Neural Modeling of Mutual Coupling for Antenna Array Synthesis

Ayestaran, R.G.; Las-Heras, Fernando; Herrán, L.F.

doi:10.1109/tap.2007.891810

Cited by 34 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Neural Networks [10] are the most popular Machine Learning tool in the scientific literature due in part to their ease of use and their excellent results in solving learning-by-examples problems. They have been used with success in a large number of applications, including the synthesis of FF patterns in antenna arrays [16], [11], [12]. Among the interesting capabilities of NNs, they displace the computational time and cost to a previous training stage when the NN learns the behavior of the system to be modeled, e.g.…”

Section: Neural Network As a Fast Near Field Focusing Methodsmentioning

confidence: 99%

“…Neural Networks (NN) [10] have been used successfully in Far Field (FF) synthesis problems in antenna arrays [11], [12] showing an interesting performance, specially considering that once trained they are able to work without relevant timecost. They concentrate all the computing time in the previous training step, providing solutions almost in real time once trained.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Near-Field Multifocusing of Antenna Arrays Including Element Coupling Using Neural Networks

Ayestaran

2018

Antennas Wirel. Propag. Lett.

View full text Add to dashboard Cite

A novel Near-Field Focusing approach based on the use of artificial Neural Networks is proposed. It is able to provide the set of weights or feeding values that must be applied to the elements of an array so that the global radiation/reception pattern is focused on one or more predefined positions in the near environment. Due to the use of a properly trained Neural Network, it is able to work fast enough for real time applications, such as wireless energy and information transfer where moving devices may require quick adaptation of the radiated field distribution, and hence of the weights applied to the array. Moreover, the training procedure using examples generated with a convenient electromagnetic analysis tool allows taking into account both the radiation pattern of the elements of the array and the coupling effects between them.

show abstract

Section: Neural Network As a Fast Near Field Focusing Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast Near-Field Multifocusing of Antenna Arrays Including Element Coupling Using Neural Networks

Ayestaran

2018

Antennas Wirel. Propag. Lett.

View full text Add to dashboard Cite

show abstract

“…Recently, in [14] neural networks (NN) [15] have been proposed as an alternative to optimization for NFMF applications, adapting previous successful approaches used for far field (FF) synthesis problems [16,17]. The resulting focusing performance is similar to that achieved using optimization techniques, but its time-cost is strongly reduced once the NN has been trained; it is able to calculate the weights required to achieve a given field distribution without relevant delay.…”

Section: Introductionmentioning

confidence: 99%

Support Vector Regression for the Modeling and Synthesis of Near-Field Focused Antenna Arrays

Ayestaran

2019

Electronics

View full text Add to dashboard Cite

The powerful support vector regression framework is proposed in a novel method for near-field focusing using antenna arrays. By using this machine-learning method, the set of weights required in the elements of an array can be calculated to achieve an assigned near-field distribution focused on one or more positions. The computational cost is concentrated in an initial training process so that the trained system is fast enough for applications where moving devices are involved. The increased learning capabilities of support vector machines allow using a reduced number of training samples. Thus, these training samples may be generated with a prototype or a convenient electromagnetic analysis tool, and hence realistic effects, such as coupling or the individual radiation patterns of the elements of the arrays, are accounted for. Illustrative examples are presented.

show abstract

“…For instance, we can find some recent works with the incorporation of Neural Networks [6] or Support Vector Machines [7] to obtain a realistic model of the problem from measured data. However, these techniques depend on the conventional full-wave methods (e.g., Method of Moments, Finite Element Method, Finite Difference Time Domain, etc.)…”

Section: Introductionmentioning

confidence: 99%

Synthesis of Phased Arrays in Complex Environments With the Multilevel Characteristic Basis Function Method

Laviada¹,

Ayestaran²,

Pino³

et al. 2009

PIER

Self Cite

View full text Add to dashboard Cite

Abstract-The aim of this paper is to present a method to carry out the synthesis of large phased arrays when they are affected by complex environments which can influence the radiation pattern. The synthesis is performed with the help of the Multilevel Characteristic Basis Function Method to calculate a matrix relating input voltages and the far field pattern samples. The method is illustrated with the synthesis of a Secondary Surveillance Radar antenna on a turret containing multiple obstacles.

show abstract

Neural Modeling of Mutual Coupling for Antenna Array Synthesis

Cited by 34 publications

References 18 publications

Fast Near-Field Multifocusing of Antenna Arrays Including Element Coupling Using Neural Networks

Fast Near-Field Multifocusing of Antenna Arrays Including Element Coupling Using Neural Networks

Support Vector Regression for the Modeling and Synthesis of Near-Field Focused Antenna Arrays

Synthesis of Phased Arrays in Complex Environments With the Multilevel Characteristic Basis Function Method

Contact Info

Product

Resources

About