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
Fig. 1. Flowchart of feature extraction and recognition method for optical fiber vibration signals
Fig. 2. Decomposition results. (a) EEMD; (b) FDM
Fig. 3. Coefficient distribution of AMDF. (a) Manual signal; (b) mechanical signal
Fig. 4. Two-dimensional feature distribution
Fig. 5. Original signal and reconstructed signal by FDM. (a) Original signal; (b) reconstructed signal by FDM
Fig. 6. Sorting and distribution of FIBF with greater correlation with the original signal
Fig. 7. FDM energy entropy distribution. (a) Tapping signal; (b) digging signal; (c) running signal; (d) electric drill signal; (e) noise
Fig. 8. Flow chart of classification recognition
|
|
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
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)