Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Acta Optica Sinica, Volume. 41, Issue 20, 2006002(2021)

Design of Raman Fiber Amplifier Based on Neural Network and Artificial Bee Colony Algorithm

Jiamin Gong1, Fang Liu2、*, Yijie Wu2, Yunsheng Zhang1, Shutao Lei2, and Zehao Zhu2
Author Affiliations
  • 1School of Electronic Engineering, Xi′an University of Posts and Telecommunications, Xi′an, Shaanxi 710121, China
  • 2School of Telecommunication and Information Engineering, Xi′an University of Posts and Telecommunications, Xi′an, Shaanxi 710121,China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (0)
    References (25)
    Cited By (5)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Schematic diagram of multi-pump Raman amplifier

    Fig. 1. Schematic diagram of multi-pump Raman amplifier

    Download full size
    BP neural network model of Raman amplifier

    Fig. 2. BP neural network model of Raman amplifier

    Download full size
    Variations of MSE with number of nodes in different hidden layers. (a) The first hidden layer; (b) the second hidden layer; (c) the third hidden layer; (d) the fourth hidden layer; (e) the fifth hidden layer

    Fig. 3. Variations of MSE with number of nodes in different hidden layers. (a) The first hidden layer; (b) the second hidden layer; (c) the third hidden layer; (d) the fourth hidden layer; (e) the fifth hidden layer

    Download full size
    Variations of R value with number of nodes in different hidden layers. (a) The first hidden layer; (b) the second hidden layer; (c) the third hidden layer; (d) the fourth hidden layer; (e) the fifth hidden layer

    Fig. 4. Variations of R value with number of nodes in different hidden layers. (a) The first hidden layer; (b) the second hidden layer; (c) the third hidden layer; (d) the fourth hidden layer; (e) the fifth hidden layer

    Download full size
    Data distributions in different hidden layers when R value is greater than 0.995

    Fig. 5. Data distributions in different hidden layers when R value is greater than 0.995

    Download full size
    MSE and R value of optimal model. (a) Variation of MSE with number of hidden layers; (b) variation of R values of training, validation and test sets with number of hidden layers

    Fig. 6. MSE and R value of optimal model. (a) Variation of MSE with number of hidden layers; (b) variation of R values of training, validation and test sets with number of hidden layers

    Download full size
    Structural diagram of the optimal BP neural network

    Fig. 7. Structural diagram of the optimal BP neural network

    Download full size
    Training results of the optimal BP model in different datasets. (a) Training set; (b) validation set; (c) test set; (d) complete dataset

    Fig. 8. Training results of the optimal BP model in different datasets. (a) Training set; (b) validation set; (c) test set; (d) complete dataset

    Download full size

    • Table 1. Simulation parameters of RFA

      View table

      Table 1. Simulation parameters of RFA

      ParameterValue
      Wavelength range of signal light /nm1520-1570
      Signal optical power /mW0.01
      Signal light interval /nm1
      Pump wavelength range /nm1410-1520
      Pump power range /mW0-500
      Signal optical loss coefficient /(dB·km-1)0.75
      Pump loss coefficient /(dB·km-1)0.9
      Fiber length /km0.12
      Effective area of optical fiber /μm215.5
      Absolute temperature of optical fiber / K300
      Rayleigh scattering coefficient /m-17×10-8
      Boltzmann constant /(J·K-1)1.38×10-23
      Planck constant /( J·s)6.626×10-34

    • Table 2. Optimized pump light parameters, gain, ΔG and error between net gain and target gain

      View table

      Table 2. Optimized pump light parameters, gain, ΔG and error between net gain and target gain

      Pump light parameterGain /dBΔG /dBError /dB
      λp /nmPp /W
      1415.45,1454.62,1503.720.1000,0.0658,0.12322.250.14860.2566
      1419.31,1455.41,1505.020.1572,0.0996,0.18253.470.17710.2279
      1409.29,1450.75,1502.720.3548,0.1014,0.20334.270.15150.2894
      1416.09,1450.69,1502.020.2950,0.1375,0.27865.210.16520.1489
      1418.64,1449.26,1498.750.2792,0.1802,0.30566.190.20440.2134
      1420.83,1448.79,1496.940.2810,0.2154,0.32377.030.23440.2872
    Tools

    Get Citation

    Copy Citation Text

    Jiamin Gong, Fang Liu, Yijie Wu, Yunsheng Zhang, Shutao Lei, Zehao Zhu. Design of Raman Fiber Amplifier Based on Neural Network and Artificial Bee Colony Algorithm[J]. Acta Optica Sinica, 2021, 41(20): 2006002

    Download Citation

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

    Category: Fiber Optics and Optical Communications

    Received: Jan. 14, 2021

    Accepted: May. 6, 2021

    Published Online: Oct. 7, 2021

    The Author Email: Liu Fang (lf15170905229@163.com)

    DOI:10.3788/AOS202141.2006002

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology