Multigrade Artificial Neural Network for the Design of Finite Periodic Arrays

Published

Journal Article

© 1963-2012 IEEE. To solve the restriction of prior knowledge in artificial neural networks (ANNs) for the modeling of finite periodic arrays, a new multigrade ANN model is proposed in this paper. Considering mutual coupling and array environment, the proposed model is designed with two sub-ANNs, element-ANN and array-ANN. Based on the relationship between the geometrical variables and the electromagnetic (EM) behavior of elements in an array, element-ANN is built to provide prior knowledge for the modeling of array-ANN. Then, in a review of mutual coupling and array environment, array-ANN is modeled to obtain the EM response of the whole array from the nonlinear superposition of the element responses. Three numerical examples of a linear phased array, a six-element printed dipole array, and a U-slot microstrip array are employed to verify the effectiveness of the proposed model.

Full Text

Duke Authors

Cited Authors

  • Xiao, LY; Shao, W; Ding, X; Liu, QH; Joines, WT

Published Date

  • May 1, 2019

Published In

Volume / Issue

  • 67 / 5

Start / End Page

  • 3109 - 3116

International Standard Serial Number (ISSN)

  • 0018-926X

Digital Object Identifier (DOI)

  • 10.1109/TAP.2019.2900359

Citation Source

  • Scopus