Open AccessA short circuit fault diagnosis method for DC voltage converter based on neural network
Author(s) -
Zhenghong Xu,
Chao Song,
Junxia Liu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1486/2/022002
Subject(s) - fault (geology) , artificial neural network , computer science , network packet , process (computing) , voltage , stuck at fault , wavelet , algorithm , pattern recognition (psychology) , control theory (sociology) , artificial intelligence , engineering , fault detection and isolation , electrical engineering , actuator , seismology , geology , computer network , control (management) , operating system
Aiming at the problem of complicated data calculation and slow data iteration in the diagnosis process of the tra ditional wavelet packet decomposition method for DC voltage converter short circuit fault diagnosis, a short circuit fault diagnosis method based on neural network is proposed. After determinin g which phase has a short circuit, the MMC method is used to locate the specific short circu it fault position. The basic structure of the neural network is determined according to the needs of short circuit fault diagnosis of the converter, and the training sample set is used to train the neural network and determine its parameters. Combined with fault location and fault characteristics, the short circu it fault diagnosis of the converter is completed by using neural network. By comparing with the short circu it fault diagnosis method based on wavelet packet decomposition, it is proved that the proposed short circuit fault diagnosis method based on neural network can complete several iterations in a short time and realize the high efficiency of fault diagnosis.