Open AccessA new discrimination of stator single-phase grounding fault based on multi-dimensional fusion for Powerformer
Author(s) -
Tao Fang,
Yue Zhou,
Wenjing Liao,
Jue Su,
Wuchao Xie,
Jianxiong Xu,
Huahui Li,
Yun Li,
Xinquan Chen,
Hailin Su
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 - 10.1088/1742-6596/1633/1/012113
Subject(s) - stator , fusion , ground , fault (geology) , set (abstract data type) , computer science , phase (matter) , algorithm , pattern recognition (psychology) , engineering , artificial intelligence , electrical engineering , geology , physics , philosophy , linguistics , quantum mechanics , seismology , programming language
Some existing fusion discriminations are used to identify whether a stator single-phase grounding fault occurs in parallel Powerformers. However, such methods are complicated to operate and require a large amount of training data as support. Therefore, a new discrimination of stator single-phase grounding fault based on multi-dimensional fusion for Powerformer is proposed. Firstly, the faulty Manhattan distance and the sound Manhattan distance about each Powerformer are calculated by the fusion formula of Manhattan distance base on the four features extracted in Powerformer. Then, the sizes of the faulty and sound Manhattan distances about each Powerformer are compared. If the faulty Manhattan distance of the Powerformer is less than the sound Manhattan distance, the Powerformer can be judged as the fault, otherwise, it can be judged as the sound Powerformer. The simulation experiment show that this method does not need a large number of data as support, nor does need to set the threshold value artificially, so it improves the practicability and applicability of the method.