Design Optimization of an Enhanced-Mode GaN HEMT with Hybrid Back Barrier and Breakdown Voltage Prediction Based on Neural Networks

Abstract

To improve the breakdown voltage (BV), a GaN-based high-electron-mobility transistor with a hybrid AlGaN back barrier (HBB-HEMT) was proposed. The hybrid AlGaN back barrier was constructed using the Al0.25Ga0.75N region and Al0.1G0.9N region, each with a distinct Al composition. Simulation results of the HBB-HEMT demonstrated a breakdown voltage (1640 V) that was 212% higher than that of the conventional HEMT (Conv-HEMT) and a low on-resistance (0.4 mΩ·cm2). Ultimately, the device achieved a high Baliga’s figure of merit (7.3 GW/cm2) among reported devices of similar size. A back-propagation (BP) neural network-based prediction model was trained to predict BV for enhanced efficiency in subsequent work. The model was trained and calibrated, achieving a correlation coefficient (R) of 0.99 and a prediction accuracy of 95% on the test set. The results indicated that the BP neural network model using the Levenberg–Marquardt algorithm accurately predicted the forward breakdown voltage of the HBB-HEMT, underscoring the feasibility and significance of neural network models in designing GaN power devices.