Temperature‐dependent models of low‐noise microwave transistors based on neural networks

Neural networks are proposed for efficient temperature‐dependent modeling of small‐signal and noise performances of low‐noise microwave transistors over a wide temperature range. The proposed models can be based either on neural networks only or on a combination of neural networks and empirical transistor models. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.     

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.     

Constitutive relations for nonlinear modeling of Si/SiGe HBTs using an ANN model

In this article, we demonstrate how the constitutive relations for the nonlinear modeling of hetro‐junction bipolar transistors (HBTs) can be based on an artificial neural network (ANN) model representation.. The model is implemented using a commercial microwave simulator, and has been validated by DC and nonlinear measurements. Excellent agreement is obtained as compared with the results of the DC measurements, and the model predicts well the higher‐order harmonics in a single tone test.. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.     

Enhancement of time domain analysis and optimization through neural networks

An efficient computational approach to time domain microwave design and optimization is presented. In particular, artificial neural networks are coupled with a full‐wave time domain simulator in order to model and optimize microwave structures. Furthermore, neural networks are used to predict the late time response from the early time response of a structure to accelerate the convergence of time domain simulations, particularly in the case of high‐Q structures such as filters and resonators. The combination of neural networks with a time domain TLM solver is demonstrated by means of a design example of an iris‐coupled band pass filter. The results demonstrate the dramatic gain in speed and numerical efficiency enabled by this approach to optimizing and modeling microwave devices. © 2007 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2007.     

Development of VHDL‐AMS neuro‐fuzzy behavioral models for RF/microwave passive components

The new generation of System‐on‐Chip (SoC) incorporates digital, analogue, RF/microwave and mixed‐signal components. Such circuits impose to reconsider the traditional design methods. Mixed‐signal designers need novel design methodologies which will have to include accurate behavioral libraries of devices and processes into hierarchical design flows. Thus, this paper describes a behavioral modeling approach which generates neuro‐fuzzy‐based models for RF/microwave devices. The models, so obtained, can be easily integrated into a VHDL‐AMS simulator. This modeling approach is applied to a microwave tunable phase shifter and it is illustrated by the development of a VHDL‐AMS model library for RF/microwave applications. © 2007 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2007.     

An impedance and power flow measurement system suitable for on‐wafer microwave device large‐signal characterization

A reflection based and thru‐less de‐embedding technique for impedance and absolute power flow measurements suitable for on‐wafer large‐signal characterization of microwave transistors is proposed. The developed system was tested for both 50 Ω and non‐50 Ω terminated passive and active devices and the results obtained are compared with those obtained with commercial instruments. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

Response correction techniques for surrogate‐based design optimization of microwave structures

Simulation‐based optimization has become an important design tool in microwave engineering. However, using electromagnetic (EM) solvers in the design process is a challenging task, primarily due to a high‐computational cost of an accurate EM simulation. In this article, we present a review of EM‐based design optimization techniques exploiting response‐corrected physically based low‐fidelity models. The surrogate models created through such a correction can be used to yield a reasonable approximation of the optimal design of the computationally expensive structure under consideration (high‐fidelity model). Several approaches using this idea are reviewed including output space mapping, manifold mapping, adaptive response correction, and shape‐preserving response prediction. A common feature of these methods is that they are easy to implement and computationally efficient. Application examples are provided. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012.     

Application of neural networks in space‐mapping optimization of microwave filters

In this paper, a design methodology combining coupling matrix representation of filters, neural models and space‐mapping techniques is presented for further enhancement of optimization efficency of microwave filters. Neural models are developed for both initial dimension generation and design parameter sensitivity analysis. Combining neural models of filter substructures with space‐mapping optimization, the total number of EM simulations of the complete filter structure is significantly reduced. The improvement in efficiency over conventional method is demonstrated using simulation and measurement results of both end‐coupled and side‐coupled waveguide dual‐mode pseudo‐elliptic filters. The total CPU times for design and optimization are reduced by 50% to 70 %.© 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012.     

Space mapping algorithm with improved convergence properties for microwave design optimization

Space mapping is one of the most efficient techniques for microwave design optimization. Still, it is well known that space mapping algorithms may suffer from convergence issues, which are consequences of certain fundamental features. In many cases, the space mapping algorithm quickly finds an acceptable solution, but then falls into oscillations with respect to the design variables and/or the objective function value; as a consequence, there are no clear criteria for terminating the optimization process. In this article, we investigate some techniques for improving the convergence properties of the space mapping algorithm, which are based on the general convergence results for such algorithms. Our approach is verified using several microwave design optimization problems. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

A Krylov‐subspace technique for the simulation of integrated RF/microwave subsystems driven by digitally modulated carriers

This article introduces a new approach to the analysis of nonlinear RF/microwave systems or subsystems described at the circuit level and excited by sinusoidal carriers modulated by arbitrary baseband signals. The circuit is simulated by a sequence of harmonic‐balance analyses based on a Krylov‐subspace method driven by an inexact Newton loop, and suitably modified to account for coupling with a finite number of preceding time instants. The Jacobian matrix of the nonlinear solving system is computed by an exact algorithm, and its structure is shown to be very well suited for the application of Krylov‐subspace techniques such as the GMRES method. In this way, problems with many millions of nodal unknowns may be efficiently tackled at the workstation level. ©1999 John Wiley & Sons, Inc. Int J RF and Microwave CAE 9: 490–505, 1999.     

