• Chinese Journal of Lasers
  • Vol. 50, Issue 11, 1101016 (2023)
Congcong Liu, Jiangyong He, Jin Li, Yu Ning, Fengkai Zhou, Pan Wang, Yange Liu, and Zhi Wang*
Author Affiliations
  • Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology, Institute of Modern Optics, College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
  • show less
    DOI: 10.3788/CJL230625 Cite this Article Set citation alerts
    Congcong Liu, Jiangyong He, Jin Li, Yu Ning, Fengkai Zhou, Pan Wang, Yange Liu, Zhi Wang. Dynamic Characteristic Extraction and Prediction of Soliton Bound States in Passively Mode‐Locked Fiber Lasers[J]. Chinese Journal of Lasers, 2023, 50(11): 1101016 Copy Citation Text show less
    Passive mode-locked fiber laser and real-time detection system based on nonlinear polarization rotation technology
    Fig. 1. Passive mode-locked fiber laser and real-time detection system based on nonlinear polarization rotation technology
    Laser mode-locked output characteristics. (a) Spectrum; (b) time-domain pulse sequence
    Fig. 2. Laser mode-locked output characteristics. (a) Spectrum; (b) time-domain pulse sequence
    Feature extraction and prediction based on convolutional autoencoder
    Fig. 3. Feature extraction and prediction based on convolutional autoencoder
    Loose soliton bound state. (a) Real-time spectral evolution; (b) spectra; (c) single period autocorrelation trace
    Fig. 4. Loose soliton bound state. (a) Real-time spectral evolution; (b) spectra; (c) single period autocorrelation trace
    Compact soliton bound state. (a) Real-time spectral evolution; (b) spectra; (c) single period autocorrelation trace
    Fig. 5. Compact soliton bound state. (a) Real-time spectral evolution; (b) spectra; (c) single period autocorrelation trace
    Training parameters and evaluation indicators. (a) Loss curve; (b) influence of number of characteristic parameters on training result; (c) Pearson correlation coefficient
    Fig. 6. Training parameters and evaluation indicators. (a) Loss curve; (b) influence of number of characteristic parameters on training result; (c) Pearson correlation coefficient
    Continuous 10-round spectra. (a) Spectra measured by experiment; (b) spectra predicted by network
    Fig. 7. Continuous 10-round spectra. (a) Spectra measured by experiment; (b) spectra predicted by network
    Real time spectral dynamics of soliton bound states. (a) Origin spectrum; (b) reconstructed spectrum
    Fig. 8. Real time spectral dynamics of soliton bound states. (a) Origin spectrum; (b) reconstructed spectrum
    One-period autocorrelation traces and phase difference evolutions of real-time spectrum and reconstructed spectrum. (a) One-period autocorrelation traces; (b) phase difference evolution at position A; (c) phase difference evolution at position B
    Fig. 9. One-period autocorrelation traces and phase difference evolutions of real-time spectrum and reconstructed spectrum. (a) One-period autocorrelation traces; (b) phase difference evolution at position A; (c) phase difference evolution at position B
    Congcong Liu, Jiangyong He, Jin Li, Yu Ning, Fengkai Zhou, Pan Wang, Yange Liu, Zhi Wang. Dynamic Characteristic Extraction and Prediction of Soliton Bound States in Passively Mode‐Locked Fiber Lasers[J]. Chinese Journal of Lasers, 2023, 50(11): 1101016
    Download Citation