Open AccessTransient signal identification of HVDC transmission lines based on wavelet entropy and SVM
Author(s) -
Luo Guomin,
Yao Changyuan,
Tan Yingjie,
Liu Yinglin
Publication year - 2019
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2018.8555
Subject(s) - wavelet , transient (computer programming) , computer science , transmission line , wavelet transform , support vector machine , electric power transmission , entropy (arrow of time) , electric power system , pattern recognition (psychology) , electronic engineering , time–frequency analysis , engineering , artificial intelligence , control theory (sociology) , power (physics) , telecommunications , electrical engineering , physics , radar , quantum mechanics , operating system , control (management)
High‐voltage DC (HVDC) transmission plays an important role in power transmission projects due to its advantages of large transmission power and good control performance. As the main protection of the DC transmission line, transient protection uses the high‐frequency signal generated by fault transient to detect faults, having the characteristics of fast response and high accuracy. However, the HVDC transmission line has complex conditions along the route and is vulnerable to lightning strikes and other accidents, resulting in the occurrence of a variety of transients in the line, which increases the difficulty of fault identification. Being able to reveal signal time‐frequency characteristic, wavelet entropy is an effective tool of signal recognition. This study proposes a method of transient signal identification based on the wavelet entropy and support vector machine (SVM). Firstly, the transient processes of three kinds of signals, including unipolar faults, lightning strike faults, and lightning disturbances, are briefly introduced. Then the time−frequency features of three kinds of transient signals under different scenes are analysed by wavelet entropy. Finally, the training set was used to train the SVM classification model with the signal wavelet entropy being taken as the eigenvector, and the test results validate the effectiveness of the proposed method.