Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm

Hammam Abdelaal Hammam Soliman, Huai Wang, Brwene Salah Abdelkarim Gadalla, Frede Blaabjerg

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

14 Citations (Scopus)

Abstract

In power electronic systems, capacitor is one of the reliability critical components . Recently, the condition monitoring of capacitors to estimate their health status have been attracted by the academic research. Industry applications require more reliable power electronics products with preventive maintenance. However, the existing capacitor condition monitoring methods suffer from either increased hardware cost or low estimation accuracy, being the challenges to be adopted in industry applications. New development in condition monitoring technology with software solutions without extra hardware will reduce the cost, and therefore could be more promising for industry applications. A condition monitoring method based on Artificial Neural Network (ANN) algorithm is therefore proposed in this paper. The implementation of the ANN to the DC-link capacitor condition monitoring in a back-to-back converter is presented. The error analysis of the capacitance estimation is also given. The presented method enables a pure software based approach with high parameter estimation accuracy.
Original languageEnglish
Title of host publicationProceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG)
Number of pages5
Place of PublicationRiga, Latvia
PublisherIEEE Press
Publication dateMay 2015
Pages587 - 591
ISBN (Print)978-1-4799-9978-1
DOIs
Publication statusPublished - May 2015
Event2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG) - Riga, Latvia
Duration: 11 May 201513 May 2015

Conference

Conference2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG)
CountryLatvia
CityRiga
Period11/05/201513/05/2015

Fingerprint

Condition monitoring
Capacitors
Neural networks
Power electronics
Hardware
Industry
Preventive maintenance
Parameter estimation
Error analysis
Costs
Capacitance
Health

Cite this

Soliman, H. A. H., Wang, H., Gadalla, B. S. A., & Blaabjerg, F. (2015). Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm. In Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG) (pp. 587 - 591). Riga, Latvia: IEEE Press. https://doi.org/10.1109/PowerEng.2015.7266382
Soliman, Hammam Abdelaal Hammam ; Wang, Huai ; Gadalla, Brwene Salah Abdelkarim ; Blaabjerg, Frede. / Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm. Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG). Riga, Latvia : IEEE Press, 2015. pp. 587 - 591
@inproceedings{135d7bd8589a40618ff2fe56cec43b04,
title = "Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm",
abstract = "In power electronic systems, capacitor is one of the reliability critical components . Recently, the condition monitoring of capacitors to estimate their health status have been attracted by the academic research. Industry applications require more reliable power electronics products with preventive maintenance. However, the existing capacitor condition monitoring methods suffer from either increased hardware cost or low estimation accuracy, being the challenges to be adopted in industry applications. New development in condition monitoring technology with software solutions without extra hardware will reduce the cost, and therefore could be more promising for industry applications. A condition monitoring method based on Artificial Neural Network (ANN) algorithm is therefore proposed in this paper. The implementation of the ANN to the DC-link capacitor condition monitoring in a back-to-back converter is presented. The error analysis of the capacitance estimation is also given. The presented method enables a pure software based approach with high parameter estimation accuracy.",
author = "Soliman, {Hammam Abdelaal Hammam} and Huai Wang and Gadalla, {Brwene Salah Abdelkarim} and Frede Blaabjerg",
year = "2015",
month = "5",
doi = "10.1109/PowerEng.2015.7266382",
language = "English",
isbn = "978-1-4799-9978-1",
pages = "587 -- 591",
booktitle = "Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG)",
publisher = "IEEE Press",

}

Soliman, HAH, Wang, H, Gadalla, BSA & Blaabjerg, F 2015, Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm. in Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG). IEEE Press, Riga, Latvia, pp. 587 - 591, 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG), Riga, Latvia, 11/05/2015. https://doi.org/10.1109/PowerEng.2015.7266382

Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm. / Soliman, Hammam Abdelaal Hammam; Wang, Huai; Gadalla, Brwene Salah Abdelkarim; Blaabjerg, Frede.

Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG). Riga, Latvia : IEEE Press, 2015. p. 587 - 591.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm

AU - Soliman, Hammam Abdelaal Hammam

AU - Wang, Huai

AU - Gadalla, Brwene Salah Abdelkarim

AU - Blaabjerg, Frede

PY - 2015/5

Y1 - 2015/5

N2 - In power electronic systems, capacitor is one of the reliability critical components . Recently, the condition monitoring of capacitors to estimate their health status have been attracted by the academic research. Industry applications require more reliable power electronics products with preventive maintenance. However, the existing capacitor condition monitoring methods suffer from either increased hardware cost or low estimation accuracy, being the challenges to be adopted in industry applications. New development in condition monitoring technology with software solutions without extra hardware will reduce the cost, and therefore could be more promising for industry applications. A condition monitoring method based on Artificial Neural Network (ANN) algorithm is therefore proposed in this paper. The implementation of the ANN to the DC-link capacitor condition monitoring in a back-to-back converter is presented. The error analysis of the capacitance estimation is also given. The presented method enables a pure software based approach with high parameter estimation accuracy.

AB - In power electronic systems, capacitor is one of the reliability critical components . Recently, the condition monitoring of capacitors to estimate their health status have been attracted by the academic research. Industry applications require more reliable power electronics products with preventive maintenance. However, the existing capacitor condition monitoring methods suffer from either increased hardware cost or low estimation accuracy, being the challenges to be adopted in industry applications. New development in condition monitoring technology with software solutions without extra hardware will reduce the cost, and therefore could be more promising for industry applications. A condition monitoring method based on Artificial Neural Network (ANN) algorithm is therefore proposed in this paper. The implementation of the ANN to the DC-link capacitor condition monitoring in a back-to-back converter is presented. The error analysis of the capacitance estimation is also given. The presented method enables a pure software based approach with high parameter estimation accuracy.

U2 - 10.1109/PowerEng.2015.7266382

DO - 10.1109/PowerEng.2015.7266382

M3 - Article in proceeding

SN - 978-1-4799-9978-1

SP - 587

EP - 591

BT - Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG)

PB - IEEE Press

CY - Riga, Latvia

ER -

Soliman HAH, Wang H, Gadalla BSA, Blaabjerg F. Condition Monitoring for DC-link Capacitors Based on Artificial Neural Network Algorithm. In Proceedings of the 2015 IEEE 5th International Conference on Power Engineering, Energy, and Electrical Drives (POWERENG). Riga, Latvia: IEEE Press. 2015. p. 587 - 591 https://doi.org/10.1109/PowerEng.2015.7266382