Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Shanghai Jiaotong University》 2005-S1
Add to Favorite Get Latest Update

A New Fault Diagnosis Method Based on Dissolved Gases Analysis for Power Transformer

DONG Li-xin1, XIAO Deng-ming1, L[AKU¨5] Gan-yun1, LIU Yi-lu2(1. School of Electronic,Information and Electrical Eng., Shanghai Jiaotong Univ., Shanghai 200240, China; 2. Dept. of Electrical Eng., Virginia Univ. of Tech, Virginia)  
A fuzzy tight wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis for power transformer using dissolved gas-in-oil analysis(DGA) was proposed. The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function, combining the advantages of wavelet analysis and neural networks. In the system diagnosis process, six trained child fuzzy wavelets, which have the same training sample set, different learning rate, middle hidden layer number and correlative parameter, diagnose the fault respectively, then the diagnosis results of the six child fuzzy wavelets NN are fused with LS weighted fusion algorithm, and the fault types with the fused result are identified finally. The mechanism has a good classified diagnosis ability. The advantages and effectiveness of this method are verified by the test.
【Fund】: 国家自然科学基金资助项目(50128706)
【CateGory Index】: TM407
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved