On condition monitoring of high frequency power GaN converters with adaptive prognostics

Mehrdad Biglarbegian; Saman Mostafavi; Sven Hauer; Shahriar Jalal Nibir; Namwon Kim; Robert Cox; Babak Parkhideh

doi:10.1109/APEC.2018.8341180

On condition monitoring of high frequency power GaN converters with adaptive prognostics

Mehrdad Biglarbegian, Saman Mostafavi, Sven Hauer, Shahriar Jalal Nibir, Namwon Kim, Robert Cox, Babak Parkhideh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

There is no doubt that in the future, a need for higher switching frequency is inevitable to extract the full benefits of reliable Gallium Nitride (GaN) device characteristics. Along with the reliability enhancement for GaN-based power converters, it is essential to monitor a precursor signature identification for diagnostics/prognostics techniques. With the availability of the most granular information deduced from advanced devices, a new data-driven scheme is proposed for system monitoring and possible lifetime extension of 400W power GaN converters at 100kHz. The approach relies on the real-time R_ds(_on) data extraction from the power converter, and calibration of an adaptive model using multi-physics co-simulations under thermal cycling. More specifically, the focus is on deploying machine learning algorithms to exploit for the parameter estimation in power electronics engineering reliability.

Original language	English
Title of host publication	APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1272-1279
Number of pages	8
ISBN (Electronic)	9781538611807
DOIs	https://doi.org/10.1109/APEC.2018.8341180
State	Published - Apr 18 2018
Externally published	Yes
Event	33rd Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2018 - San Antonio, United States Duration: Mar 4 2018 → Mar 8 2018

Publication series

Name	Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC
Volume	2018-March

Conference

Conference	33rd Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2018
Country/Territory	United States
City	San Antonio
Period	03/4/18 → 03/8/18

Funding

ACKNOWLEDGMENT This research was supported by the National Science Foundation under Award No. 1610250. The authors would like to thank the Energy Production and Infrastructure Center (EPIC), and Electrical and Computer Engineering Department at the University of North Carolina at Charlotte. This research was supported by the National Science Foundation under Award No. 1610250. The authors would like to thank the Energy Production and Infrastructure Center (EPIC), and Electrical and Computer Engineering Department at the University of North Carolina at Charlotte.

Funders	Funder number
National Science Foundation	1610250
Ecumenical Project for International Cooperation
National Science Foundation

Keywords

Fault prognostics
High frequency dc-dc converter
Internet of things
Machine learning
Metropolis-hasting
Power GaN
Reliability
Wide bandgap semiconductors

Access to Document

10.1109/APEC.2018.8341180

Cite this

Biglarbegian, M., Mostafavi, S., Hauer, S., Nibir, S. J., Kim, N., Cox, R., & Parkhideh, B. (2018). On condition monitoring of high frequency power GaN converters with adaptive prognostics. In APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition (pp. 1272-1279). (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC; Vol. 2018-March). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APEC.2018.8341180

Biglarbegian, Mehrdad ; Mostafavi, Saman ; Hauer, Sven et al. / On condition monitoring of high frequency power GaN converters with adaptive prognostics. APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1272-1279 (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC).

@inproceedings{152be70e46054664a64f4b9fae734cad,

title = "On condition monitoring of high frequency power GaN converters with adaptive prognostics",

abstract = "There is no doubt that in the future, a need for higher switching frequency is inevitable to extract the full benefits of reliable Gallium Nitride (GaN) device characteristics. Along with the reliability enhancement for GaN-based power converters, it is essential to monitor a precursor signature identification for diagnostics/prognostics techniques. With the availability of the most granular information deduced from advanced devices, a new data-driven scheme is proposed for system monitoring and possible lifetime extension of 400W power GaN converters at 100kHz. The approach relies on the real-time Rds(on) data extraction from the power converter, and calibration of an adaptive model using multi-physics co-simulations under thermal cycling. More specifically, the focus is on deploying machine learning algorithms to exploit for the parameter estimation in power electronics engineering reliability.",

keywords = "Fault prognostics, High frequency dc-dc converter, Internet of things, Machine learning, Metropolis-hasting, Power GaN, Reliability, Wide bandgap semiconductors",

