ANN Characterization of Multi-Layer Reflectarray Elements for Contoured-Beam Space Antennas in the Ku-Band

Robustillo, P.; Zapata, J.; Encinar, José A.; Rubio, José Antonio Pérez

doi:10.1109/tap.2012.2196941

Cited by 54 publications

(47 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These border values, as well as the step size, determine the size of the discretized input set. We can profit from the multilayer structure, [5], [10]. Thanks to it, the speed up factor for training set computation would be about 30-50.…”

Section: A Geometrical Parametersmentioning

confidence: 99%

“…The RA antenna met the requirements given in [5]. The central band frequency is 11.95GHz, and the coverage area is the south American region.…”

Section: Artificial Neural Network Definitionmentioning

confidence: 99%

“…One important technique to be used for RA element optimization instead of calls to EM procedures is the use of Artificial Neural Networks, [5]. ANNs are considered in this EM context as multiple-input, multiple-output, non-linear interpolators, [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accurate characterization of multi-resonant reflectarray cells by artificial neural networks

Robustillo

Zapata

Encinar

et al. 2014

The 8th European Conference on Antennas and Propagation (EuCAP 2014)

View full text Add to dashboard Cite

Abstract-This paper describes the accurate characterization of the reflection coefficients of a multilayered reflectarray element by means of artificial neural networks. The procedure has been tested with different RA elements related to actual specifications. Up to 9 parameters were considered and the complete reflection coefficient matrix was accurately obtained, including cross polar reflection coefficients. Results show a good agreement between simulations carried out by the Method of Moments and the ANN model outputs at RA element level, as well as with performances of the complete RA antenna designed.

show abstract

Section: A Geometrical Parametersmentioning

confidence: 99%

“…The RA antenna met the requirements given in [5]. The central band frequency is 11.95GHz, and the coverage area is the south American region.…”

Section: Artificial Neural Network Definitionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate characterization of multi-resonant reflectarray cells by artificial neural networks

Robustillo

Zapata

Encinar

et al. 2014

The 8th European Conference on Antennas and Propagation (EuCAP 2014)

View full text Add to dashboard Cite

show abstract

“…In [13], the ANNs were validated by analyzing a contoured-beam reflectarray demonstrator previously designed, manufactured, and tested [14].…”

Section: Introductionmentioning

confidence: 99%

“…In this letter, the ANNs described in [13] that accurately model a three-layer RA element have been integrated in the design process to optimize the patch dimensions, replacing the MoM computations. Hence, ANNs are used for RA designing purposes and not only for analysis, as in [13].…”

Section: Introductionmentioning

confidence: 99%

Design of a Contoured-Beam Reflectarray for a EuTELSAT European Coverage Using a Stacked-Patch Element Characterized by an Artificial Neural Network

Robustillo

Zapata

Encinar

et al. 2012

Antennas Wirel. Propag. Lett.

View full text Add to dashboard Cite

The design of a reflectarray for satellite applications is accomplished in this letter. The use of full-wave electromagnetic methods to compute the reflectarray elements in the design process has been replaced by the characterization of the reflectarray elements by artificial neural networks (ANNs). The antenna is designed to provide coverage in Ku-band to a European region defined by EuTELSAT. The results obtained using ANN in the design are compared to those obtained from the method of moments (MoM), and a good agreement is achieved. The speedup factor between reflectarray optimization by both the ANN and the MoM is in the order of 10 . Hence, the use of ANN is presented here as a promising fast technique in the design of reflectarrays.Index Terms-Artificial neural networks (ANNs), contoured-beam reflectarray, reflectarray, reflectarray design.

show abstract

An efficient synthesis approach for electromagnetic near‐ and far‐field contoured patterns using alternative narrow‐beam field functions transformed from the radiations of linearly excited array antennas with least computational complexity

Chou

2015

Radio Science

View full text Add to dashboard Cite

This paper presents an effective scheme to accelerate the computational efficiency in synthesizing the electromagnetic contoured patterns spanned by the radiations of phased array antennas, which is applicable to synthesize both the near-and far-field patterns. The core concept is to adapt/create closed-form and simple formulations with least computational unknowns to be used in the iterative synthesis procedure. The efficiency is assured by avoiding the cumbersome numerical integration/summation for the radiation fields in the synthesis procedure. Thus, the scheme first transforms the conventional field basis functions (FBFs) defined by the radiations of every array elements into a set of global FBFs arising from the radiations of a set of overlapped virtual arrays, where each of the virtual arrays is properly excited by a Gaussian taper to avoid the ray caustic problems encountered in the asymptotic evaluations. The new FBFs (NFBFs) created by this transformation have radiation fields focused in narrow spans in contrast to the wide patterns of conventional FBFs and may reduce the number of FBFs in the computation if a small coverage area is considered. Furthermore, the closed-form formulations of global NFBFs are obtained by asymptotic evaluation and may dramatically reduce the computational time. This approach is implemented with the use of successive projection method, which also provides closed-form formulations to update the excitations in each iterative step, to synthesize the near-and far-field contoured patterns to demonstrate the feasibility and efficiency.

show abstract

ANN Characterization of Multi-Layer Reflectarray Elements for Contoured-Beam Space Antennas in the Ku-Band

Cited by 54 publications

References 21 publications

Accurate characterization of multi-resonant reflectarray cells by artificial neural networks

Accurate characterization of multi-resonant reflectarray cells by artificial neural networks

Design of a Contoured-Beam Reflectarray for a EuTELSAT European Coverage Using a Stacked-Patch Element Characterized by an Artificial Neural Network

An efficient synthesis approach for electromagnetic near‐ and far‐field contoured patterns using alternative narrow‐beam field functions transformed from the radiations of linearly excited array antennas with least computational complexity

Contact Info

Product

Resources

About