AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors

Alireza Mehrabi; Keyvan Yari; Willem D. Van Driel; Rene H. Poelma

doi:10.1109/ESTC60143.2024.10712146

AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors

Alireza Mehrabi, Keyvan Yari, Willem D. Van Driel, Rene H. Poelma

Electronic Components, Technology and Materials

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

13 Downloads (Pure)

Abstract

A significant challenge in the implementation of health monitoring systems for estimating the health state of devices is the lack of accurate information about design details. This challenge is particularly prominent in the field of power electronics, where both IC designers and converter designers are often hesitant to share information about their designs. Addressing this issue, this paper introduces a novel AI-driven digital twin modeling methodology that enables the detection and classification of failures in power semiconductors, particularly Wide Band Gap semiconductors. By employing AI-based system identification techniques, this method offers a noninvasive approach to health monitoring of power switches with high resolution, even while operating under real conditions. The proposed method has been validated by simulating wire bond failure in a SiC power MOSFET using MATLAB SIMULINK, and the results demonstrate its accuracy.

Original language	English
Title of host publication	Proceedings of the 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC)
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	979-8-3503-9036-0
ISBN (Print)	979-8-3503-9037-7
DOIs	https://doi.org/10.1109/ESTC60143.2024.10712146
Publication status	Published - 2024
Event	10th IEEE Electronics System-Integration Technology Conference, ESTC 2024 - Berlin, Germany Duration: 11 Sept 2024 → 13 Sept 2024

Conference

Conference	10th IEEE Electronics System-Integration Technology Conference, ESTC 2024
Country/Territory	Germany
City	Berlin
Period	11/09/24 → 13/09/24

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

AI
Digital twin
Health monitoring
Kalman filter
NARX-ANN
Power converter
WBG semiconductor

Access to Document

10.1109/ESTC60143.2024.10712146

AI-Driven_Digital_Twin_for_Health_Monitoring_of_Wide_Band_Gap_Power_SemiconductorsFinal published version, 1.26 MB

Cite this

@inproceedings{1e73f2f0f90f454fb0e4035b7ad8030a,

title = "AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors",

abstract = "A significant challenge in the implementation of health monitoring systems for estimating the health state of devices is the lack of accurate information about design details. This challenge is particularly prominent in the field of power electronics, where both IC designers and converter designers are often hesitant to share information about their designs. Addressing this issue, this paper introduces a novel AI-driven digital twin modeling methodology that enables the detection and classification of failures in power semiconductors, particularly Wide Band Gap semiconductors. By employing AI-based system identification techniques, this method offers a noninvasive approach to health monitoring of power switches with high resolution, even while operating under real conditions. The proposed method has been validated by simulating wire bond failure in a SiC power MOSFET using MATLAB SIMULINK, and the results demonstrate its accuracy.",

keywords = "AI, Digital twin, Health monitoring, Kalman filter, NARX-ANN, Power converter, WBG semiconductor",

author = "Alireza Mehrabi and Keyvan Yari and {Van Driel}, {Willem D.} and Poelma, {Rene H.}",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 10th IEEE Electronics System-Integration Technology Conference, ESTC 2024 ; Conference date: 11-09-2024 Through 13-09-2024",

year = "2024",

doi = "10.1109/ESTC60143.2024.10712146",

language = "English",

isbn = "979-8-3503-9037-7",

booktitle = "Proceedings of the 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC)",

publisher = "IEEE",

address = "United States",

}

Mehrabi, A , Yari, K , Van Driel, WD & Poelma, RH 2024, AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors. in Proceedings of the 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC). IEEE, 10th IEEE Electronics System-Integration Technology Conference, ESTC 2024, Berlin, Germany, 11/09/24. https://doi.org/10.1109/ESTC60143.2024.10712146

AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors. / Mehrabi, Alireza ; Yari, Keyvan ; Van Driel, Willem D. et al.
Proceedings of the 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC). IEEE, 2024.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors

AU - Mehrabi, Alireza

AU - Yari, Keyvan

AU - Van Driel, Willem D.

AU - Poelma, Rene H.

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2024

Y1 - 2024

N2 - A significant challenge in the implementation of health monitoring systems for estimating the health state of devices is the lack of accurate information about design details. This challenge is particularly prominent in the field of power electronics, where both IC designers and converter designers are often hesitant to share information about their designs. Addressing this issue, this paper introduces a novel AI-driven digital twin modeling methodology that enables the detection and classification of failures in power semiconductors, particularly Wide Band Gap semiconductors. By employing AI-based system identification techniques, this method offers a noninvasive approach to health monitoring of power switches with high resolution, even while operating under real conditions. The proposed method has been validated by simulating wire bond failure in a SiC power MOSFET using MATLAB SIMULINK, and the results demonstrate its accuracy.

AB - A significant challenge in the implementation of health monitoring systems for estimating the health state of devices is the lack of accurate information about design details. This challenge is particularly prominent in the field of power electronics, where both IC designers and converter designers are often hesitant to share information about their designs. Addressing this issue, this paper introduces a novel AI-driven digital twin modeling methodology that enables the detection and classification of failures in power semiconductors, particularly Wide Band Gap semiconductors. By employing AI-based system identification techniques, this method offers a noninvasive approach to health monitoring of power switches with high resolution, even while operating under real conditions. The proposed method has been validated by simulating wire bond failure in a SiC power MOSFET using MATLAB SIMULINK, and the results demonstrate its accuracy.

KW - AI

KW - Digital twin

KW - Health monitoring

KW - Kalman filter

KW - NARX-ANN

KW - Power converter

KW - WBG semiconductor

UR - http://www.scopus.com/inward/record.url?scp=85208149780&partnerID=8YFLogxK

U2 - 10.1109/ESTC60143.2024.10712146

DO - 10.1109/ESTC60143.2024.10712146

M3 - Conference contribution

AN - SCOPUS:85208149780

SN - 979-8-3503-9037-7

BT - Proceedings of the 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC)

PB - IEEE

T2 - 10th IEEE Electronics System-Integration Technology Conference, ESTC 2024

Y2 - 11 September 2024 through 13 September 2024

ER -

AI-Driven Digital Twin for Health Monitoring of Wide Band Gap Power Semiconductors

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this