期刊
PHOTONICS
卷 10, 期 3, 页码 -出版社
MDPI
DOI: 10.3390/photonics10030294
关键词
photonic-crystal fiber; four-wave mixing; deep learning neural networks
类别
In this paper, the application of a deep learning neural network (DNN) in the dispersion-oriented inverse design of photonic-crystal fiber (PCF) for four-wave mixing (FWM) fine-tuning is demonstrated. A large dataset of phase-matching curves of various PCF designs is generated using the empirical formula of PCF dispersion instead of numerical simulation, significantly improving the accuracy of the DNN prediction. The accuracies of DNNs' predicted PCF structure parameters are all above 95%. The simulations of the DNN-predicted PCFs structure show that the FWM wavelength has an average numerical mean square error (MAE) of 1.92 nm from the design target. With the assistance of DNN, a specific PCF for wavelength conversion from 1064 nm to 770 nm is designed and fabricated for biomedical imaging applications, with the signal wavelength measured at 770.2 nm.
In this paper, we demonstrate the application of a deep learning neural network (DNN) in the dispersion-oriented inverse design of photonic-crystal fiber (PCF) for the fine-tuning of four-wave mixing (FWM). The empirical formula of PCF dispersion is applied instead of numerical simulation to generate a large dataset of phase-matching curves of various PCF designs, which significantly improves the accuracy of the DNN prediction. The accuracies of DNNs' predicted PCF structure parameters are all above 95%. The simulations of the DNN-predicted PCFs structure demonstrate that the FWM wavelength has an average numerical mean square error (MAE) of 1.92 nm from the design target. With the help of DNN, we designed and fabricated a specific PCF for wavelength conversion via FWM from 1064 nm to 770 nm for biomedical imaging applications. Pumped by a microchip laser at 1064 nm, the signal wavelength is measured at 770.2 nm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据