Support vector design of the microstrip lines

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 black‐box 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. © 2008 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2008.     

Modeling of microstrip lines using neural networks: Applications to the design and analysis of distributed microstrip circuits

In this article, two models for solving microstrip lines are presented. The models utilize radial-basis-function neural networks. Using the first model, one estimates the effective dielectric constant and the width of the microstrip line, knowing its characteristic impedance and the frequency. The second model provides the effective dielectric constant and the characteristic impedance of the line based on knowledge of its width and the frequency. Besides their remarkably fast responses, the proposed models are capable of estimating the required quantities with very high accuracy. The potential of the proposed models is demonstrated in the design and analysis of two distributed microstrip circuits. © 2004 Wiley Periodicals, Inc. Int J RF and Microwave CAE 14, 166–173, 2004.     

Neural network analysis of switchability of microstrip rectangular patch antenna printed on ferrite material

A switchable microstrip rectangular patch antenna printed on ferrite substrate in the X‐band is presented using general artificial neural network (ANN) analysis. The ferrite substrate offers a number of unique radiation characteristics including switchable and polarized radiations from a microstrip antenna with DC magnetic biasing. In such a case, for particular frequency most of the power is converted into magnetostatic waves and little radiates into air. Subsequently, the antenna behaves as switch off, in the sense that it effectively absent as radiator. Both synthesis and analysis are mainly focused on the switchability of antenna. In this work, radial basis function (RBF) networks are used in ANN models. Synthesis is defined as the forward side and then analysis as the reverse side of the problem. Here, the analysis is considered as a final stage of the design procedure, therefore, the parameters of the analysis ANN network are determined by the data obtained reversing the input–output data of the synthesis network. In the RBF network, the spread value was chosen as 0.01, which gives the best accuracy. RBF is tested with 100 sample frequencies but trained only for particular cutoff 15 sample frequencies. © 2009 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

Microstrip antenna design using artificial neural networks

Neural‐network computational modules have recently gained recognition as an unconventional and useful tool for RF and microwave modeling and design. Neural networks can be trained to learn the behavior of passive/active components/circuits. This work describes the fundamental concepts in this emerging area aimed at teaching RF/microwave engineers what neural networks are, why they are useful, when they can be used, and how to use them to model microstrip patch antenna. This work studies in‐depth different designs and analysis methods of microstrip patch antenna using artificial neural‐network and different network structure are also described from the RF/microwave designer's perspective. This article also illustrates two examples of microstrip antenna design and validating the utility of ANN in the area of microstrip antenna design. © 2009 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

An efficient method for analyzing nonuniformly coupled microstrip lines

This article presents an efficient method for analyzing nonuniformly coupled microstrip lines. By choosing a modal‐transformation matrix, the coupled nonlinear differential equations describing the symmetric nonuniformly coupled microstrip lines are decoupled using even‐ and odd‐mode parameters; the original problem is thus transformed into two single nonuniform transmission lines. A power‐law function of arbitrary order and having two adjustable parameters is chosen to better approximate the equation coefficients. Closed‐form ABCD matrix solutions are obtained and used to calculate the S‐parameters of nonuniformly coupled microstrip lines. Numerical results for two examples are compared with those from a full‐wave commercial package and experimental ones in the literature in order to demonstrate the accuracy and efficiency of this method. This highly efficient method is employed to optimize a cosine‐shape 10‐dB codirectional coupler, which has good return loss and high directivity performance over a wide frequency range. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.     

Field coupling to nonuniform coupled microstrip transmission lines

An efficient method for frequency‐domain and transient analysis of the nonuniform lossless coupled microstrip transmission lines excited by external electromagnetic waves is presented. The nonuniform coupled microstrip transmission lines system is first decomposed into a large number of uniform sections called steplines. Using the modal decomposition method, each step is modeled as a linear system with matrix coefficients. The effects of the external excitation are then modeled as inputs in the proper positions of the system. Finally, the solution in the frequency domain is obtained, and the fast Fourier transform algorithm is used to find the time‐domain response of the lines. © 2003 Wiley Periodicals, Inc. Int J RF and Microwave CAE 13: 215–228, 2003.     

山火的无线传感与RBF分析研究

研发了一种基于智能无线传感器网络的电力铁塔山火监测分析系统,系统通过对楚雄腰站变电站输电线路周围山地火灾诱发参数情况进行远程在线监测,对监测数据进行趋势分析,对山火发生情况下产生的数据变化进行分析。并采用径向基函数（RBF）神经网络进行回归拟合,预测火灾危险等级。经过测试样本的验证,表明 RBF 神经网络对于山火监测有较高的准确率,可以对监测数据进行预测分析,适用于山火预测。     

Planar electromagnetic bandgap structures

This article presents various novel and conventional planar electromagnetic bandgap (EBG)‐assisted transmission lines. Both microstrip lines and coplanar waveguides (CPWs) are designed with circular, rectangular, annular, plus‐sign and fractal‐patterned EBGs and dumbbell‐shaped defected ground structure (DGS). The dispersion characteristics and the slow‐wave factors of the design are investigated. © 2006 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2006.     

