Yuzhao Ma, Tingting Zhang, Qingxiao Zhu, Meng Li. Optical Fiber Perimeter Intrusion Event Recognition Based on ISSA and Genetic Algorithm Optimized BiLSTM Neural Network[J]. Laser & Optoelectronics Progress, 2024, 61(5): 0506001
- Laser & Optoelectronics Progress
- Vol. 61, Issue 5, 0506001 (2024)
Fig. 1. Fiber perimeter system based on dual Mach-Zehnder
Fig. 2. Schematic diagram of ISSA method
Fig. 3. BiLSTM neural network structure diagram
Fig. 4. Principle diagram of GA-BiLSTM neural network recognize intrusion events
Fig. 5. Fiber perimeter intrusion signal. (a) Climb; (b) run; (c) knock; (d) static; (e) wind; (f) rain
Fig. 6. Knock signal singular spectrum analysis. (a) Distribution of singular value; (b) distribution of contribution rate
Fig. 7. Time-frequency analysis of knock signal. (a) Time domain; (b) frequency domain
Fig. 8. Number of main signal frequencies
Fig. 9. Time-frequency analysis of knock signal components after one SSA. (a) Time domain;(b) frequency domain
Fig. 10. Time-frequency analysis of knock signal components after twice SSAs. (a) Time domain; (b) frequency domain
Fig. 11. Time-frequency analysis of knock signal components after three SSAs. (a) Time domain;(b) frequency domain
Fig. 12. Recognition accuracy of optimization algorithms under different evolutions. (a) 24 times; (b) 72 times; (c) 120 times; (d) 240 times
Fig. 13. Fitness change curve
Fig. 14. RNN recognition effect diagram
Fig. 15. GA-RNN recognition effect diagram
Fig. 16. BiLSTM neural network recognition effect diagram
Fig. 17. GA-BiLSTM neural network recognition effect diagram
|
Table 1. Laser parameters
|
Table 2. Comparison of denoising performance of SSA and ISSA
|
Table 3. Neural networks recognition time for different evolutions
|
Table 4. Comparison of recognition effect of different neural networks
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20