Feature Extraction Method Based on FDM Energy Entropy and its Application on Optical Fiber Vibration Recognition

Hongquan Qu; Bingbing Wei; Zheng Zhang; Zhiyong Sheng

doi:10.3788/LOP202158.0706006

Laser & Optoelectronics Progress, Volume. 58, Issue 7, 0706006(2021)

Feature Extraction Method Based on FDM Energy Entropy and its Application on Optical Fiber Vibration Recognition

Hongquan Qu, Bingbing Wei, Zheng Zhang, and Zhiyong Sheng^*

Author Affiliations

School of Information Science and Technology, North China University of Technology, Beijing 100144, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Flowchart of feature extraction and recognition method for optical fiber vibration signals

Download full size

Fig. 2. Decomposition results. (a) EEMD; (b) FDM

Download full size

Fig. 3. Coefficient distribution of AMDF. （a） Manual signal; （b） mechanical signal

Download full size

Fig. 4. Two-dimensional feature distribution

Download full size

Fig. 5. Original signal and reconstructed signal by FDM. (a) Original signal; (b) reconstructed signal by FDM

Download full size

Fig. 6. Sorting and distribution of FIBF with greater correlation with the original signal

Download full size

Fig. 7. FDM energy entropy distribution. (a) Tapping signal; (b) digging signal; (c) running signal; (d) electric drill signal; (e) noise

Download full size

Fig. 8. Flow chart of classification recognition

Download full size

Table 1. Recognition rate of optical fiber signal with different features processed by FDM
View table
Table 1. Recognition rate of optical fiber signal with different features processed by FDM
Feature Tapping signal Digging signal Running signal Electric drill signal Noise
$H_{e}$ 89.9 32.1 72.6 31.3 84.2
$T_{A M D F}$ 16.7 78.2 18.4 81.4 62.5
$|T|$ 96.5 91.8 89.3 92 90

Table 2. Recognition rates of fiber optical signal with different features processed by EEMD
View table
Table 2. Recognition rates of fiber optical signal with different features processed by EEMD
Feature Tapping signal Digging signal Running signal Electric drill signal Noise
$H_{e}$ 81.5 62.4 61.9 31.5 76.2
$T_{A M D F}$ 18.9 78.2 18.4 81.4 58.5
$|T|$ 86.9 85.2 85.7 92.8 82.5

Tools

Get Citation

Copy Citation Text

Hongquan Qu, Bingbing Wei, Zheng Zhang, Zhiyong Sheng. Feature Extraction Method Based on FDM Energy Entropy and its Application on Optical Fiber Vibration Recognition[J]. Laser & Optoelectronics Progress, 2021, 58(7): 0706006

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Fiber Optics and Optical Communications

Received: Jul. 13, 2020

Accepted: Sep. 18, 2020

Published Online: Apr. 25, 2021

The Author Email: Sheng Zhiyong (szy1183@ncut.edu.cn)

DOI:10.3788/LOP202158.0706006

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Recognition rate of optical fiber signal with different features processed by FDM

Table 1. Recognition rate of optical fiber signal with different features processed by FDM

Table 2. Recognition rates of fiber optical signal with different features processed by EEMD

Table 2. Recognition rates of fiber optical signal with different features processed by EEMD