Semi-automatic analysis of gyrotropic semiconductor waveguides using neural network

Abstract

This paper focuses on the analysis technique of gyrotropic circular cylindrical semiconductor waveguide by the use of an electrodynamical model. Authors propose the semi-automatic extraction of the dispersion characteristics by the use of single-layer perceptron neural network. The waveguide analysis algorithm consists of four main stages: initialization of system parameters, evaluation of transcendental linear dispersion equation system, extraction of dispersion characteristics and evaluation of the waveguide broad bandwidth. In this paper three types of waveguides (n-InP, n-InSb and p-InP) are analysed using a proposed algorithm. According to the results of analysis, the use of gyrotropic n-InP and p-InP semiconductor, semiconductor-dielectric waveguides are more preferred than to n-InSb waveguides due to their wider broad bandwidth.