DATA-DRIVEN MODELING OF ERBIUM DOPED FIBER AMPLIFIERS BY NEURAL NETWORKS

    公开(公告)号:US20240243540A1

    公开(公告)日:2024-07-18

    申请号:US18414425

    申请日:2024-01-16

    CPC classification number: H01S3/10015 H01S2301/04

    Abstract: Dependence of EDFA gain shape on input power and input spectrum shape is modelled using a simple neural network-based architecture for amplifiers with different gains and output powers. The model can predict the gain within ±0.1 dB. While the model has good success predicting the performance of an EDFA it is trained with, it is not as successful when predicting a different EDFA, or the same EDFA with different pump power. Retraining the model with a small amount of supplementary data from a separate EDFA makes the model able to predict the performance of the second EDFA with little loss in performance. Experiments show that machine learning model of an EDFA is capable of modelling spectralhole burning effects accurately. As a result, it significantly outperforms black-box models that neglect inhomogenous effects. Model achieves an average RMSE error of 0.016 dB between the model and measurements.

    REPEATER DESIGN FOR DISTRIBUTED ACOUSTIC SENSING ON MULTISPAN FIBER LINKS

    公开(公告)号:US20210356316A1

    公开(公告)日:2021-11-18

    申请号:US17314006

    申请日:2021-05-06

    Abstract: Aspects of the present disclosure are directed to alternative repeater design(s) that advantageously improve signal-to-noise of distributed acoustic sensing (DAS) systems using coherent detection of Rayleigh backscatter in multi-span links including inline amplification that may be employed—for example—in undersea submarine systems. The repeater designs incorporate Rayleigh combine units (RCU) and Rayleigh drop units (RDU) to reduce Rayleigh backscatter loss as Rayleigh signal(s) is/are routed to a link that propagates the backscatter signal in an opposite direction relative to interrogation pulse(s).

Patent Agency Ranking