Artificial neural network application for novel 3D printed nonuniform ceramic reflectarray antenna
MetadataShow full item record
CitationMahouti, M., Kuskonmaz, N., Mahouti, P., Belen, M. A., & Palandoken, M. (2020). Artificial neural network application for novel 3D printed nonuniform ceramic reflectarray antenna. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields. 33(6),
The main inconvenience in design process of modern high performance reflec-tarray antennas is that these designs are heavily depended on full-wave electro-magnetic simulation tools, where in most of the cases the design optimizationprocess would be an inefficient or impractical. However, thanks to the recentadvances in computer-aided design and advanced hardware systems, artificialneural networks based modeling of microwave systems has become a popularresearch topic. Herein, design optimization of an alumina-based ceramic sub-strate reflectarray antenna by using multilayer perceptron (MLP) and 3D printingtechnology had been presented. MLP-based model of ceramic reflectarray (CRA)unit element is used as a fast, accurate, and reliable surrogated model for the pre-diction of reflection phase of the incoming EM wave on the CRA unit cell withrespect to the variation of unit elements design parameters, operation frequency,and substrate thickness. The structural design of a reflectarray antenna with non-uniform reflector height operating in Xband has been fabricated for the experi-mental measurement of reflectarray performance using 3D printer technology.The horn feeding based CRA antenna has a measured gain characteristic of22 dBi. The performance of the prototyped CRA antenna is compared with thecounterpart reflectarray antenna designs in the literature.