Combining Intelligence With Rules for Device Modeling: Approximating the Behavior of AlGaN/GaN HEMTs Using a Hybrid Neural Network and Fuzzy Logic Inference System

This paper uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) to investigate and propose a new alternative behavioral modeling technique for microwave power transistors. Utilizing measured I-V characteristics, associated parameters like transconductance
$(g_{\text {m}})$
and output conductance
$(g_{\text {ds}})$
, etc., S-parameters characteristics, and RF performance parameters such as unity current gain frequency
$(f_{\text {T}})$
, maximum unilateral gain frequency
$(f_{\max })$
, ANFIS-based behavioral models are developed for Gallium Nitride (GaN) High Electron Mobility Transistors (HEMTs) and validated. The models have been developed using two distinct devices with dimensions of
$10\times 200~\mu m$
and
$10\times 250~\mu m$
for multi-bias conditions and over a broad frequency range (0.5 to 43.5 GHz). Subsequently, the proposed model performance is validated on devices with geometries of
$10\times 220~\mu m$
,
$4\times 100~\mu m$
, and
$2\times 200~\mu m$
to examine the interpolation accuracy, extrapolation potential, and scalability. Here, ANFIS utilizes the subtractive clustering method to process the measurement characteristics by computing the clusters and opts for the best-performing model using error and number of fuzzy rules as criteria. The parameters involved in the fuzzy representation are trained using neural network algorithms, namely gradient-descent and least squares estimate. The proposed models are subsequently incorporated in a commercial circuit simulator (Keysight’s ADS) and the class-F power amplifier’s gain and stability characteristics are computed and studied.