Vertical GaN diode BV maximization through rapid TCAD simulation and ML-enabled surrogate model
Abstract
In this paper, two methodologies are used to speed up the maximization of the breakdown voltage (BV) of a vertical GaN diode that has a theoretical maximum BV of ∼ 2100 V. Firstly, we demonstrated a 5X faster accurate simulation method in Technology Computer-Aided-Design (TCAD). This allows us to find 50 % more numbers of high BV (>1400 V) designs at a given simulation time. Secondly, a machine learning (ML) model is developed using TCAD-generated data and used as a surrogate model for differential evolution optimization. It can inversely design an out-of-the-training-range structure with BV as high as 1887 V (89 % of the ideal case) compared to ∼ 1100 V designed with human domain expertise.
- Publication:
-
Solid State Electronics
- Pub Date:
- December 2022
- DOI:
- 10.1016/j.sse.2022.108468
- arXiv:
- arXiv:2208.01142
- Bibcode:
- 2022SSEle.19808468L
- Keywords:
-
- Power electronics;
- Power device;
- Breakdown voltage;
- Differential evolution;
- Gallium nitride (GaN);
- Machine learning;
- Technology Computer-Aided Design (TCAD);
- Diode;
- Computer Science - Machine Learning;
- Electrical Engineering and Systems Science - Signal Processing
- E-Print:
- 4 pages, 7 figures