This study is focused on the modeling of an active electronic device based on the gallium-nitride (GaN) semiconductor technology by using an optimization-based procedure. Gated recurrent units (GRUs) are used to build the device model for predicting the scattering (S-) parameter measurements. By comparing measurements and simulations under different operating conditions, it is found that the extracted GRU-based model can faithfully reproduce the frequency- and temperature-dependent performance of the studied power device. In addition, the proposed modeling method is used to analyze and model the magnitude of the short-circuit current gain (h 21 ).
Cai, J., Gugliandolo, G., Marinković, Z., Latino, M., Fazio, E., Bosi, G., et al. (2023). GaN HEMT Small-Signal Modeling Using an Optimization Strategy Based on Gated Recurrent Unit Networks. In 2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 - Proceedings (pp.422-426). Institute of Electrical and Electronics Engineers Inc. [10.1109/MetroXRAINE58569.2023.10405657].
GaN HEMT Small-Signal Modeling Using an Optimization Strategy Based on Gated Recurrent Unit Networks
Bosi, Gianni;
2023
Abstract
This study is focused on the modeling of an active electronic device based on the gallium-nitride (GaN) semiconductor technology by using an optimization-based procedure. Gated recurrent units (GRUs) are used to build the device model for predicting the scattering (S-) parameter measurements. By comparing measurements and simulations under different operating conditions, it is found that the extracted GRU-based model can faithfully reproduce the frequency- and temperature-dependent performance of the studied power device. In addition, the proposed modeling method is used to analyze and model the magnitude of the short-circuit current gain (h 21 ).
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
