Data-Driven Parameter Fault Classification for A DC–DC Buck Converter

Yichuan Fu; Zhiwei Gao; Aihua Zhang

doi:10.1109/efea49713.2021.9406258

Data-Driven Parameter Fault Classification for A DC–DC Buck Converter

Yichuan Fu^*, Zhiwei Gao^*, Aihua Zhang

^*Corresponding author for this work

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

10 Citations (Scopus)

Abstract

DC–DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC–DC Buck converters are prone to faults due to age and unexpected accidents. As a result, there is a high demand to improve the operation reliability and safety of power converters by using condition monitoring and fault diagnosis techniques. In this paper, data-driven and machine learning-based fault detection and fault classification strategies are addressed for DC–DC Buck converters under disparate faulty scenarios of the parameters. A variety of algorithms such as principal component analysis, multi-linear principal component analysis, uncorrelated multi-linear principal component analysis, and Fast Fourier Transformation pre-processing based multi-linear principal component analysis and uncorrelated multi-linear principal component analysis techniques are applied for fault classification and diagnosis of the parameter faults in the DC–DC Buck converters. The effectiveness is demonstrated and discussed with details.

Original language	English
Title of host publication	Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA
Editors	Radostina A. Angelova, Rositsa Velichkova
Place of Publication	Piscataway
Publisher	IEEE
Pages	1-7
Number of pages	7
ISBN (Electronic)	9781728170114, 9781728170107
DOIs	https://doi.org/10.1109/efea49713.2021.9406258
Publication status	Published - 24 Mar 2021
Event	EFEA 2021: Are you ready to change the world? - Technical University of Sofia, Sofia, Bulgaria Duration: 24 Mar 2021 → 26 Mar 2021 https://cerdecen.wixsite.com/efea2021

Publication series

Name	2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)
Publisher	IEEE
ISSN (Electronic)	2688-2558

Conference

Conference	EFEA 2021
Country/Territory	Bulgaria
City	Sofia
Period	24/03/21 → 26/03/21
Internet address	https://cerdecen.wixsite.com/efea2021

Keywords

data-driven
fault classification
DC–DC Buck converter systems

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/efea49713.2021.9406258

Cite this

Fu, Y., Gao, Z., & Zhang, A. (2021). Data-Driven Parameter Fault Classification for A DC–DC Buck Converter. In R. A. Angelova, & R. Velichkova (Eds.), Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA (pp. 1-7). Article 9406258 (2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)). IEEE. https://doi.org/10.1109/efea49713.2021.9406258

Fu, Yichuan ; Gao, Zhiwei ; Zhang, Aihua. / Data-Driven Parameter Fault Classification for A DC–DC Buck Converter. Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA. editor / Radostina A. Angelova ; Rositsa Velichkova. Piscataway : IEEE, 2021. pp. 1-7 (2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)).

@inproceedings{a85c26eeb16c4fd3a31756112ff2ee89,

title = "Data-Driven Parameter Fault Classification for A DC–DC Buck Converter",

abstract = "DC–DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC–DC Buck converters are prone to faults due to age and unexpected accidents. As a result, there is a high demand to improve the operation reliability and safety of power converters by using condition monitoring and fault diagnosis techniques. In this paper, data-driven and machine learning-based fault detection and fault classification strategies are addressed for DC–DC Buck converters under disparate faulty scenarios of the parameters. A variety of algorithms such as principal component analysis, multi-linear principal component analysis, uncorrelated multi-linear principal component analysis, and Fast Fourier Transformation pre-processing based multi-linear principal component analysis and uncorrelated multi-linear principal component analysis techniques are applied for fault classification and diagnosis of the parameter faults in the DC–DC Buck converters. The effectiveness is demonstrated and discussed with details.",

keywords = "data-driven, fault classification, DC–DC Buck converter systems",

author = "Yichuan Fu and Zhiwei Gao and Aihua Zhang",

note = "The authors would like to thank the research support from National Nature Science Foundation of China (NNSFC) under Grant 61673074, and the E\&E faculty at Northumbria University, Newcastle upon Tyne, NE1 8ST, United Kingdom.; EFEA 2021 : Are you ready to change the world? ; Conference date: 24-03-2021 Through 26-03-2021",

