Deep neural network-based approach for breakdown voltage and specific on-resistance prediction of SOI LDMOS with field plate

Abstract

Breakdown voltage (BV) and specific on-resistance (R (on,sp)), are critical indicators to measure the quality of the power device. To improve the device performance, field plate technology has been developed by modifying the electric field distribution. However, the current technology computer-aided design (TCAD) simulation cannot predict the effect of field plate on BV and R (on,sp) simultaneously, and the operation process is complicated. This paper proposes a deep neural network (DNN)-based model instead of TCAD to predict the effect of field plates on BV and R (on,sp) of silicon on insulator lateral double diffused metal oxide semiconductor. The experimental results show that, compared with TCAD simulation, the average deviation for BV and R (on,sp) is 5.06% and 2.55%, respectively. Also, the time for BV prediction is accelerated significantly up by 1.23 x 10(5). Our DNN model provides a potential direction to predict device performance with higher efficiency.