Physics-Informed Neural Network for Optical Fiber Parameter Estimation From the Nonlinear Schrödinger Equation
Physics-Informed Neural Network for Optical Fiber Parameter Estimation From the Nonlinear Schrödinger Equation
复制标题
用于根据非线性薛定谔方程估计光纤参数的物理信息神经网络
DOI：
10.1109/jlt.2022.3199782
复制
发表时间：
2022-11
影响因子：
4.7
通讯作者：
Min Zhang
中科院分区：
文献类型：
--
作者：
Xiaotian Jiang;Danshi Wang;Xue Chen;Min Zhang
对于任何遵循严格的数学和物理理论的系统，如光纤系统，系统参数估计是系统检测和监控的关键。本文提出了一种基于物理信息神经网络（PINN）的光纤参数估计方法，该方法通过求解非线性薛定谔方程（NLSE）的逆问题，推断NLSE的未知参数。该方法既考虑了物理规律的先验知识，又考虑了观测数据的特点，仅从发射和接收波形中得到。在PINN中，NLSE和观测数据被设置为损耗函数，并且典型的光纤参数（衰减、色散和非线性系数）通过学习有限的观测数据被迭代地优化，直到它们满足推断的NLSE。分别对单高斯脉冲传输、超短脉冲在高非线性光纤中的传输以及光信号在标准单模光纤中的传输进行了实验验证。该方法将信号的发射功率作为参数特征嵌入PINN中，使PINN能够同时学习不同功率下的信号传输。适当调整损失函数中NLSE和观测数据的均方误差项的权重，以平衡学习难度。并对128种不同信号的统计结果和不同信噪比下的模型性能进行了分析。作为扩展，本文还研究了光纤长度的估计，在发射功率为0dBm时，误差为0.375%。我们的工作可验证地表明，所提出的方法表现良好，可以进一步扩展到光纤中的多种应用。
For any system that follows rigorous mathematical and physical theories like fiber-optic system, system parameter estimation is crucial for system detection and monitoring. In this paper, a physics-informed neural network (PINN)-based method is proposed for optical fiber parameter estimation by solving the inverse problem of the nonlinear Schrödinger equation (NLSE), i.e., inferring the unknown parameters of NLSE. The proposed method considers both the prior knowledge of physical law and the characteristics of observation data from only the transmitted and received waveforms. In PINN, the NLSE and observation data are set as the loss function, and the typical fiber parameters (attenuation, dispersion, and nonlinear coefficient) are optimized iteratively until they satisfy the inferred NLSE by learning the limited observation data. Three scenarios are validated, including single Gaussian pulse propagation, ultrashort pulse propagation in highly nonlinear fiber, and optical signal transmission in standard single-mode fiber. The launch power of the signal is embedded in PINN as a parametric feature, which makes PINN learn the signal transmissions under different powers simultaneously. The weights of mean square error terms for NLSE and observation data in the loss function are properly adjusted to balance learning difficulties. Moreover, the statistical results of 128 different signals and model performance under different signal-to-noise ratios are analyzed. As an extension, fiber length estimation is also studied, and the error is 0.375% when the launch power is 0 dBm. Our work verifiably shows that the proposed approach performs well and can be further extended to multiple applications in fiber optics.
登录
查看更多内容
DOI：
--
发表时间：
2021-04
期刊：
--
影响因子：
--
作者：
T. Sasai;M. Nakamura;E. Yamazaki;Shuto Yamamoto;H. Nishizawa;Y. Kisaka
通讯作者：
T. Sasai;M. Nakamura;E. Yamazaki;Shuto Yamamoto;H. Nishizawa;Y. Kisaka
影响因子：
11
作者：
Xiaotian Jiang;Danshi Wang;Qirui Fan;Min Zhang;Chao Lu;A. Lau
通讯作者：
Xiaotian Jiang;Danshi Wang;Qirui Fan;Min Zhang;Chao Lu;A. Lau
影响因子：
4.7
作者：
T. Sasai;M. Nakamura;E. Yamazaki;Shuto Yamamoto;H. Nishizawa;Y. Kisaka
通讯作者：
T. Sasai;M. Nakamura;E. Yamazaki;Shuto Yamamoto;H. Nishizawa;Y. Kisaka
影响因子：
4.7
作者：
T. Tanimura;S. Yoshida;K. Tajima;S. Oda;T. Hoshida
通讯作者：
T. Tanimura;S. Yoshida;K. Tajima;S. Oda;T. Hoshida
影响因子：
4.7
作者：
K. Nakajima;M. Ohashi;M. Tateda
通讯作者：
K. Nakajima;M. Ohashi;M. Tateda