The study on machine learning approach for optimization of superjunction MOSFET
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

In this work, the the adoption of machine learning for optimization of superjunction MOSFET is investigated. Abundant data (on-resistance(RON), breakdown voltage(BV)) with various process parameters is earned by technology computer-aided design (TCAD) simulation. We also compare the prediction accuracy between eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM). XGBoost shows higher accuracy than LightGBM. The use of machine learning is very effective way to reduce the cost and time of superjunction MOSFET development. Copyright ? The Korean Institute of Electrical Engineers.

키워드

Machine LearningNumerical simulationSuperjunction MOSFETTCAD simulation
제목
The study on machine learning approach for optimization of superjunction MOSFET
저자
Lee, G.Ha, J.Kim, J.
DOI
10.5370/KIEE.2021.70.10.1475
발행일
2021-10
유형
Article
저널명
전기학회논문지
70
10
페이지
1475 ~ 1480