Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems

Hammam Abdelaal Hammam Soliman; Pooya Davari; Huai Wang; Frede Blaabjerg

doi:10.1109/ECCE.2017.8096961

Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems

Hammam Abdelaal Hammam Soliman, Pooya Davari, Huai Wang, Frede Blaabjerg

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

48 Citations (Scopus)

Abstract

In modern design of power electronic converters, reliability of dc-link capacitors is one of the critical considered aspects. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. However, the existing condition monitoring methodologies are rarely adopted by industry due to shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of new
condition monitoring methodologies that are based on advanced software and requires no extra hardware could be more attractive to industry. In this digest, a condition monitoring methodology that estimates the capacitance value of the dc-link capacitor in a three phase Front-End diode bridge motor drive is proposed. The proposed software methodology is based on Artificial Neural Network (ANN) algorithm. The harmonics of the dc-link voltage are used
as training data to the Artificial Neural Network. Fast Fourier Transform (FFT) of the dc-link voltage is analysed in order to study the impact of capacitance variation on the harmonics order. Laboratory experiments are conducted to
validate the proposed methodology and the error analysis of the estimated results is also studied.

Original language	English
Title of host publication	Proceedings of 2017 IEEE Energy Conversion Congress and Exposition (ECCE)
Number of pages	8
Publisher	IEEE Press
Publication date	Oct 2017
Pages	5795-5802
ISBN (Electronic)	978-1-5090-2998-3
DOIs	https://doi.org/10.1109/ECCE.2017.8096961
Publication status	Published - Oct 2017
Event	2017 IEEE Energy Conversion Congress and Exposition (ECCE) - Cincinnati, Ohio, United States Duration: 1 Oct 2017 → 5 Oct 2017

Conference

Conference	2017 IEEE Energy Conversion Congress and Exposition (ECCE)
Country/Territory	United States
City	Cincinnati, Ohio
Period	01/10/2017 → 05/10/2017

Access to Document

10.1109/ECCE.2017.8096961

AUB Link

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

REPEPS: REliable Power Electronic based Power System
Blaabjerg, F. (PI), Iannuzzo, F. (CoI), Davari, P. (CoI), Wang, H. (CoI), Wang, X. (CoI) & Yang, Y. (CoI)
01/08/2017 → 01/12/2023
Project: Research
APETT: Advanced Power Electronic Technology and Tools
Blaabjerg, F. (PI), Munk-Nielsen, S. (CoI), Iannuzzo, F. (Project Participant), Wang, H. (Project Participant), Uhrenfeldt, C. (Project Participant), Beczkowski, S. (Project Participant), Zhou, D. (Project Participant), Choi, U. (Project Participant), Jørgensen, A. B. (Project Participant), Vernica, I. (Project Participant), Sangwongwanich, A. (Project Participant), Christensen, N. (Project Participant), Ceccarelli, L. (Project Participant), Nielsen, C. K. (Project Participant), Bahman, A. S. (Project Participant), Pedersen, K. (Project Participant), Pedersen, K. B. (Project Participant) & Kristensen, P. K. (Project Participant)
Innovation Fund Denmark
01/01/2017 → 30/06/2021
Project: Research
Multi-Physics of High Power Density Power Electronic Systems
Davari, P. (PI) & Steffensen, B. (Project Coordinator)
DFF-Individuelle postdocstipendier : DFF-1333-00034
01/03/2016 → 31/05/2018
Project: Research

Cite this

@inproceedings{6fad68814e6445d291a2410d2bdbd55d,

title = "Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems",

abstract = "In modern design of power electronic converters, reliability of dc-link capacitors is one of the critical considered aspects. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. However, the existing condition monitoring methodologies are rarely adopted by industry due to shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of newcondition monitoring methodologies that are based on advanced software and requires no extra hardware could be more attractive to industry. In this digest, a condition monitoring methodology that estimates the capacitance value of the dc-link capacitor in a three phase Front-End diode bridge motor drive is proposed. The proposed software methodology is based on Artificial Neural Network (ANN) algorithm. The harmonics of the dc-link voltage are usedas training data to the Artificial Neural Network. Fast Fourier Transform (FFT) of the dc-link voltage is analysed in order to study the impact of capacitance variation on the harmonics order. Laboratory experiments are conducted tovalidate the proposed methodology and the error analysis of the estimated results is also studied.",

