Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Diagnosis of Transformer Faults Based on Improved ANFIS

LIU Wei,SU Hong-sheng,ZENG Xiao-qin(College of Automation & Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)  
Based on dissolved gas analysis(DGA) in transformer oil,an adaptive neuro-fuzzy inference system(ANFIS) based transformer insulation fault diagnosis method is proposed in this paper.The system uses the three gas ratios of IEC Three-ratio Method as input vectors to construct three-input and one-output ANFIS,and then it is trained by hybrid learning arithmetic improved by Fletcher-Reeves conjugate gradient method.Finally,the availability of ANFIS is tested,and compared with BP trained ANFIS.The results show that the method based on ANFIS is feasible and the diagnosis accuracy is enhanced in identifying transformer faults.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved