TY - GEN
T1 - Artificial Neural Network based DC-link capacitance estimation in a diode-bridge front-end inverter system
AU - Soliman, Hammam
AU - Abdelsalam, Ibrahim
AU - Wang, Huai
AU - Blaabjerg, Frede
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/25
Y1 - 2017/7/25
N2 - In modern design of power electronic converters, reliability of DC-link capacitors is an essential aspect to be considered. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. The existing condition monitoring methods suffer from shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of new condition monitoring methodologies that are based on advanced software algorithms could be the way out of the aforementioned challenges and shortcomings. In this paper, a proposed software condition monitoring methodology based on Artificial Neural Network (ANN) algorithm is presented. Matlab software is used to train and generate the proposed ANN. The proposed methodology estimates the capacitance of the DC-link capacitor in a three phase front-end diode bridge AC/DC/AC converter. The estimation is based on the usage of single phase output current and dc-link voltage ripple. The impact of training data type, source and amount are also investigated for estimation accuracy analysis. Experimental validation of the proposed method is also conducted.
AB - In modern design of power electronic converters, reliability of DC-link capacitors is an essential aspect to be considered. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. The existing condition monitoring methods suffer from shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore, development of new condition monitoring methodologies that are based on advanced software algorithms could be the way out of the aforementioned challenges and shortcomings. In this paper, a proposed software condition monitoring methodology based on Artificial Neural Network (ANN) algorithm is presented. Matlab software is used to train and generate the proposed ANN. The proposed methodology estimates the capacitance of the DC-link capacitor in a three phase front-end diode bridge AC/DC/AC converter. The estimation is based on the usage of single phase output current and dc-link voltage ripple. The impact of training data type, source and amount are also investigated for estimation accuracy analysis. Experimental validation of the proposed method is also conducted.
UR - http://www.scopus.com/inward/record.url?scp=85034047413&partnerID=8YFLogxK
U2 - 10.1109/IFEEC.2017.7992442
DO - 10.1109/IFEEC.2017.7992442
M3 - Conference contribution
AN - SCOPUS:85034047413
T3 - 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017
SP - 196
EP - 201
BT - 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017
Y2 - 3 June 2017 through 7 June 2017
ER -