A simple geometry classifier based on normative spectrum of fault mode and its application in fault diagnosis of power transformer
ZHANG Deng-feng
LIU Shi-ya
WANG Xiang-dong
Abstract：Based on normative spectrum, modes for transformer is defined, a geometry classifier is developed with Euclidean distance, which is of simple structure and antijamming capability, so classifier is easily realized and suitable to be inserted into diagnosis systems on line. Finally, an example is given to illustrate our results based on dissolved oxygen analysis (DGA) and comparisons with previous related research results are made, which shows our method is valid.
Keywords：fault diagnosisnonlinear classifierpower transformerrobust stability
Publication Date：2015-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 50-54 )