Inrush current method of transformer based on wavelet packet and neural network. Issue 16 (6th February 2019)

• Record Type: Journal Article
• Authors: Wang, Wei; Yan, Lin; Jin, Tao; Liu, Hong; Hu, Fan; Wu, Dongxun
• Is Part Of: Journal of engineering. Volume 2019:Issue 16(2019)
• Page Start: 1257
• Page End: 1260
• Publication Date: 2019-02-06
• Subjects: feature extraction -- wavelet transforms -- neural nets -- power engineering computing -- power transformer protection -- fault currents -- vectors -- signal reconstruction -- power system identification; neural network -- power system -- operation state -- security -- stability -- power transformer -- recognition method -- fault current signal -- wavelet packet reconstruction coefficients -- real‐time identification system -- inrush current method -- feature vectors; Engineering -- Periodicals; Engineering; Electronic journals; Periodicals; 620.005
• DOI: 10.1049/joe.2018.8847
• Languages: English
• ISSNs: 2051-3305

Abstract

Abstract : The transformer is an important equipment of power system; its operation state is directly related to the security and stability of the power system. Aiming at the problem that the differential protection of power transformer has been plagued by inrush current, a recognition method based on wavelet packet and the neural network is proposed. The inrush current and fault current signal are decomposed and reconstructed by using wavelet packet to extract wavelet packet reconstruction coefficients and calculate the energy of each band. These feature vectors are chosen as input values for the neural network. It has been shown by experiments that the inrush current and internal fault current can be accurately identified and the identification method can meet the requirement of the transformer inrush current real‐time identification system.