Neural Network-based Classification of Breakdown Mechanisms and Prediction of breakdown Voltage and On-resistance for 4H-SiC Trench Gate MOS Devices

Jiaxi Zhang, Shiyan Zhang, Ze Sun, Yucheng Wang, Yupan Wu, Wei Li, Shaoxi Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Since neural networks do not face the convergence issues like TCAD simulations, we attempted to construct two types of neural networks for numerical prediction and mechanism classification, respectively. After training with the SiC trench gate MOS dataset obtained from different structural parameters using TCAD simulations, the accurate prediction results were achieved. During the validation process, the breakdown type classifier achieves an accuracy of 96.5%, and the numerical predictors for breakdown voltage and on-resistance have the average errors within 10%.

Original languageEnglish
Title of host publication2024 International Symposium of Electronics Design Automation, ISEDA 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages780-781
Number of pages2
ISBN (Electronic)9798350352030
DOIs
StatePublished - 2024
Event2024 International Symposium of Electronics Design Automation, ISEDA 2024 - Xi�an, China
Duration: 10 May 202413 May 2024

Publication series

Name2024 International Symposium of Electronics Design Automation, ISEDA 2024

Conference

Conference2024 International Symposium of Electronics Design Automation, ISEDA 2024
Country/TerritoryChina
CityXi�an
Period10/05/2413/05/24

Keywords

  • Neural Network
  • Power Device
  • Silicon Carbide
  • TCAD simulations

Fingerprint

Dive into the research topics of 'Neural Network-based Classification of Breakdown Mechanisms and Prediction of breakdown Voltage and On-resistance for 4H-SiC Trench Gate MOS Devices'. Together they form a unique fingerprint.

Cite this