Frequency‐dependent maximum average power‐handling capabilities of single and edge‐coupled microstrip lines on low‐temperature co‐fired ceramic (LTCC) substrates

The frequency‐dependent maximum average power‐handling capabilities (APHCs) of single and edge‐coupled microstrip lines (MLs) on low‐temperature co‐fired ceramic (LTCC) substrates are investigated in this article. Although LTCCs have excellent high‐frequency performance, the thermal conductivity is about 2.0–3.0 W/m°C, which is much smaller than that of sapphires, alumina, silicon, and GaAs. The method used to predict the APHC is based on the calculated conductive and dielectric attenuation constants for different modes, and the proposed multilayer thermal model for the temperature rise. Numerical investigations are carried out to examine the effects of geometric and physical parameters on the wideband pulse responses and maximum APHC for single finite‐ground thin‐film and coupled MLs, respectively. Methodologies to enhance the power‐handling capability which are useful in the design of high‐density microstrip interconnects on or embedded in multi‐layer LTCCs are proposed. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2006.     

ANN‐based modeling of compact impedance‐varying transmission lines with applications to ultra‐wideband Wilkinson power dividers

The modeling of the physical and electrical characteristics of microstrip non‐uniform transmission lines (NTLs) utilizing artificial neural networks (ANNs) is investigated. The fundamental equations and constraints for designing variable impedance transmission lines are first presented. Then, a proof‐of‐concept example of a compact non‐uniform matching transformer and the counterpart modeled version is elaborated for source and load impedances Z_s and Z_l, respectively, at 0.5 GHz. For comparison purposes, weights and biases of the proposed ANN are established with three different training techniques; namely: backpropagation (BP), Quasi‐Newton (QN), and conjugate gradient (CG); at which the ABCD matrix, impedance variations, input port matching (S₁₁), and transmission parameter (S₂₁) are set as benchmarks to examine the validity of the trained model. The concept is then extended to model a NTL ultrawideband (UWB) Wilkinson power divider (WPD) with three resistors for improved isolation. S‐parameters derived from the trained ANN outputs are close to those obtained by the traditional time‐consuming optimization procedure, and show input and output ports matching and isolation of below ?10 dB, and acceptable values of transmission parameters over the 3.1 GHz to 10.6 GHz band. The resulting models outperform traditional optimizations in terms of simulation time and reserved resources with comparable accuracy. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:563–572, 2015.     

Modeling of microstrip antennas using neural networks techniques: A review

Artificial neural networks modeling have recently acquired enormous importance in microwave community especially in analyzing and synthesizing of microstrip antennas (MSAs) due to their generalization and adaptability features. A trained neural model estimates response very fast, which is nearly equal to its measured and/or simulated counterpart. Thus, it completely bypasses the repetitive use of conventional models as these models need rediscretization for every minor changes in the geometry, which itself is a time‐consuming exercise. The purpose of this article is to review this emerging area comprehensively for both analyzing and synthesizing of the MSAs. During reviewing process, some untouched cases are also observed, which are essentially required to be resolved for antenna designers. Unique and efficient neural networks‐based solutions are suggested for these cases. The proposed neural approaches are validated by fabricating and characterizing of the prototypes too. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:747–757, 2015.     

Very accurate and simple CAD models based on neural networks for coplanar waveguide synthesis

Very accurate and simple neural models for coplanar waveguide (CPW) synthesis are proposed. The results obtained from these neural models are compared with the results of quasi‐static analysis, the other synthesis formulas, and other experimental works. The accuracy of the neural models is found to be better than 0.4% for 11,206 CPW samples. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.     

Novel neural network modeling method and applications

Neural networks play an important role for designing the parametric model of electromagnetic structures. The current neural network methods are unfit for a circuit model with many input variables because it is costly to extract a large number of the training data and test data to complete the highly nonlinear mapping approximation. This article proposes a new neural network modeling method—the multidimensional neural network model, which can be used to solve the issue of multivariable radiofrequency and microwave passive device modeling. The entire multidimensional neural network modeling problem is simplified into a set of neural network submodels through decomposition method. Then the submodels are combined into an equivalent model, and the final entire model is produced through the neural‐network mapping model developed with the submodels and equivalent model. A microstrip hairpin filter model is developed using the proposed method. The simulation results show the correctness and the effectivity of the proposed method. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:769–779, 2015.     