year = "2021",

month = mar,

day = "24",

doi = "10.1109/efea49713.2021.9406258",

language = "English",

series = "2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)",

publisher = "IEEE",

pages = "1--7",

editor = "\{ Angelova\}, \{Radostina A.\} and Rositsa Velichkova",

booktitle = "Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA",

address = "United States",

url = "https://cerdecen.wixsite.com/efea2021",

}

Fu, Y, Gao, Z & Zhang, A 2021, Data-Driven Parameter Fault Classification for A DC–DC Buck Converter. in RA Angelova & R Velichkova (eds), Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA., 9406258, 2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA), IEEE, Piscataway, pp. 1-7, EFEA 2021, Sofia, Bulgaria, 24/03/21. https://doi.org/10.1109/efea49713.2021.9406258

Data-Driven Parameter Fault Classification for A DC–DC Buck Converter. / Fu, Yichuan; Gao, Zhiwei; Zhang, Aihua.
Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA. ed. / Radostina A. Angelova; Rositsa Velichkova. Piscataway: IEEE, 2021. p. 1-7 9406258 (2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)).

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

TY - GEN

T1 - Data-Driven Parameter Fault Classification for A DC–DC Buck Converter

AU - Fu, Yichuan

AU - Gao, Zhiwei

AU - Zhang, Aihua

N1 - The authors would like to thank the research support from National Nature Science Foundation of China (NNSFC) under Grant 61673074, and the E&E faculty at Northumbria University, Newcastle upon Tyne, NE1 8ST, United Kingdom.

PY - 2021/3/24

Y1 - 2021/3/24

N2 - DC–DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC–DC Buck converters are prone to faults due to age and unexpected accidents. As a result, there is a high demand to improve the operation reliability and safety of power converters by using condition monitoring and fault diagnosis techniques. In this paper, data-driven and machine learning-based fault detection and fault classification strategies are addressed for DC–DC Buck converters under disparate faulty scenarios of the parameters. A variety of algorithms such as principal component analysis, multi-linear principal component analysis, uncorrelated multi-linear principal component analysis, and Fast Fourier Transformation pre-processing based multi-linear principal component analysis and uncorrelated multi-linear principal component analysis techniques are applied for fault classification and diagnosis of the parameter faults in the DC–DC Buck converters. The effectiveness is demonstrated and discussed with details.

AB - DC–DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC–DC Buck converters are prone to faults due to age and unexpected accidents. As a result, there is a high demand to improve the operation reliability and safety of power converters by using condition monitoring and fault diagnosis techniques. In this paper, data-driven and machine learning-based fault detection and fault classification strategies are addressed for DC–DC Buck converters under disparate faulty scenarios of the parameters. A variety of algorithms such as principal component analysis, multi-linear principal component analysis, uncorrelated multi-linear principal component analysis, and Fast Fourier Transformation pre-processing based multi-linear principal component analysis and uncorrelated multi-linear principal component analysis techniques are applied for fault classification and diagnosis of the parameter faults in the DC–DC Buck converters. The effectiveness is demonstrated and discussed with details.

KW - data-driven

KW - fault classification

KW - DC–DC Buck converter systems

UR - https://www.scopus.com/pages/publications/85105302163

U2 - 10.1109/efea49713.2021.9406258

DO - 10.1109/efea49713.2021.9406258

M3 - Conference contribution

T3 - 2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)

SP - 1

EP - 7

BT - Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA

A2 - Angelova, Radostina A.

A2 - Velichkova, Rositsa

PB - IEEE

CY - Piscataway

T2 - EFEA 2021

Y2 - 24 March 2021 through 26 March 2021

ER -

Fu Y, Gao Z, Zhang A. Data-Driven Parameter Fault Classification for A DC–DC Buck Converter. In Angelova RA, Velichkova R, editors, Proceedings of the 2021 6th International Symposium on Environment Friendly Energies and Applications (EFEA. Piscataway: IEEE. 2021. p. 1-7. 9406258. (2021 6th International Symposium on Environment-Friendly Energies and Applications (EFEA)). doi: 10.1109/efea49713.2021.9406258

Data-Driven Parameter Fault Classification for A DC–DC Buck Converter

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this