A particle swarm neural networks electrothermal modeling approach applied to GaN HEMTs

Jarndal, Anwar; Muhaureq, Sanaa A.

doi:10.1007/s10825-019-01397-1

Cited by 11 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their models give better performance as compared to the traditional ANN based models. The alternative solution to address initialization and convergence issues in ANN based GaN HEMT modelling is by the use PSO-SVR in the model development of GaN HEMT [16], [17]. The SVR can drive the solutions towards global minimums because it has an inbuilt SRM principle as opposed to the traditional ANN based approaches.…”

Section: Brief Literature Reviewmentioning

confidence: 99%

“…This can therefore facilitate the easy implementation of the device models in circuit design tools and the PAs can be produced on mass-scale easily. Therefore, recently a number of papers have been reported to describe the smallsignal behavior of GaN HEMT using Artificial Neural Network [11]- [14], global optimization-oriented ANN [15] and Particle swarm optimization (PSO)-based Support Vector Regression (SVR) [16]- [17]. But due to parametric nature of ANN and SVR algorithms, the performance of developed models heavily depend upon the nature of the dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT

Husain

Khusro

Hashmi

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

This paper develops and presents a CAD deployability of small-signal model of Gallium Nitride (GaN) High Electron Mobility Transistor (HEMT). First, a Gaussian Process Regression (GPR), a non-parametric probability-based method, is utilized to develop a small-signal model to effectively describe the behavior of the device. The model is developed to captures the bias and frequency dependence of GaN HEMT. The performance of the model is supplemented by advanced preprocessing and tuning of the hyperparameters of GPR approach. The tuning is done using 10-fold cross-validation error loss function. To examine the model's generalization ability the Mean squared error (MSE) metrics is used for both training and testing sets. Thereafter, the developed GPR based model is incorporated into CAD environment. Then the performance of the model is evaluated for stability and is also investigated for the usefulness of the model in class-F power amplifier design. The amplifier achieves excellent maximum available gain and small-signal voltage gain.

show abstract

Section: Brief Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT

Husain

Khusro

Hashmi

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

show abstract

“…The self‐heating in addition to the ambient temperature have strong impact on the small‐ and large‐signal characteristics as well as reliability of GaN HEMTs and the associated circuits 9 . These aspects are widely analyzed by electrothermal modeling of GaN devices under large‐signal and small‐signal conditions 10‐18 …”

Section: Introductionmentioning

confidence: 99%

Genetic algorithm initialized artificial neural network based temperature dependent small‐signal modeling technique for GaN high electron mobility transistors

Jarndal

Husain

Hashmi

2021

Int J RF Microw Comput Aided Eng

Self Cite

View full text Add to dashboard Cite

This paper explores and develops efficient temperature‐dependent small‐signal modeling approaches for GaN high electron mobility transistors (HEMTs). The multilayer perceptron (MLP) architecture and cascaded MLP architecture of artificial neural network are employed to model temperature dependence of 2‐mm GaN‐on‐silicon device. It is identified that both architectures face problem of dependence on initials values of weights and biases. To overcome this issue, the genetic algorithm (GA) is incorporated in both MLP and cascaded MLP architectures. The models are trained on a large set of operating conditions (bias voltages and ambient temperatures) over a frequency range of 0.1 to 20 GHz and then tested for both temperature interpolation and extrapolation cases to assess their accuracy and robustness. An excellent agreement between the measured and the modeled S‐parameters over the entire frequency range demonstrate the quality and robustness of the proposed technique. It is also shown that the cascaded MLP with GA exhibits better performance but with increased complexity.

show abstract

“…Another very important issue is the device modelling, which is necessary for designing application circuits. Many studies have been reported during the last years for modelling GaN-on-SiC and Dia substrate [29][30][31][32][33][34]. This study is contributing by developing a physics-relevant equivalent circuit model that can be easily developed and implemented.…”

Section: Introductionmentioning

confidence: 99%

Modelling of GaN high electron mobility transistor on diamond substrate

Jarndal

2021

IET Microwaves Antenna & Prop

Self Cite

View full text Add to dashboard Cite

A reliable small‐signal modelling approach has been developed and applied on GaN‐on‐diamond high electron mobility transistor. The extrinsic elements' extraction procedure was improved to provide an accurate characterization for the quasistatic behaviour of the intrinsic transistor. The frequency independence of the intrinsic elements at active multibias condition has been considered as another objective in addition to measurements' fitting. Physical relevant values for the model elements have been obtained. The model accuracy was also validated by means of S‐parameters simulation, which showed a very good fitting of the measured data.

show abstract

A particle swarm neural networks electrothermal modeling approach applied to GaN HEMTs

Cited by 11 publications

References 33 publications

Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT

Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT

Genetic algorithm initialized artificial neural network based temperature dependent small‐signal modeling technique for GaN high electron mobility transistors

Modelling of GaN high electron mobility transistor on diamond substrate

Contact Info

Product

Resources

About