbance modes recognition method based on multi-parameters is presented. A weighted average synthetic evaluation function is used for characteristic parameters pattern recognization including square difference, short time level crossing rate, short time Fourier transform and duration of the disturbance. By the proposed method, four disturbance modes including stress damage (breaking), climbing, watering (simulate rain environment) and mild crushing (simulate harmless artificial disturbance) are effectively recognized. The recognition rate of disturbance pattern recognization is realized as 91.2%, 88.3%, 90% and 86.7%, respectively, for the corresponding four disturbance modes by analyzing the statistics of 60 groups of 240 samples. The proposed method breaks though the limitation of disturbance modes recognized by current single-characteristic parameter method and improves the reliability of disturbance pattern recognization.

    Tools

    Get Citation

    Copy Citation Text

    Zhang Yan, Lou Shuqin, Liang Sheng, Wang Peng. Study of Pattern Recognition Based on Multi-Characteristic Parameters for φ-OTDR Distributed Optical Fiber Sensing System[J]. Chinese Journal of Lasers, 2015, 42(11): 1105005

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Optical communication

    Received: May. 12, 2015

    Accepted: --

    Published Online: Nov. 27, 2015

    The Author Email: Yan Zhang (13120044@bjtu.edu.cn)

    DOI:10.3788/cjl201542.1105005

    Topics