An ANN Application for Fault Finding in Antenna Arrays

Patnaik, Amalendu; Choudhury, Balamati; Pradhan, Priyam; Mishra, Rabindra Kishore; Christodoulou, C.G.

doi:10.1109/tap.2007.891557

Cited by 95 publications

(48 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Faults in antennas distort the radiation pattern and cause sharp variations in the field intensity around an antenna array which increases the side lobes and ripple level of the power pattern [26] [29]. The patterns can be restored however through readjustment of the excitations of the non-defective elements to produce a pattern with respect to the original [21] [30].…”

Section: Fault Findingmentioning

confidence: 99%

“…Information on the number and location of the faulty elements is required and these methods generally find it difficult to handle fault diagnosis. Hence new approaches are required [20][21][22][25] [26].Built in monitoring and calibration systems are complex and costly [33].The digital beamforming in smart antenna arrays provides possibility of failure correction and thus a cost-effective solution to hardware replacement [20].Artificial neural networks (ANNs) [10] [14] are non linear and use simple mathematical operators. They are able to locate faults by performing mapping between the damaged radiation pattern/s with the position of the fault element/s.…”

Section: Introductionmentioning

confidence: 99%

“…By using ANNs it is possible to recalculate and produce the radiation pattern close to the original pattern [24][25] [26][29] [31][32]. The adaline [24], multilayer perceptron (MLP) [21][ [25][26][33]the radial basis function (RBF) neural networks [31][32]and the discrete mean field neural network based on Vidyasagar net [22] and have been found quite effective in finding faults in the antenna arrays. Genetic algorithms have also been very effectively used in fault diagnosis of arrays as mentioned ahead [20] [21][23] [30].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Applications of Neural Networks and Genetic Algorithms in Fault Diagnostics for Antenna Arrays

Mishra¹

2013

IOSR-JEEE

View full text Add to dashboard Cite

Section: Fault Findingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Applications of Neural Networks and Genetic Algorithms in Fault Diagnostics for Antenna Arrays

Mishra¹

2013

IOSR-JEEE

View full text Add to dashboard Cite

“…With these approaches one can determine the excitation coefficients of each radiating element and detects the failures by comparing the reconstructed ones with the nominal currents. Several deterministic and stochastic techniques have been developed [4][5][6][7][8][9] in the last years. Among the stochastic approaches, we point out the learning algorithms based on examples, such as neural networks [4,5], and the genetic algorithms based approaches [6,7].…”

Section: Motivationsmentioning

confidence: 99%

“…Several deterministic and stochastic techniques have been developed [4][5][6][7][8][9] in the last years. Among the stochastic approaches, we point out the learning algorithms based on examples, such as neural networks [4,5], and the genetic algorithms based approaches [6,7]. These methods have the advantage to require small amount of samples of the radiated field and, in many cases, only amplitude data [7], but, due to the high size of search space, they can have poor performances.…”

Section: Motivationsmentioning

confidence: 99%

Large Phased Arrays Diagnostic via Distributional Approach

Buonanno¹,

D’Urso²,

Cicolani³

et al. 2009

PIER

View full text Add to dashboard Cite

Abstract-A deterministic method for detecting faulty elements in phased arrays is proposed and tested against experimental and numerical data. The solution approach assumes as input the amplitude and phase of the near-field distributions and allows to determine both positions and currents of radiating elements. The corresponding non linear inverse problem is properly solved by exploiting the distributional approach, which allows to cast the initial problem to the solution of a linear one, whose solution is made stable by adopting a proper regularization scheme based on the Truncated Singular Value Decomposition tool. The results fully confirm accuracy of the proposed technique. MOTIVATIONSMany applications, ranging from sonar, radar and space communications, need for fully active phased arrays [1][2][3]. These antennas have several hundreds of radiating elements or proper sub-arrays [2,3], and the possibility of their failure strongly increases. These element failures can cause sharp variations in the aperture field across the array aperture, thus increasing both the sidelobes and the ripple level of the far-field radiation pattern. In order to know which element or elements are damaged, active antennas can include calibration systems. TheseCorresponding author: M. D'Urso (mdurso@selex-si.com).

show abstract

Machine learning‐enabled two‐port wideband MIMO hybrid rectangular dielectric resonator antenna for n261 5G NR millimeter wave

Rai,

Ranjan,

Kumar

et al. 2024

Int J Communication

View full text Add to dashboard Cite

SummaryIn this article, a two‐port multiple‐input multiple‐output (MIMO) hybrid rectangular dielectric resonator antenna (DRA) with machine learning (ML) approach for the n261 5G New Radio (NR) application is presented. The proposed antenna is designed on an RT/duroid 5880 (Ɛr = 2.2) substrate activated by 50 Ω, L‐shaped microstrip slot feeds beneath both DRAs. The isolation is more than 19 dB, and the gain is 10 dBi in the operating frequency range. The proposed antenna is optimized through knowledge‐based neural networks (KBNN), artificial neural networks (ANNs), and ML. The optimal design parameters of the proposed antenna are accomplished using the ML optimization approach, which includes ridge regression, ANNs, and KBNN. KBNN ML techniques provide 96.88% accuracy and correctly predict the S‐parameters of the proposed antenna. The MIMO diversity parameters like envelope correlation coefficient (ECC), diversity gain (DG), total active reflection coefficient (TARC), and channel capacity loss (CCL) are calculated and found within the limits. Hence, the proposed antenna is used for 5G NR mm‐wave application.

show abstract

An ANN Application for Fault Finding in Antenna Arrays

Cited by 95 publications

References 5 publications

A Survey on Applications of Neural Networks and Genetic Algorithms in Fault Diagnostics for Antenna Arrays

A Survey on Applications of Neural Networks and Genetic Algorithms in Fault Diagnostics for Antenna Arrays

Large Phased Arrays Diagnostic via Distributional Approach

Machine learning‐enabled two‐port wideband MIMO hybrid rectangular dielectric resonator antenna for n261 5G NR millimeter wave

Contact Info

Product

Resources

About