Ground plane design configuration estimation of 4.9 GHzreconfigurable monopole antenna for desired radiationfeatures using artificial neural network

摘要

This paper presents a system based on artificial neural network (ANN) thatpredicts ground plane design for desired radiation properties of a monopoleantenna with operation band of 4.8 to 5 GHz. The operating frequency can beadapted to any other frequency regimes. Initially, a 180×180 mm~2 groundplane, which is composed of a copper layer, is designed and integrated to aradiative pole that creates monopole antenna configuration. The ground planeis divided into 18 rows and 18 columns as 18×18 matrix so that each unit cellhas a square shape having 10 mm side length. Moreover, 152 different groundplane configurations are created by using logic 1 s and 0 s. Multi-layered feedforward ANN is used along with Scale Conjugate Gradient learning algorithmto design ground plane of the monopole antenna. Simulated 152 random groundplane arrays and obtained radiation patterns are used to train ANN forthe ground plane design. If a user wants to manipulate radiation, artificial neuralnetwork gives the optimum ground plane design for the desired radiationdirection and gain with 91.03% accuracy. Finally, one test antenna is fabricatedand experimentally measured to support the results of the simulated one. Theproposed ANN model approach can be easily used for antenna applications inthe antenna industry.