Efficient numerical CAD technique for RF and microwave amplifiers

The real frequency technique (RFT) is an efficient numerical method to design the matching networks of microwave active circuits. It provides several advantages over most of the usual techniques. By directly including measured scattering and noise parameter data, it does not require any rational functions or circuit models. Moreover, a predetermined matching circuit topology is not necessary. The described method also allows the design of stability-guaranteed broadband circuits when employing potentially unstable transistors. With the Levenberg–Merquardt algorithm, the RFT can be applied to simultaneously optimize transducer power gain, input and output VSWRs, noise figure, and group delay of a multistage microwave active circuit. Applications as different as low-noise amplifier, active filter, or broadband amplifier are possible. © 1998 John Wiley & Sons, Inc. Int J RF and Microwave CAE 8: 131–141, 1998.     

An efficient multilayered shielded microwave circuit analysis method based on neural networks

In previous works, a neural network based technique to analyze multilayered shielded microwave circuits was developed. The method is based on the approximation of the shielded media Green's functions by radial‐basis‐function neural networks (RBFNNs). The trained neural networks, substitute the original Green's functions during the application of the integral equation approach, allowing a faster analysis than the direct solution. In this article, new and important improvements are applied to the training of the RBFNNs, which permit a reduction in the approximation error introduced by the neural networks. Furthermore, outstanding time reductions in the analysis of printed circuits are achieved, clearly outperforming the former technique. The main improvement consists on a better processing of the Green's function singularity near the source. The singularity produces rapid variations near the source that makes difficult the neural network training. In this work, the singularity is extracted in a more suitable fashion than in previous works. The functions resulting from the singularity extraction present a smooth behavior, so they can be easily approximated by neural networks. In addition, a new subdivision strategy for the input space is proposed to efficiently train the neural networks. Two practical microwave filters are analyzed using the new techniques. Comparisons with measured results are also presented for validation. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

Waveform engineering: State‐of‐the‐art and future trends (invited paper)

The term waveform engineering denotes all those circuit design techniques that are based on shaping the transistor voltage and current waveforms. From a general perspective, these design techniques can be grouped in two main categories according to the adopted design tool: measurement‐ and model‐based. In the last two decades, thanks to the proliferation of setups enabling calibrated waveform acquisition at microwave frequencies, waveform engineering has attracted continuously increasing interest in the microwave engineering community. In this article, a comprehensive analysis of the waveform‐engineering based design techniques is reported, paying particular attention to the advantages and drawbacks associated to each approach.     

A new neural network technique for the design of multilayered microwave shielded bandpass filters

In this work, we propose a novel technique based on neural networks, for the design of microwave filters in shielded printed technology. The technique uses radial basis function neural networks to represent the non linear relations between the quality factors and coupling coefficients, with the geometrical dimensions of the resonators. The radial basis function neural networks are employed for the first time in the design task of shielded printed filters, and permit a fast and precise operation with only a limited set of training data. Thanks to a new cascade configuration, a set of two neural networks provide the dimensions of the complete filter in a fast and accurate way. To improve the calculation of the geometrical dimensions, the neural networks can take as inputs both electrical parameters and physical dimensions computed by other neural networks. The neural network technique is combined with gradient based optimization methods to further improve the response of the filters. Results are presented to demonstrate the usefulness of the proposed technique for the design of practical microwave printed coupled line and hairpin filters. © 2008 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2009.     

Low power quadrature voltage controlled oscillator

In this article, a low voltage low power quadrature voltage controlled oscillator (QVCO) coupled by four P&N transistors is presented. First, a novel negative resistance inductance capacitor (LC) oscillator is described, the N‐metal oxide semiconductor (NMOS) and P‐metal oxide semiconductor (PMOS) transistors are in series with the LC tank in the direct‐current (DC) path, and they generate the required negative resistance to compensate the energy loss of the LC tank and maintain the steady oscillation of the oscillator. Then, based on two identical LC oscillators, four P&N transistors are used as coupling terminals to generate quadrature outputs. The proposed QVCO is designed and simulated with GlobalFoundries' 0.18 μm CMOS RF process. The Cadence IC design tools postlayout simulation results demonstrate that the oscillation frequency of the QVCO can be tuned from 2.0 to 5.6 GHz by adjusting the bias voltage, and the phase noise of the voltage controlled oscillator is ?114 dBc/Hz at 1 MHz offset. Moreover, the proposed QVCO consumes only 2.31 mW from a 1.2 V supply voltage and it occupies a compact area of 0.45 mm² including the bond pads.     

Efficient characterization of millimeter‐wave asymmetric coupled microstrip structures using the quasi‐symmetric approach

To sustain the ever‐increasing use of coupled‐line structures in RF/microwave systems, efficient design tools should be developed. In this article, an original approach combining accuracy and speediness is proposed to shorten time‐to‐market design cycles when such structures are involved. By introducing the quasi‐symmetric approach, CPU‐time required to analyze asymmetric coupled‐lines can be significantly reduced, leading to faster models without sacrificing the overall design accuracy. To achieve this aim, a rigorous formulation was developed and, for the first time, trial functions of C‐ and π‐modes were obtained from the quasi‐symmetric case and applied to the asymmetric case. The proposed approach, easily implementable in commercial simulators, was demonstrated through comparisons with published data. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.