Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Pawel Piotr Kubulus; Szymon Michal Beczkowski; Stig Munk-Nielsen; Asger Bjørn Jørgensen

doi:10.1109/ECCE53617.2023.10361953

Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Pawel Piotr Kubulus^*, Szymon Michal Beczkowski, Stig Munk-Nielsen, Asger Bjørn Jørgensen

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

1 Citation (Scopus)

135 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.

Original language	English
Title of host publication	2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
Number of pages	4
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	29 Oct 2023
Pages	5906-5909
Article number	10361953
ISBN (Electronic)	9798350316445
DOIs	https://doi.org/10.1109/ECCE53617.2023.10361953
Publication status	Published - 29 Oct 2023
Event	2023 IEEE Energy Conversion Congress and Exposition (ECCE) - Nashville, United States Duration: 29 Oct 2023 → 2 Nov 2023 https://www.ieee-ecce.org/2023/

Conference

Conference	2023 IEEE Energy Conversion Congress and Exposition (ECCE)
Country/Territory	United States
City	Nashville
Period	29/10/2023 → 02/11/2023
Internet address	https://www.ieee-ecce.org/2023/

Series	IEEE Energy Conversion Congress and Exposition (ECCE)
ISSN	2329-3748

Keywords

inductance extraction
layout optimization
neural networks
power module
printed circuit board

Access to Document

10.1109/ECCE53617.2023.10361953

Ultra-Fast_Power_Module_Inductance_Estimation_using_Convolutional_Neural_NetworksAccepted author manuscript, 3.73 MB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{9c58d7d2154d44f9aa89d171a87cbc43,

title = "Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks",

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.",

keywords = "inductance extraction, layout optimization, neural networks, power module, printed circuit board",

author = "Kubulus, {Pawel Piotr} and Beczkowski, {Szymon Michal} and Stig Munk-Nielsen and J{\o}rgensen, {Asger Bj{\o}rn}",

year = "2023",

month = oct,

day = "29",

doi = "10.1109/ECCE53617.2023.10361953",

language = "English",

series = "IEEE Energy Conversion Congress and Exposition (ECCE)",

pages = "5906--5909",

booktitle = "2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

address = "United States",

note = "2023 IEEE Energy Conversion Congress and Exposition (ECCE) ; Conference date: 29-10-2023 Through 02-11-2023",

url = "https://www.ieee-ecce.org/2023/",

}

Kubulus, PP , Beczkowski, SM , Munk-Nielsen, S & Jørgensen, AB 2023, Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks. in 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023., 10361953, IEEE (Institute of Electrical and Electronics Engineers), IEEE Energy Conversion Congress and Exposition (ECCE), pp. 5906-5909, 2023 IEEE Energy Conversion Congress and Exposition (ECCE), Nashville, Tennessee, United States, 29/10/2023. https://doi.org/10.1109/ECCE53617.2023.10361953

Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks. / Kubulus, Pawel Piotr ; Beczkowski, Szymon Michal ; Munk-Nielsen, Stig et al.
2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. IEEE (Institute of Electrical and Electronics Engineers), 2023. p. 5906-5909 10361953 (IEEE Energy Conversion Congress and Exposition (ECCE)).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

AU - Kubulus, Pawel Piotr

AU - Beczkowski, Szymon Michal

AU - Munk-Nielsen, Stig

AU - Jørgensen, Asger Bjørn

PY - 2023/10/29

Y1 - 2023/10/29

N2 - 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.

AB - 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.

KW - inductance extraction

KW - layout optimization

KW - neural networks

KW - power module

KW - printed circuit board

UR - http://www.scopus.com/inward/record.url?scp=85182923341&partnerID=8YFLogxK

U2 - 10.1109/ECCE53617.2023.10361953

DO - 10.1109/ECCE53617.2023.10361953

M3 - Article in proceeding

T3 - IEEE Energy Conversion Congress and Exposition (ECCE)

SP - 5906

EP - 5909

BT - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 2023 IEEE Energy Conversion Congress and Exposition (ECCE)

Y2 - 29 October 2023 through 2 November 2023

ER -

Kubulus PP , Beczkowski SM , Munk-Nielsen S , Jørgensen AB. Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks. In 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. IEEE (Institute of Electrical and Electronics Engineers). 2023. p. 5906-5909. 10361953. (IEEE Energy Conversion Congress and Exposition (ECCE)). doi: 10.1109/ECCE53617.2023.10361953

Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

CoDE: Center of Digitalized Electronics (CoDE)

Digital Twin Based Automated Design for Converters Incorporating Wide-Band Gap Devices

Cite this

Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

CoDE: Center of Digitalized Electronics (CoDE)

Digital Twin Based Automated Design for Converters Incorporating Wide-Band Gap Devices

Cite this