Mobile QR Code QR CODE : The Transactions of the Korean Institute of Electrical Engineers
Title The Study on Machine Learning Approach for Optimization of Superjunction MOSFET
Authors 이경엽(Gyeongyeop Lee) ; 하종현(Jonghyun Ha) ; 김정식(Jungsik Kim)
DOI https://doi.org/10.5370/KIEE.2021.70.10.1475
Page pp.1475-1480
ISSN 1975-8359
Keywords Machine Learning; Superjunction MOSFET; numerical simulation; TCAD simulation
Abstract In this work, the the adoption of machine learning for optimization of superjunction MOSFET is investigated. Abundant data (on-resistance(), 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.