author = "Mehrdad Biglarbegian and Saman Mostafavi and Sven Hauer and Nibir, {Shahriar Jalal} and Namwon Kim and Robert Cox and Babak Parkhideh",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 33rd Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2018 ; Conference date: 04-03-2018 Through 08-03-2018",

year = "2018",

month = apr,

day = "18",

doi = "10.1109/APEC.2018.8341180",

language = "English",

series = "Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1272--1279",

booktitle = "APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition",

}

Biglarbegian, M, Mostafavi, S, Hauer, S, Nibir, SJ, Kim, N, Cox, R & Parkhideh, B 2018, On condition monitoring of high frequency power GaN converters with adaptive prognostics. in APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition. Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC, vol. 2018-March, Institute of Electrical and Electronics Engineers Inc., pp. 1272-1279, 33rd Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2018, San Antonio, United States, 03/4/18. https://doi.org/10.1109/APEC.2018.8341180

On condition monitoring of high frequency power GaN converters with adaptive prognostics. / Biglarbegian, Mehrdad; Mostafavi, Saman; Hauer, Sven et al.
APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1272-1279 (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC; Vol. 2018-March).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On condition monitoring of high frequency power GaN converters with adaptive prognostics

AU - Biglarbegian, Mehrdad

AU - Mostafavi, Saman

AU - Hauer, Sven

AU - Nibir, Shahriar Jalal

AU - Kim, Namwon

AU - Cox, Robert

AU - Parkhideh, Babak

PY - 2018/4/18

Y1 - 2018/4/18

N2 - There is no doubt that in the future, a need for higher switching frequency is inevitable to extract the full benefits of reliable Gallium Nitride (GaN) device characteristics. Along with the reliability enhancement for GaN-based power converters, it is essential to monitor a precursor signature identification for diagnostics/prognostics techniques. With the availability of the most granular information deduced from advanced devices, a new data-driven scheme is proposed for system monitoring and possible lifetime extension of 400W power GaN converters at 100kHz. The approach relies on the real-time Rds(on) data extraction from the power converter, and calibration of an adaptive model using multi-physics co-simulations under thermal cycling. More specifically, the focus is on deploying machine learning algorithms to exploit for the parameter estimation in power electronics engineering reliability.

AB - There is no doubt that in the future, a need for higher switching frequency is inevitable to extract the full benefits of reliable Gallium Nitride (GaN) device characteristics. Along with the reliability enhancement for GaN-based power converters, it is essential to monitor a precursor signature identification for diagnostics/prognostics techniques. With the availability of the most granular information deduced from advanced devices, a new data-driven scheme is proposed for system monitoring and possible lifetime extension of 400W power GaN converters at 100kHz. The approach relies on the real-time Rds(on) data extraction from the power converter, and calibration of an adaptive model using multi-physics co-simulations under thermal cycling. More specifically, the focus is on deploying machine learning algorithms to exploit for the parameter estimation in power electronics engineering reliability.

KW - Fault prognostics

KW - High frequency dc-dc converter

KW - Internet of things

KW - Machine learning

KW - Metropolis-hasting

KW - Power GaN

KW - Reliability

KW - Wide bandgap semiconductors

UR - http://www.scopus.com/inward/record.url?scp=85046953924&partnerID=8YFLogxK

U2 - 10.1109/APEC.2018.8341180

DO - 10.1109/APEC.2018.8341180

M3 - Conference contribution

AN - SCOPUS:85046953924

T3 - Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC

SP - 1272

EP - 1279

BT - APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2018

Y2 - 4 March 2018 through 8 March 2018

ER -

Biglarbegian M, Mostafavi S, Hauer S, Nibir SJ, Kim N, Cox R et al. On condition monitoring of high frequency power GaN converters with adaptive prognostics. In APEC 2018 - 33rd Annual IEEE Applied Power Electronics Conference and Exposition. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1272-1279. (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC). doi: 10.1109/APEC.2018.8341180

On condition monitoring of high frequency power GaN converters with adaptive prognostics

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this