Application of temporal difference learning rules in short‐term traffic flow prediction

Studying dynamic behaviours of a transportation system requires the use of the system mathematical models as well as prediction of traffic flow in the system. Therefore, traffic flow prediction plays an important role in today's intelligent transportation systems. This article introduces a new approach to short‐term daily traffic flow prediction based on artificial neural networks. Among the family of neural networks, multi‐layer perceptron (MLP), radial basis function (RBF) neural network and wavenets have been selected as the three best candidates for performing traffic flow prediction. Moreover, back‐propagation (BP) has been adapted as the most efficient learning scheme in all the cases. It is shown that the coefficients produced by temporal signals improve the performance of the BP learning (BPL) algorithm. Temporal signals provide researchers with a new model of temporal difference BP learning algorithm (TDBPL). The capability and performance of TDBPL algorithm are examined by means of simulation in order to prove that the wavelet theory, with its multi‐resolution ability in comparison to RBF neural networks, is a suitable algorithm in traffic flow forecasting. It is also concluded that despite MLP applications, RBF neural networks do not provide negative forecasts. In addition, the local minimum problems are inevitable in MLP algorithms, while RBF neural networks and wavenet networks do not encounter them.     

Average power handling capability of multilayer microstrip lines

This article describes the average power handling capability (APHC) of multilayer microstrip lines, including the effect of mismatch at the terminations. The data presented herein are validated by considering an example of a 12‐W monolithic microwave integrated circuit power amplifier fabricated using multilayer low‐loss microstrip technology. The calculated value of APHC for a 50‐Ω line of a 75‐μm‐thick GaAs substrate is 1445 W at 10 GHz, whereas the corresponding value for a multilayer microstrip that has 10‐μm‐thick polyimide is only 44 W. At 40 GHz, these values are reduced by a factor of 2. © 2001 John Wiley & Sons, Inc. Int J RF and Microwave CAE 11: 385–395, 2001.     

A novel method for crosstalk reduction in coupled pair microstrip lines

This article demonstrates novel ideas for mitigation of far‐end as well as near‐end crosstalk in coupled pair microstrip lines (CPMLs) by means of defected microstrip structure (DMS). Simple equations and models for analysis and design of a DMS are presented and extracted. Different configurations of DMS‐CPMLs are introduced, and their performances in crosstalk reduction are compared. Finally, the best configuration for far‐end crosstalk reduction is fabricated and tested. A maximum of 35 dB reduction in far‐end and 38 dB reduction in near‐end crosstalk are achieved. The signal integrity performance of the structure is also verified by eye‐diagrams. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012.     

Miniaturized planar ferrite junction circulator in the form of substrate‐integrated waveguide

The theoretical analysis and engineering implementation of the planar substrate‐integrated waveguide (SIW) ferrite junction circulator have been proposed in this article. The ferrite junction circulator is implemented in the form of SIW, taking the features of low profile, small volume and easy integration with other planar circuits. The design strategies of the device have been introduced, including the design consideration of the microstrip transition. One C‐band prototype of SIW ferrite junction circulator has been fabricated and measured. The experimental results indicate the bandwidth is about 33% at −15 dB isolation and the maximum isolation is near 40 dB. However, the insertion loss is a little big, owing to the imperfect dielectric material and fabrication inaccuracy. The SIW ferrite junction circulator and the microstrip transition are integrated into a same substrate, resulting in a very compact planar ferrite junction circulator and indicating potential applications in integrated communication and radar systems. © 2007 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2008.     

Estimation of radiation characteristics of different slotted microstrip antennas using a knowledge‐based neural networks model

In this article, a common neural model incorporated with prior knowledge is suggested for estimating radiation characteristics (i.e., resonance frequencies, gains, directivities, antenna efficiencies, and radiation efficiencies) of four‐slotted microstrip antennas with inserted air‐gap for dual‐frequency operation. By incorporating prior knowledge in the existing neural networks, the required numbers of training patterns are drastically reduced. Further, the proposed approach is capable for accurately estimating the radiation characteristics in extrapolation region too. The proposed neural approach is also validated with measured results. A very good agreement is achieved in simulated, estimated, and measured results. © 2014 Wiley Periodicals, Inc. Int J RF and Microwave CAE 24:673–680, 2014.     

A review of genetic algorithms applied to training radial basis function networks

The problems associated with training feedforward artificial neural networks (ANNs) such as the multilayer perceptron (MLP) network and radial basis function (RBF) network have been well documented. The solutions to these problems have inspired a considerable amount of research, one particular area being the application of evolutionary search algorithms such as the genetic algorithm (GA). To date, the vast majority of GA solutions have been aimed at the MLP network. This paper begins with a brief overview of feedforward ANNs and GAs followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.     

Neural model of microwave cylindrical cavity loaded with arbitrary‐raised dielectric slab

A combined knowledge‐based neural‐multilayer perceptron (KBN‐MLP) model to account for a loading effect of arbitrary raised dielectric slab in a microwave cylindrical metallic cavity is presented. Existing partial knowledge about the resonant frequency behavior of loaded cavity is incorporated in the KBN part of suggested model. In comparison with the model based on classical MLP network, more accurate and efficient resonant frequencies calculation is achieved. © 2008 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2009.