Deep Learning Method for Breakdown Voltage and Forward I-V Characteristic Prediction of Silicon Carbide Schottky Barrier Diodes

TL;DR

This paper introduces a deep learning model to accurately predict the breakdown voltage and forward I-V characteristics of silicon carbide diodes, reducing the need for costly destructive testing.

Contribution

A high-precision deep learning model is developed for predicting device characteristics of SiC SBDs with minimal experimental testing.

Findings

A model predicting breakdown voltage achieved 99% accuracy using 600 data sets after 200 epochs.

The model predicted forward I-V characteristics with a mean squared error of less than 10−3 after 1000 epochs.

The deep learning approach proved efficient and applicable for device characteristic prediction in SiC SBDs.

Abstract

This work employs a deep learning method to develop a high-precision model for predicting the breakdown voltage (Vbr) and forward I-V characteristics of silicon carbide Schottky barrier diodes (SiC SBDs). The model significantly reduces the testing costs associated with destructive experiments, such as breakdown voltage testing. Although the model requires a certain amount of time to establish itself, it supports linear variations in related variables once developed. A predicted model for Vbr with an accuracy of up to 99% was successfully developed using 600 sets of input data after 200 epochs of training. After training for 1000 epochs, the deep learning-based model could predict not only point values like Vbr but also curves, such as forward I-V characteristics, with a mean squared error (MSE) of less than 10−3. Our research shows the applicability and high efficiency of introducing deep learning into device characteristic prediction.

Figures