author = "Soliman, {Hammam Abdelaal Hammam} and Pooya Davari and Huai Wang and Frede Blaabjerg",

year = "2017",

month = oct,

doi = "10.1109/ECCE.2017.8096961",

language = "English",

pages = "5795--5802",

booktitle = "Proceedings of 2017 IEEE Energy Conversion Congress and Exposition (ECCE)",

publisher = "IEEE Press",

note = "2017 IEEE Energy Conversion Congress and Exposition (ECCE) ; Conference date: 01-10-2017 Through 05-10-2017",

}

Soliman, HAH, Davari, P , Wang, H & Blaabjerg, F 2017, Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems. in Proceedings of 2017 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE Press, pp. 5795-5802, 2017 IEEE Energy Conversion Congress and Exposition (ECCE), Cincinnati, Ohio, United States, 01/10/2017. https://doi.org/10.1109/ECCE.2017.8096961

Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems. / Soliman, Hammam Abdelaal Hammam; Davari, Pooya ; Wang, Huai et al.
Proceedings of 2017 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE Press, 2017. p. 5795-5802.

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

TY - GEN

T1 - Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems

AU - Soliman, Hammam Abdelaal Hammam

AU - Davari, Pooya

AU - Wang, Huai

AU - Blaabjerg, Frede

PY - 2017/10

Y1 - 2017/10

N2 - In modern design of power electronic converters, reliability of dc-link capacitors is one of the critical considered aspects. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. However, the existing condition monitoring methodologies are rarely adopted by industry due to shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of newcondition monitoring methodologies that are based on advanced software and requires no extra hardware could be more attractive to industry. In this digest, a condition monitoring methodology that estimates the capacitance value of the dc-link capacitor in a three phase Front-End diode bridge motor drive is proposed. The proposed software methodology is based on Artificial Neural Network (ANN) algorithm. The harmonics of the dc-link voltage are usedas training data to the Artificial Neural Network. Fast Fourier Transform (FFT) of the dc-link voltage is analysed in order to study the impact of capacitance variation on the harmonics order. Laboratory experiments are conducted tovalidate the proposed methodology and the error analysis of the estimated results is also studied.

AB - In modern design of power electronic converters, reliability of dc-link capacitors is one of the critical considered aspects. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. However, the existing condition monitoring methodologies are rarely adopted by industry due to shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of newcondition monitoring methodologies that are based on advanced software and requires no extra hardware could be more attractive to industry. In this digest, a condition monitoring methodology that estimates the capacitance value of the dc-link capacitor in a three phase Front-End diode bridge motor drive is proposed. The proposed software methodology is based on Artificial Neural Network (ANN) algorithm. The harmonics of the dc-link voltage are usedas training data to the Artificial Neural Network. Fast Fourier Transform (FFT) of the dc-link voltage is analysed in order to study the impact of capacitance variation on the harmonics order. Laboratory experiments are conducted tovalidate the proposed methodology and the error analysis of the estimated results is also studied.

U2 - 10.1109/ECCE.2017.8096961

DO - 10.1109/ECCE.2017.8096961

M3 - Article in proceeding

SP - 5795

EP - 5802

BT - Proceedings of 2017 IEEE Energy Conversion Congress and Exposition (ECCE)

PB - IEEE Press

T2 - 2017 IEEE Energy Conversion Congress and Exposition (ECCE)

Y2 - 1 October 2017 through 5 October 2017

ER -

Capacitance estimation algorithm based on DC-link voltage harmonics using artificial neural network in three-phase motor drive systems

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Projects

REPEPS: REliable Power Electronic based Power System

APETT: Advanced Power Electronic Technology and Tools

Multi-Physics of High Power Density Power Electronic Systems

Cite this