Presentation 2020-11-20
[Invited Talk] Power Device Degradation Estimation by Machine Learning of Gate Waveforms
Hiromu Yamasaki, Koutaro Miyazaki, Yang Lo, A. K. M. Mahfuzul Islam, Katsuhiro Hata, Takayasu Sakurai, Makoto Takamiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A method to detect bonding wire lift-off of SiC MOSFETs using machine learning from the gate voltage waveform is proposed. In this paper, we proposed a new method that can be applied to 3-terminal SiC MOSFETs without the need for insulation compared to the conventional bonding wire lift-off detection method and demonstrated its effectiveness by SPICE simulation. By applying a linear regression algorithm to the two parameters extracted from the gate voltage waveform, we succeeded in constructing a bonding wire lift-off detection method that is robust to load current and temperature fluctuations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Linear regression / Machine learning / Power device / Reliability / Gate
Paper # SDM2020-29
Date of Issue 2020-11-12 (SDM)

Conference Information
Committee SDM
Conference Date 2020/11/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Virtual conference
Topics (in Japanese) (See Japanese page)
Topics (in English) Process, Device, Circuit simulation, etc.
Chair Hiroshige Hirano(TowerPartners Semiconductor)
Vice Chair Shunichiro Ohmi(Tokyo Inst. of Tech.)
Secretary Shunichiro Ohmi(AIST)
Assistant Taiji Noda(Panasonic) / Tomoyuki Suwa(Tohoku Univ.)

Paper Information
Registration To Technical Committee on Silicon Device and Materials
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Talk] Power Device Degradation Estimation by Machine Learning of Gate Waveforms
Sub Title (in English)
Keyword(1) Linear regression
Keyword(2) Machine learning
Keyword(3) Power device
Keyword(4) Reliability
Keyword(5) Gate
1st Author's Name Hiromu Yamasaki
1st Author's Affiliation The University of Tokyo(Univ. of Tokyo)
2nd Author's Name Koutaro Miyazaki
2nd Author's Affiliation The University of Tokyo(Univ. of Tokyo)
3rd Author's Name Yang Lo
3rd Author's Affiliation The University of Tokyo(Univ. of Tokyo)
4th Author's Name A. K. M. Mahfuzul Islam
4th Author's Affiliation The University of Tokyo(Univ. of Tokyo)
5th Author's Name Katsuhiro Hata
5th Author's Affiliation The University of Tokyo(Univ. of Tokyo)
6th Author's Name Takayasu Sakurai
6th Author's Affiliation The University of Tokyo(Univ. of Tokyo)
7th Author's Name Makoto Takamiya
7th Author's Affiliation The University of Tokyo(Univ. of Tokyo)
Date 2020-11-20
Paper # SDM2020-29
Volume (vol) vol.120
Number (no) SDM-239
Page pp.pp.32-35(SDM),
#Pages 4
Date of Issue 2020-11-12 (SDM)