Artificial neural networks in their simplest forms for analysis and synthesis of RF/microwave planar transmission lines

Güneş, Filiz; Türker, Nurhan

doi:10.1002/mmce.20103

Cited by 14 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…and the coefficients a i , a 0 i , and b must be chosen in order to minimize the regression risk in the dual problem. In (16), the kernel function K(m i , m) 5 h/(m i ),/(m)i works on the original space M. Commonly used kernels are polynomial and radial kernels [2].…”

Section: Synthesismentioning

confidence: 99%

“…A number of investigators have proposed such formulas, which are based on approximate analytical solutions along with empirical adjustment of various numerical constants so as to achieve the desired accuracy (see [13][14][15]). Furthermore, the four main types of the RF/Microwave planar transmission lines are analyzed using one simple ANN and then synthesized in the second ANN by reversing the analysis process [16]. Similar to the work in [16], the SVR is utilized in this work as a universal function-approximator in the modeling of microstrip transmission lines and for this purpose, the empirical analytical formulas in the [11][12][13] are employed in the generation of the training and test data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Support vector design of the microstrip lines

Güneş

Tokan

Gürgen

2008

Int J RF and Microwave Comp Aid Eng

Self Cite

View full text Add to dashboard Cite

In this article, the support vector regression is adapted to the analysis and synthesis of microstrip lines on all isotropic/anisotropic dielectric materials, which is a novel technique based on the rigorous mathematical fundamentals and the most competitive technique to the popular artificial neural networks (ANN). In this design process, accuracy, computational efficiency and number of support vectors are investigated in detail and the support vector regression performance is compared with an ANN performance. It can be concluded that the ANN may be replaced by the support vector machines in the regression applications because of its higher approximation capability and much faster convergence rate with the sparse solution technique. Synthesis is achieved by utilizing the analysis blackbox bidirectionally by reverse training. Furthermore, by using the adaptive step size, a much faster convergence rate is obtained in the reverse training. Besides, design of microstrip lines on the most commonly used isotropic/anisotropic dielectric materials are given as the worked examples.

show abstract

Section: Synthesismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Support vector design of the microstrip lines

Güneş

Tokan

Gürgen

2008

Int J RF and Microwave Comp Aid Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, in microwave application conventional computer aided design(CAD) has been coupled with ANN to obtain an efficient and accurate results that can be seen as a candidate with massive computations such as: broadband nonlinear RF/microwave circuits [15], calculation of Green's Functions [16], analysis and synthesis of RF/microwave planar transmission lines [17], computational electromagnetics [18], and modeling of microstrip lines [19].…”

Section: Introductionmentioning

confidence: 99%

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

Hayati

Lotfi

2011

Micro & Optical Tech Letters

View full text Add to dashboard Cite

In this article, S‐parameters of compact microstrip resonator cell are predicted using artificial neural network (ANN) to design class of elliptic function compact low‐pass filter with sharp cut‐off frequency. The ANN structure used in this work is multilayer perceptron (MLP) neural network. The data used for training the network is obtained using electromagnetic (EM) simulator. We compared measurement results and simulation results of filter by EM‐simulator and ANN. The results show accurate attenuation at cut off frequency. In comparison with EM‐simulator, simulation results by ANN have merits such as: mitigated consumption time, efficient performance and good accuracy. © 2011 Wiley Periodicals, Inc. Microwave Opt Technol Lett 53:1323–1328, 2011; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.26008

show abstract

“…Yet neural network models are simple, and model evaluation is very fast. Recent works have let to their use for modeling of both active and passive components such as transistors [5,6] planar transmission line microstrip, coplanar wave (CPW) guides [7] vias, CPW discontinuities, and spiral inductors [8].…”

Section: Introductionmentioning

confidence: 99%

A novel neural Smith chart for use in microwave circuitry

Güneş

Çağlar

2009

Int J RF and Microwave Comp Aid Eng

View full text Add to dashboard Cite

In this article, briefly the Smith chart is mapped with an artificial neural network (ANN) covering its whole details to be exploited CAD of the microwave circuitry. Thus, relative to the similar works in the existing literature, this article provides the continuous Smith chart domain to facilitate the ''Smith chart'' methodology in solving the highly nonlinear transformation equations between the rectangular impedance and polar reflection planes for an infinite number of passive impedance to be used in design tasks of the microwave circuits. Data ensembles for the training and testing processes are obtained from the systematically selected locations on the Smith chart with the adaptive radius sampling algorithm. The ANN architecture is also simple, which consists of the two simple multilayer perceptron (MLP) modules with the common inputs which are the termination Z S 5 R S 1 jX S , line {', Z 0 } operation bandwidth B between the defined f min , f max and the dielectric e. Briefly, the outputs of these ANN modules are the standing waves and the impedance transformation, which are the characteristic features of the transmission line circuits. Activation of the hidden layers of the modules are performed by the tangential-sigmoid type of function while the output layers are activated linearly. Furthermore, the neural unit element (NUE) is defined by the two independent neural networks as problems in the forward and reverse directions to be incorporated into the analysis and design algorithms of the unit element (UE). This can also be considered as solving the simultaneous nonlinear equation set for (', Z 0 ) parameters of the required impedance transformations Z OUT (x) 5 R OUT (x) 1 X OUT (x) from the given complex termination Z S 5 R S 1 jX S . Applications of the Neural Smith chart are given by the numerous examples with the proved accuracy. Thus it has been verified that this neural Smith chart can be exploited for the whole classical transmission line theory including impedance matching.

show abstract

Artificial neural networks in their simplest forms for analysis and synthesis of RF/microwave planar transmission lines

Cited by 14 publications

References 9 publications

Support vector design of the microstrip lines

Support vector design of the microstrip lines

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

A novel neural Smith chart for use in microwave circuitry

Contact Info

Product

Resources

About