Nonlinear Equivalent Circuit Model Base on BPNN for GaN HEMTs

A Back-Propagation Neural Network (BPNN) nonlinear model of $GaN$ HEMT is proposed, which can adaptively fit the nonlinear parameter relationship, and reduce computation. The network weights are obtained automatically, and then the nonlinear mapping relation is determined. The comparison between BPNN model and test data proves the good consistency.

[1]  Ruimin Xu,et al.  An Electrothermal Model for Empirical Large- Signal Modeling of AlGaN/GaN HEMTs Including Self-Heating and Ambient Temperature Effects , 2014, IEEE Transactions on Microwave Theory and Techniques.

[2]  Jianjun Xu,et al.  Dynamic FET model - DynaFET - for GaN transistors from NVNA active source injection measurements , 2014, 2014 IEEE MTT-S International Microwave Symposium (IMS2014).

[3]  P. Colantonio,et al.  RF Dynamic Behavioral Model Suitable for GaN-HEMT Devices , 2006, 2006 International Workshop on Integrated Nonlinear Microwave and Millimeter-Wave Circuits.

[4]  Anwar Jarndal,et al.  A Reliable Model Parameter Extraction Method Applied to AlGaN/GaN HEMTs , 2016, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  Jianjun Xu,et al.  Measurement-Based Non-Quasi-Static Large-Signal FET Model Using Artificial Neural Networks , 2006, 2006 IEEE MTT-S International Microwave Symposium Digest.