J. Dobeš and L. Pospíšil (Czech Republic)
Artificial neural network (ANN), GaAs FET, pHEMT, mi crowave varactor, optimization, parameters extraction.
In the recent PSpice programs, five types of the GaAs FET model have been implemented. However, some of them are too sophisticated and therefore difficult to measure and identify afterwards, especially the realistic model of Parker and Skellern. In the paper, simple enhancements of one of the classical models are proposed first. The resulting modi fication is usable for reliable modeling of both GaAs FETs and pHEMTs. Moreover, its adjusted capacitance func tion can effectively serve as a convenient representation of microwave varactors. The accuracy of these models can be strongly enhanced using the artificial neural networks – both using an exclusive neural network without an analytic model and cooperating a corrective neural network with the updated analytic model are discussed. The accuracy of the updated analytic models, the models based on the exclu sive neural network, and the models created as a combina tion of the updated analytic model and the corrective neural network is compared.
Important Links:
Go Back
