Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

25 Downloads (Pure)

Abstract

The widespread usage of wide bandgap (WBG) semiconductors forces extra emphasis on the early estimation of the layout parasitic elements. Be it a printed circuit board or a power module, layout optimization is necessary to minimize the negative effects of present inductances. Unfortunately, multiple invocations of inductance extraction software can be time-consuming. In this work, state-of-the-art convolutional neural networks (CNN) are applied in order to lower the time consumption of inductance estimation without compromising the accuracy.
OriginalsprogEngelsk
Titel2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
Antal sider4
ForlagIEEE
Publikationsdato29 okt. 2023
Sider5906-5909
Artikelnummer10361953
ISBN (Elektronisk)9798350316445
DOI
StatusUdgivet - 29 okt. 2023
Begivenhed2023 IEEE Energy Conversion Congress and Exposition (ECCE) - Nashville, USA
Varighed: 29 okt. 20232 nov. 2023
https://www.ieee-ecce.org/2023/

Konference

Konference2023 IEEE Energy Conversion Congress and Exposition (ECCE)
Land/OmrådeUSA
ByNashville
Periode29/10/202302/11/2023
Internetadresse
NavnIEEE Energy Conversion Congress and Exposition (ECCE)
ISSN2329-3748

Fingeraftryk

Dyk ned i forskningsemnerne om 'Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks'. Sammen danner de et unikt fingeraftryk.

Citationsformater