• Acta Optica Sinica
  • Vol. 42, Issue 20, 2006003 (2022)
Zehang Ma1, Rui Gong1, Bin Li2, Li Pei1, and Huai Wei1、*
Author Affiliations
  • 1Key Laboratory of All Optical Network and Advanced Telecommunication Network, Ministry of Education, Institute of Lightwave Technology, Beijing Jiaotong University, Beijing 100044, China
  • 2School of Information and Communication Engineering, Communication University of China, Beijing 100024, China
  • show less
    DOI: 10.3788/AOS202242.2006003 Cite this Article
    Zehang Ma, Rui Gong, Bin Li, Li Pei, Huai Wei. Optical Fiber Multi-Parameter Measurement Based on Machine Learning[J]. Acta Optica Sinica, 2022, 42(20): 2006003 Copy Citation Text show less


    This paper proposes a method to extract the parameters to be measured from the incomplete information of the signal by machine learning. Instead of the data containing all the pulse amplitude and phase information, the method employs the power spectrum amplitude data containing only part of the signal information for parameter extraction. It overcomes the difficulty in measuring the phase information of complex optical signals. Simulations verify the ability to utilize machine learning algorithms to extract the parameter information of transmission medium from pulse evolution and the feasibility of using the power spectrum of pulse without phase information to realize optical fiber multi-parameter measurement. The simulation results show that the mean square error of this method can be controlled below 0.3% with proper machine learning algorithms.