Abstract
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 µm, pitch from 0.8-2.0 µm, 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.
Highlights
Photonic crystal fiber (PCF) was first proposed by Knight et al [1] in 1996, which consists of a core with the periodic arrangement of air holes running along the length of the fiber
We validate the trained artificial neural networks (ANN) model by evaluating their outputs for a solid-core PCF at unknown design parameters, and the computational runtimes of ANN model are compared with the numerical simulations
This paper has shown that how we can predict the effective index, effective mode area, dispersion and confinement loss of a photonic crystal fiber within milliseconds, in contrast of needing few minutes with numerical simulations
Summary
Photonic crystal fiber (PCF) was first proposed by Knight et al [1] in 1996, which consists of a core with the periodic arrangement of air holes running along the length of the fiber. Hollow core PCF has a negative refractive index difference between the core and cladding, and light guidance is based on photonic band gap (PBG) mechanism [2] Such structures exhibit the novel properties of being low loss and endlessly single mode propagation. Accurate modeling and optimization of photonic crystal structures generally relies upon the numerical methods such as finite difference method [11], finite element method (FEM) [12], block-iterative frequency-domain method [13], and plane wave expansion method [14, 15] These methods require significant computer resources when dealing with complex photonic crystal structures which needs to be simulated multiple times to obtain an optimized design.
Sign-in/Register to view highlights & summary 
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call