Title :
The study of improved Fisher ratio for default diagnosis of power transformer
Author :
Liu, Donghui ; Liang, Youngchun ; Li, Aihua ; Bian, Jianpeng ; Sun, Xiaoyun
Author_Institution :
Sch. of Electr. Technol.&Inf. Sci., Hebei Univ. of Sci. & Technol., Shijiazhuang
Abstract :
Improved Fisher ratio method is presented in default diagnosis of power transformer based on dissolved gas analysis. Owing to the disadvantages of Fisher ratio method in RBF network structure optimization, authors put forward using improved Fisher ratio method to select the RBF centers, optimize the network structure. The results show that the neural structure is simplified strongly, the converged precision and class separability is improved, and this method is satisfied to diagnosis the default of power transformer.
Keywords :
fault diagnosis; power engineering computing; power transformers; radial basis function networks; RBF neural network structure; dissolved gas analysis; improved Fisher ratio method; power transformer default diagnosis; Algorithm design and analysis; Artificial neural networks; Clustering algorithms; Dissolved gas analysis; Equations; Neural networks; Optimization methods; Power system reliability; Power transformers; Radial basis function networks; Default diagnosis; Fisher ratio; Power transformer; RBF network; Structure optimization;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593977
