Efficient Graphene Reconfigurable Reflectarray Antenna Electromagnetic Response Prediction Using Deep Learning

Aiming at the time-consuming problem of full-wave (FW) simulation scattering characteristics traditional graphene reconfigurable reflectarray antenna, a fast prediction method electromagnetic (EM) response based on deep learning is proposed. The convolutional neural network (CNN) in effectively used research this paper. This first discretizes input vector (patch geometry, chemical potential, frequency, incident angle, etc.) and then preprocesses data into two-dimensional image suitable for CNN training, finally uses to train model instead extensive FW calculations, EM antenna calculated. training results three algorithms support regression (SVR), radial basis function (RBFN) are comprehensively compared. experimental show that has good performance accuracy with an over 99%, can also save least 99% time.