Scholarlink

<p>Reverse design of highly GeO<sub>2</sub>-doped silica optical fibers with broadband and flat dispersion profiles is proposed using a neural network (NN) combined with a particle swarm optimization (PSO) algorithm. Firstly, the NN model designed to predict optical fiber dispersion is trained with an appropriate choice of hyperparameters, achieving a root mean square error (<i>RMSE</i>) of 9.47×10<sup>−7</sup> on the test dataset, with a determination coefficient (<i>R</i><sup>2</sup>) of 0.999. Secondly, the NN is combined with the PSO algorithm for the inverse design of dispersion-flattened optical fibers. To expand the search space and avoid particles becoming trapped in local optimal solutions, the PSO algorithm incorporates adaptive inertia weight updating and a simulated annealing algorithm. Finally, by using a suitable fitness function, the designed fibers exhibit flat group velocity dispersion (<i>GVD</i>) profiles at 1 400–2 400 nm, where the <i>GVD</i> fluctuations and minimum absolute <i>GVD</i> values are below 18 ps·nm<sup>−1</sup>·km<sup>−1</sup> and 7 ps·nm<sup>−1</sup>·km<sup>−1</sup>, respectively.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Inverse design of broadband and dispersion-flattened highly GeO2-doped optical fibers based on neural networks and particle swarm algorithm

  • 期刊论文

  • 发表日期：

    2025年5月3日

查看全文
  • Runrui Li,
  • Chuncan Wang

摘要

Reverse design of highly GeO2-doped silica optical fibers with broadband and flat dispersion profiles is proposed using a neural network (NN) combined with a particle swarm optimization (PSO) algorithm. Firstly, the NN model designed to predict optical fiber dispersion is trained with an appropriate choice of hyperparameters, achieving a root mean square error (RMSE) of 9.47×10−7 on the test dataset, with a determination coefficient (R2) of 0.999. Secondly, the NN is combined with the PSO algorithm for the inverse design of dispersion-flattened optical fibers. To expand the search space and avoid particles becoming trapped in local optimal solutions, the PSO algorithm incorporates adaptive inertia weight updating and a simulated annealing algorithm. Finally, by using a suitable fitness function, the designed fibers exhibit flat group velocity dispersion (GVD) profiles at 1 400–2 400 nm, where the GVD fluctuations and minimum absolute GVD values are below 18 ps·nm−1·km−1 and 7 ps·nm−1·km−1, respectively.