Envelope signal of partial discharge pattern recognition based on wavelet packet transform

doi:10.4028/www.scientific.net/AMR.823.536

	Envelope signal of partial discharge pattern recognition based on wavelet packet transform
	Luo, Dongsong; Chen, Kunpeng
	2013
会议日期	October 27, 2013 - October 28, 2013
会议地点	Wuhan, Hubei, China
关键词	Defects Fault detection Feature extraction Industrial engineering Neural networks Partial discharges Singular value decomposition BP neural networks Coefficient matrix Discharge characteristics Feature vectors Insulation defects Partial discharge pattern recognition Ultra-high frequency Wavelet packet transforms
卷号	823
DOI	10.4028/www.scientific.net/AMR.823.536
页码	536-540
英文摘要	In order to achieve the GIS fault detection and defect type recognition, four typical defect models were designed and discharge tests are carried out aiming at insulation defect as well as discharge characteristics in the GIS.With a large number of ultra high frequency envelope signal,a method of domain feature extraction was proposed based on wavelet packet transform with singular value decomposition.The envelope signal was decomposed through wavelet packet transform first in the method, then the coefficient matrix of wavelet packet transform was built in the scale,after that feature vectors of matrix were extracted by means of singular value decomposition. On this basis, BP neural network was took advantage of for pattern recognition.The results show that the good recognition effect was obtained with that method. © (2013) Trans Tech Publications, Switzerland.
会议录	Advanced Materials Research
会议录出版者	Trans Tech Publications Ltd, Kreuzstrasse 10, Zurich-Durnten, CH-8635, Switzerland
语种	英语
ISSN号	10226680
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/117565]
专题	电气工程与信息工程学院
作者单位	College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China
推荐引用方式 GB/T 7714	Luo, Dongsong,Chen, Kunpeng. Envelope signal of partial discharge pattern recognition based on wavelet packet transform[C]. 见:. Wuhan, Hubei, China. October 27, 2013 - October 28, 2013.