Zlatica Marinkovic

An Extensive Experimental Analysis of the Kink Effects in

This paper, for the first time, analyzes in detail the kink phenomenon in S22 as observed in GaN HEMT technology. To gain a comprehensive understanding, the kink effect (KE) is studied with respect to temperature and bias conditions. The achieved results clearly show that the dependence of the KE on the operating condition should be mainly ascribed to the transconductance, which plays a determinant role in the appearance of this effect. Furthermore, the analysis is extended to investigate the peak in the magnitude of h21 showing its disappearance at low drain-source voltage, due to the increase of the intrinsic output conductance. The importance of this investigation originates from the fact that an accurate and complete characterization of these anomalous phenomena enables microwave engineers to properly take them into account during the modeling and design phases.enables microwave engineers to properly take them into account during the modeling and design phases.

{ S}_{22}

Abstract Extraction of parameters of a small-signal model is the first step in modeling transistors for advanced microwave applications. There are different extraction techniques, mostly based on optimizations or on direct analytical procedures. An alternative to the standard extraction methods are procedures based on the application of artificial neural networks. Namely, an artificial neural network is trained to determine equivalent circuit elements directly from the measured scattering parameters without the need for any additional tuning of the elements. In this study the results of a comprehensive analysis of the neural network based extraction procedures are presented. Stability of the extracted values with the choice of the input set of scattering parameters as well as accuracy of the final small-signal model were examined. Moreover, the influence of the number of measured data necessary for development of reliable neural models was investigated. The extraction procedure was examined for a HEMT transistor working under varying temperature conditions.

and

In this paper, the artificial neural network approach is proposed for prediction purposes of temperature behavior of microwave transistors. Neural networks are used for modeling of temperature dependencies of elements of transistor small-signal models including noise. These dependencies are extracted from transistor signal and noise data referred to a set of temperatures, The developed models are valid in the whole operational range of temperatures.

{ h}_{21}

In this paper an automated procedure for prediction of microwave transistor noise parameters versus temperature is presented. It is based on an improved Pospieszalskis noise model. In order to avoid extraction of device noise model equivalent circuit parameters (ECP) from the measured scattering and noise parameters for each operating temperature, an artificial neural network is introduced for modeling of the ECP temperature dependence. Therefore, it is necessary to acquire the measured data and extract the ECP only for several operating temperatures used for the network training. Once the network is trained and assigned to the considered noise model, the device noise parameters are easily obtained for each temperature from the operating range. It is done without changes in the network structure and without the need for time consuming and complex measurements and optimiztions.

for a GaN HEMT

Low-noise pHEMT transistors, that have excellent performances at microwave frequencies, can be described by their scattering and noise parameters. In this paper, a pHEMT neural model, based on multilayer perceptron neural networks is proposed. The obtained neural models can predict transistors signal and noise performances very efficiently and accurately for a broad range of bias conditions in the operating frequency range.

Analysis and validation of neural network approach for extraction of small-signal model parameters of microwave transistors

This paper presents the results of neural networks application in microwave transistor noise modeling. The neural networks are used to model noise parameters dependence on bias conditions and frequency. In order to improve the modeling, S-parameters are included as inputs of neural models. Once trained, the developed model can be used to predict noise parameters without additional knowledge about noise parameters or any additional computational effort.

Implementation of temperature dependence in small-signal models of microwave transistors including noise

An application of neural networks in microwave FET transistor (MESFET) noise modeling is presented. A multilayer perceptron neural network is implemented to model four transistor noise parameters. Inputs for the neural models include small-signal intrinsic equivalent circuit elements, two equivalent temperatures and frequency, while outputs are noise parameters. Pospieszalskis approach is employed to characterize the noise parameters.

Artificial neural networks for temperature dependent noise modeling of microwave transistors

This paper gives a comprehensive analysis of modeling of the FinFET forward transmission coefficient by using artificial neural networks. Models for the whole device and the actual device obtained after applying the de-embedding procedure the effects of pads, transmission lines, and substrate have been developed and validated in a wide range of bias conditions for frequencies up to 50 GHz. Special attention has been paid to the modeling of kink effects at low frequencies caused by lossy silicon substrate.

Signal and noise neural models of pHEMTs

The aim of this paper is to discuss and compare two neural approaches applied in small-signal modelling of microwave FETs. One of them is completely based on artificial neural networks, while the other is a hybrid model putting together artificial neural networks and an equivalent circuit representation of a microwave transistor. Devices with different gate width are considered in this paper. Different modelling aspects are compared, with special emphasis on the model development procedure and model accuracy.

Neural models of microwave transistor noise parameters based on bias conditions and S-parameters

An improved noise modeling technique for microwave MESFET/HEMT versus temperature is presented. It is based on an artificial neural network (ANN) that produces noise parameters as its outputs for device temperature, S parameters and frequency at its inputs. Once trained, the proposed model can be used for efficient prediction of transistor noise parameters over a wide temperature range. Since the model is based on ANN, all noise-generating mechanisms are included and therefore it is more accurate than empirical transistor models, as it is shown on a numerical example