Open AccessTypical current modelling and feature extraction of high voltage circuit breaker towards condition analysis and fault diagnosis
Author(s) -
Ji Tianyao,
Ye Xiuzhen,
Shi Mengjie,
Li Mengshi,
Wu Qinghua
Publication year - 2020
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2018.5385
Subject(s) - softmax function , circuit breaker , computer science , cluster analysis , data mining , pattern recognition (psychology) , classifier (uml) , feature extraction , artificial intelligence , fault (geology) , engineering , artificial neural network , electrical engineering , seismology , geology
This study proposes a coil current model and an energy storage motor current (ESMC) model of circuit breakers (CBs) with spring operated mechanism. To make sure the signals generated by the models are identical to the actual ones, this study proposes a stochastic optimisation algorithm to optimise the model parameters. Based on the data produced by the optimised models, two fault diagnosis methods are proposed to assess operational condition and detect faults. The first method is based on fast template matching, which adopts K‐means clustering algorithm to cluster the data and form a template library. The second one combines deep belief network and Softmax classifier, which can not only extract high level information of the characteristic signals, but also avoid the negative impact of the large dimension on classification results. In the simulation studies, the two methods are tested on various scenarios and their merits are demonstrated, respectively, where the latter one shows superior performance.