Machine learning approach for computing optical properties of a photonic crystal fiber
Machine learning approach for computing optical properties of a photonic crystal fiber
复制标题
DOI：
10.1364/oe.27.036414
复制
发表时间：
2019-12-09
期刊：
影响因子：
3.8
通讯作者：
Rahman, B. M. A.
中科院分区：
文献类型：
--
作者：
Chugh, Sunny;Gulistan, Aamir;Rahman, B. M. A.
光子晶体光纤（PCF）是一种特殊的光波导，在非线性光信号处理和高功率光纤放大器等领域有着广泛的应用。在本文中，机器学习技术被用来计算各种光学特性，包括有效折射率，有效模式面积，色散和限制损耗的实芯光子晶体光纤。这些基于人工神经网络的机器学习算法能够对二氧化硅实芯光子晶体光纤中波长范围为0.5-1.8 μ m、间距范围为0.8-2.0 μ m、直径间距范围为0.6-0.9、环数为4或5的常用参数空间的上述光学性质进行准确预测。我们演示了使用简单和快速训练的前馈人工神经网络，预测输出未知的设备参数比传统的数值模拟技术更快。还比较了神经网络（用于训练和测试）和Lumerical MODE解决方案所需的计算运行时间。(C)根据OSA开放获取出版协议的条款，2019年美国光学学会
Photonic crystal fibers (PCFs) are the specialized optical waveguides that led to many interesting applications ranging from nonlinear optical signal processing to high-power fiber amplifiers. In this paper, machine learning techniques are used to compute various optical properties including effective index, effective mode area, dispersion and confinement loss for a solid-core PCF. These machine learning algorithms based on artificial neural networks are able to make accurate predictions of above-mentioned optical properties for usual parameter space of wavelength ranging from 0.5-1.8 mu m, pitch from 0.8-2.0 mu m, diameter by pitch from 0.6-0.9 and number of rings as 4 or 5 in a silica solid-core PCF. We demonstrate the use of simple and fast-training feed-forward artificial neural networks that predicts the output for unknown device parameters faster than conventional numerical simulation techniques. Computation runtimes required with neural networks (for training and testing) and Lumerical MODE solutions are also compared. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement