Infrared and Laser Engineering, Volume. 51, Issue 5, 20210419(2022)
Demodulation method of overlapping spectrum based on convolutional neural network
Figures & Tables(9)
Fig. 1. Schematic diagram of the aliasing spectrum data acquisition system
Fig. 2. Program block diagram of the upper computer of the aliasing spectrum data acquisition
Fig. 3. Overlap process of the spectrum in the display interface of the host computer
Fig. 4. Schematic diagram of 1D convolutional neural network structure
Fig. 5. CNN training time and test time under different training samples
Fig. 7. Spectral demodulation results under different degrees of aliasing
Table 1. Comparison between different algorithms
View tableView in ArticleTable 1. Comparison between different algorithms
Algorithm RMS/pm Computational time/s Data source ELM 0.918 0.200 Ref.[ 8 ]LS-SVR 3.955 0.0736 Ref.[ 7 ]PSO-SA <5.000 -- Ref.[ 10 ]LSTM 0.674 0.574 Ref.[ 8 ]CNN 0.0826 0.338 This work
Table 2. Demodulation results with different degrees of aliasing
View tableView in ArticleTable 2. Demodulation results with different degrees of aliasing
Case FBG1/nm FBG2/nm Δλ/nm RMS/pm a 1536.8488 1536.1514 0.6974 0.0322 b 1537.1559 1536.1521 1.0038 0.0319 c 1535.7527 1536.1434 −0.3907 0.0148 d 1536.1317 1536.1549 −0.0232 0.0301
Tools
Get Citation
Copy Citation Text
Hanlin Liu, Jingtao Xin, Wei Zhuang, Jiabin Xia, Lianqing Zhu. Demodulation method of overlapping spectrum based on convolutional neural network[J]. Infrared and Laser Engineering, 2022, 51(5): 20210419
Paper Information
Category: Optical communication and sensing
Received: Dec. 25, 2021
Accepted: --
Published Online: Jun. 14, 2022
The Author Email: Zhuang Wei (zhuangwei@bistu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20