Translated Title
Fault type identification for distribution network based on singular value decomposition and multi-level support vector machine
Translated Abstract
It is helpful for fault location and accident analysis to identify fault types in distribution network timely and accurately.In this paper,a method for fault identification based on Singular Value Decomposition (SVD) of Time-Frequency Matrix and Multi-Level Support Vector Machine (SVM) is proposed.First,7 fault waves including voltage and current of three-phase are pretreated by Hilbert-Huang Transform (HHT) band pass filter algorithm.And 7 time-frequency matrixes are reconstructed.After that,the time-frequency matrixes are decomposed by SVD,and parts of effective singular values are extracted to be characteristics for training and testing SVM.A model of 10kV distribution network is constructed by PSCAD/EMTDC to acquire samples for training and testing.The test results show that the identification accuracy of this method is excellent for identifying 10 faults including single-phase grounding,two-phase grounding,two-phase fault,three-phase fault in distribution network.What''s more,this method behaves good adaptability in circumstances of noise,asynchronous sampling,changes of network structure,load current,system equivalent impedance,arc suppression coil grounded system,and distributed power access.
Translated Keyword
distribution network
fault type identification
Hilbert-Huang transform
singular value decomposition (SVD)
support vector machine (SVM)
Access Number
WF:perioarticaldzclyyqxb201802011