Neural Network Characterization of Reflectarray Antennas

Abstract

An efficient artificial neural network (ANN) approach for the modeling of reflectarray elementary components is introduced to improve the numerical efficiency of the different phases of the antenna design and optimization procedure, without loss in accuracy. The comparison between the results of the analysis of the entire reflectarray designed using the simplified ANN model or adopting a full-wave characterization of the unit cell finally proves the effectiveness of the proposed model.

Prediction of Slot-Size and Inserted Air-Gap for Improving the Performance of Rectangular Microstrip Antennas Using Artificial Neural Networks

“…Hence, the coefficients of variations for these five values are coming out to be 0.1932, 0.2051, 0.1856, 0.2159, and 0.2031, respectively. Thus, it is concluded here that all the error points over a full validation set of 1350 samples are uniformly distributed [26].…”

“…Robustillo et al [25] have designed a contoured-beam reflectarray for a EuTELSAT European Coverage using ANN. An ANN modeling has been suggested by Freni et al for modeling the behavior of the reflectarray reradiating elements [26]. In the literature [10]- [26], a neural-networks-based synthesis model has not been proposed for predicting the appropriate size of introduced slot on the radiating patch and inserted air-gap between the ground plane and the substrate sheet, simultaneously.…”

“…An ANN modeling has been suggested by Freni et al for modeling the behavior of the reflectarray reradiating elements [26]. In the literature [10]- [26], a neural-networks-based synthesis model has not been proposed for predicting the appropriate size of introduced slot on the radiating patch and inserted air-gap between the ground plane and the substrate sheet, simultaneously. It is very much essential for the antenna designers to predict the "slot-size" and inserted "air-gap" for achieving the desired level of performance parameters like 1.5 GHz resonance frequencies GHz, 6.2 dBi gains dBi, 6.6 dBi directivities dBi, 83% antenna efficiencies %, and % radiation efficiencies % for dual-resonance.…”

Prediction of Slot-Shape, Slot-Size and Inserted Air-Gap of a Microstrip Antenna Using Knowledge-Based Neural Network

“…For this purpose, a relationship between mean and standard deviation (SD) is developed by considering a term coefficient of variation (CoV) which is defined as the ratio of standard deviation (SD) to the mean value. CoV closer to 0 represents greater uniformity whereas CoV closer to 1 represents larger variability of the errors [27]. For KBNN model-2, the mean and standard deviation of five-dimensional computed error are mentioned as follow: …”

Investigations for Performance Improvement of X-Shaped Rmsa Using Artificial Neural Network by Predicting Slot Size

“…Robustillo et al [21] have designed a contoured-beam reflectarray for a EuTELSAT European coverage using stacked patch element with the help of ANN. Thereafter, an ANN based synthesis has been suggested in [22,23] for a single feed circularly-polarized truncated corners square MSA and for reflectarray antennas respectively. Further, an application of ANN for computing resonant frequency of E-shaped compact patch antenna has been proposed in [24].…”