Off-State Performance Characterization of an AlGaN/GaN Device via Artificial Neural Networks

Abstract

Due to the complexity of the 2D coupling effects in AlGaN/GaN HEMTs, the characterization of a device’s off-state performance remains the main obstacle to exploring the device’s breakdown characteristics. To predict the off-state performance of AlGaN/GaN HEMTs with efficiency and veracity, an artificial neural network-based methodology is proposed in this paper. Given the structure parameters, the off-state current–voltage (I–V) curve can therefore be obtained along with the essential performance index, such as breakdown voltage (BV) and saturation leakage current, without any physics domain requirement. The trained neural network is verified by the good agreement between predictions and simulated data. The proposed tool can achieve a low average error of the off-state I–V curve prediction (Ave. Error < 5%) and consumes less than 0.001‰ of average computing time than in TCAD simulation. Meanwhile, the convergence issue of TCAD simulation is avoided using the proposed method.