“…It was previously demonstrated that neural networks can provide a large-signal description from the small-signal dependence of linear elements with the bias voltages [8] or from pulsed measurements [9]. In this work, neural networks are used to match, simultaneously, the nonlinear I/V characteristic in each bias point, based on DC or pulsed measurements and its derivative parameters up to the 3 rd order [10].…”
A new method for characterization of HEMT distortion parameters, which extracts the coefficents of a Taylor series expansion of Ids(Vgs, Vds), including all cross-terms, is developed from low-frequency harmonic measurements. The extracted parameters will be used either in a Volterra series model around a fixed bias point for 3rd-order characterization of small-signal Ids nonlinearity, or in a large-signal model of Ids characteristic, where its partial derivatives are locally characterized up to the 3rd order in the whole bias region, using a novel neural-network representation. The two models are verified by one-tone and two-tone intermodulation distortion (IMD) tests on a PHEMT device
“…It was previously demonstrated that neural networks can provide a large-signal description from the small-signal dependence of linear elements with the bias voltages [8] or from pulsed measurements [9]. In this work, neural networks are used to match, simultaneously, the nonlinear I/V characteristic in each bias point, based on DC or pulsed measurements and its derivative parameters up to the 3 rd order [10].…”
A new method for characterization of HEMT distortion parameters, which extracts the coefficents of a Taylor series expansion of Ids(Vgs, Vds), including all cross-terms, is developed from low-frequency harmonic measurements. The extracted parameters will be used either in a Volterra series model around a fixed bias point for 3rd-order characterization of small-signal Ids nonlinearity, or in a large-signal model of Ids characteristic, where its partial derivatives are locally characterized up to the 3rd order in the whole bias region, using a novel neural-network representation. The two models are verified by one-tone and two-tone intermodulation distortion (IMD) tests on a PHEMT device
“…This kind of model has the potential to enhance and automate new device model development even if the device theory/equations are not available by computerised training with measured device characteristics. Neural Networks have been used in transistor modelling to replace empirical equations or table based models in frequency domain equivalent circuits [3,4]. Neural Networks for time domain modelling have been imple- mented in the form of a black box amplifier to model existing simulation results [5], the aim being to increase simulation speed.…”
“…uniroma2.it. circuit, giving physical insight into device behavior [1,2,3]. As operating frequency increases, the accurate characterization of passive and active devices for MMIC simulation becomes more and more difficult.…”
Artificial neural networks (ANNs) are presented for the technologyindependent modeling of active devices in MMICs. ANNs trained with S-parameter and DC measurements over the entire bias and frequency operational band are used for the small-signal bias-dependent modeling of a low-noise GaAs HEMT device, without the need of the equivalent circuit parameter extraction. ANNs are also used within the large-signal model of a power MESFET device, modeling the drain-source current I ds and charges Q g and Q d obtained from integration of their partial derivatives. After training and testing, the ANN models have been implemented as two-port networks into a microwave circuit simulator. This enabled the ANN models to be used in the design, analysis, and optimization of microwave/mm-wave circuits. Improved techniques in network building to provide not only accurate but also fast simulation models have been applied.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.