TY - JOUR
T1 - Fault diagnosis for three-phase PWM rectifier based on deep feedforward network with transient synthetic features
AU - Kou, Lei
AU - Liu, Chuang
AU - Cai, Guo-wei
AU - Zhang, Zhe
AU - Zhou, Jia-ning
AU - Wang, Xue-mei
PY - 2020
Y1 - 2020
N2 - Three-phase PWM rectifiers are adopted extensively in industry because of their excellent properties and potential advantages. However, while the IGBT has an open-circuit fault, the system does not crash suddenly, the performance will be reduced for instance voltages fluctuation and current harmonics. A fault diagnosis method based on deep feedforward network with transient synthetic features is proposed to reduce the dependence on the fault mathematical models in this paper, which mainly uses the transient phase current to train the deep feedforward network classifier. Firstly, the features of fault phase current are analyzed in this paper. Secondly, the historical fault data after feature synthesis is employed to train the deep feedforward network classifier, and the average fault diagnosis accuracy can reach 97.85% for transient synthetic fault data, the classifier trained by the transient synthetic features obtained more than 1% gain in performance compared with original transient features. Finally, the online fault diagnosis experiments show that the method can accurately locate the fault IGBTs, and the final diagnosis result is determined by multiple groups results, which has the ability to increase the accuracy and reliability of the diagnosis results.
AB - Three-phase PWM rectifiers are adopted extensively in industry because of their excellent properties and potential advantages. However, while the IGBT has an open-circuit fault, the system does not crash suddenly, the performance will be reduced for instance voltages fluctuation and current harmonics. A fault diagnosis method based on deep feedforward network with transient synthetic features is proposed to reduce the dependence on the fault mathematical models in this paper, which mainly uses the transient phase current to train the deep feedforward network classifier. Firstly, the features of fault phase current are analyzed in this paper. Secondly, the historical fault data after feature synthesis is employed to train the deep feedforward network classifier, and the average fault diagnosis accuracy can reach 97.85% for transient synthetic fault data, the classifier trained by the transient synthetic features obtained more than 1% gain in performance compared with original transient features. Finally, the online fault diagnosis experiments show that the method can accurately locate the fault IGBTs, and the final diagnosis result is determined by multiple groups results, which has the ability to increase the accuracy and reliability of the diagnosis results.
KW - Deep feedforward network
KW - Fault diagnosis
KW - Open-circuit fault in IGBT
KW - Three-phase PWM rectifier
KW - Transient synthetic features
U2 - 10.1016/j.isatra.2020.01.023
DO - 10.1016/j.isatra.2020.01.023
M3 - Journal article
C2 - 31987580
SN - 0019-0578
VL - 101
SP - 399
EP - 407
JO - ISA Transactions
JF - ISA Transactions
ER -