Artificial Neural Network Model of SOS-MOSFETs Based on Dynamic Large-Signal Measurements

Ko, Youngseo; Roblin, Patrick; Landa, Andres Zarate-de; Reynoso-Hernández, J.A.; Nobbe, Dan; Olson, C. W.; Martínez, Francisco

doi:10.1109/tmtt.2014.2298372

Cited by 33 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example of such an embedding device circuit was reported in for the Angelov device model. Another example of such an embedding device circuit was reported in for an artificial neural network . In both cases, when implemented in a circuit simulator, the embedding device model achieves an exact inversions of the device model up to numerical precision.…”

Section: Embedding Device Modelmentioning

confidence: 99%

On the design of GaN Chireix power amplifiers using an embedding device model

Roblin

Chang

Martinez-Rodriguez

et al. 2016

Int J Numerical Modelling

Self Cite

View full text Add to dashboard Cite

As wireless cellular communication keeps expanding toward higher bandwidth, multiband signals, and high frequencies of operation, the design of power efficient radio frequency power amplifiers (PAs) for cellular phone basestations is submitted to more stringent requirements. This paper discusses the promising technique of nonlinear embedding , which may help stream line the design of such PAs. To this order, the design of a GaN radio frequency PA from device modeling to circuit design is presented. The large signal modeling of GaN high-electron-mobility transistors including thermal and trapping memory effects is discussed first. The nonlinear embedding device model is then introduced using the concept of an anti-circuit transfer network. This embedding device model is then applied to the design of a Chireix amplifier. New Chireix design equations are developed to work with the memoryless inner core of the embedding device model, and their validity is confirmed in circuit simulations. The Chireix amplifier is then designed using the multi-harmonic impedance terminations predicted by the embedding device model for the package reference planes. Finally, the resulting Chireix amplifier is implemented in a circuit simulator with the original GaN high-electron-mobility transistors device model and verified in simulations to have a performance approaching that of the originally targeted Chireix at the current reference planes. These theoretical and simulation results demonstrate the potential of the nonlinear embedding PA design technique in the design of Chireix power amplifiers.

show abstract

Section: Embedding Device Modelmentioning

confidence: 99%

On the design of GaN Chireix power amplifiers using an embedding device model

Roblin

Chang

Martinez-Rodriguez

et al. 2016

Int J Numerical Modelling

Self Cite

View full text Add to dashboard Cite

show abstract

“…[15][16][17] One specific ML example is centered on artificial neural network (ANN) techniques, which have found their place as an efficient tool that can be applied for modeling of microwave field-effect transistors (FETs). [18][19][20][21] Based on the application of this technique to small signal modeling of FETs, it provides effective alternatives to conventional methods. [18][19][20] In 19 an ANN-based model is applied to multi-bias small signal modeling of microwave FETs differing in the gate width.…”

Section: Introductionmentioning

confidence: 99%

Modified small‐signal behavioral model for GaN HEMTs based on support vector regression

Geng

Cai

King

et al. 2021

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

A novel, modified small signal behavioral modeling methodology for gallium nitride (GaN) high electron-mobility transistors (HEMTs), based on the support vector regression (SVR) technique, is presented in this paper. Compared with the classic equivalent small-signal circuit model, the proposed model adds an error correction technique, which is developed using SVR techniques. The proposed model maintains accuracy across a broad frequency range, from 1 GHz to 10 GHz. The verification is performed through comparisons with measured multibias S-parameter data performed on an 8 Â 125 μm GaN HEMT device with a 0.25 μm gate feature size. The modified model shows a significant improvement in S-parameter prediction accuracy when compared with the classic equivalent circuit modeling approach.

show abstract

“…After training, the ANN model can respond fast and accurately to the task it learned within the environment of high‐level circuit and system simulation and design. Applications reported in the literature include transistor modeling, amplifier, filter, microwave circuit design and optimization, , etc.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, a space mapping (SM) neuromodeling technique, combining ANNs , with SM, was introduced, exploiting the learning capability of neural networks to automatically map and modify an existing equivalent circuit model to an accurate model. The technique can be applied to the modeling and optimization of passive and small‐signal devices.…”

Section: Introductionmentioning

confidence: 99%

An advanced analytical neuro–space mapping technique with sensitivity analysis for transistor modeling

Zhu

Liu

et al. 2016

Int J Numerical Modelling

View full text Add to dashboard Cite

This paper presents an advanced analytical neuro–space mapping (neuro‐SM) technique for accurate and efficient modeling of transistor devices. This is an improvement over the existing neuro‐SM, which aims to use neural networks to map a given approximate device model towards an accurate model. The proposed neuro‐SM retains the ability of the existing neuro‐SM in modifying the voltage relationship between the given approximate device model and the accurate model. The proposed technique can also map the current relationship between the given model and the accurate model. In this way, the proposed neuro‐SM can produce improved accuracy over the existing neuro‐SM. In addition, analytical formulas of mapping and sensitivities of the direct current, small‐signal S parameter, and large‐signal harmonic of the proposed neuro‐SM model with respect to mapping parameters and coarse‐model parameters are also derived. The sensitivity analysis can be used with a gradient‐based training technique to improve the model training efficiency. The validity and efficiency of the proposed approach are verified through 2 transistor modeling examples and use of the proposed neuro‐SM models in a large‐signal behavior analysis of an amplifier.

show abstract

Artificial Neural Network Model of SOS-MOSFETs Based on Dynamic Large-Signal Measurements

Cited by 33 publications

References 19 publications

On the design of GaN Chireix power amplifiers using an embedding device model

On the design of GaN Chireix power amplifiers using an embedding device model

Modified small‐signal behavioral model for GaN HEMTs based on support vector regression

An advanced analytical neuro–space mapping technique with sensitivity analysis for transistor modeling

Contact Info

Product

Resources

About