Paper Title:
Fault Diagnosis of Power Transformer Based on DDAG-SVM
  Abstract

Support vector machine (SVM) is a novel machine learning method based on statistical learning theory. SVM is powerful for the problem with small sampling, nonlinear and high dimension. A decision directed acyclic graph(DDAG) based on SVM classifier is applied to fault diagnosis of power transformer. We optimize the structure of a decision directed acyclic graph by putting SVM with higher generalization ability at the upper nodes of the decision tree. The test results show that the classifier has an excellent performance on training speed and reliability.

  Info
Periodical
Advanced Materials Research (Volumes 121-122)
Edited by
Donald C. Wunsch II, Honghua Tan, Dehuai Zeng, Qi Luo
Pages
819-824
DOI
10.4028/www.scientific.net/AMR.121-122.819
Citation
W. G. Zhao, L. Y. Wang, "Fault Diagnosis of Power Transformer Based on DDAG-SVM", Advanced Materials Research, Vols. 121-122, pp. 819-824, 2010
Online since
June 2010
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Xin Gang Chen, Yang Yang Zhao, Chao Feng Zhang, Xiao Xiao Tian
Chapter 4: Fault Diagnose and Electronmechanical Control
Abstract:As one of the most important equipments in the power system, partial discharge (PD) affects the transformer’s properties in a long-term...
933
Authors: Xuan Hu He, Ming Chao Xia
Chapter 5: Computer-Aided Design in Materials Engineering
Abstract:The advantages and disadvantages of various power transformer fault detection methods are analyzed. According to the different sonic...
1250
Authors: Ping He, Zhi Jie Zhu, Hong Cheng Jiang
Chapter 6: Power System and Automation
Abstract:In a centralized control center SCADA system, thousands of real-time data are sent to SCADA, including real-time signal, telemetering and...
971
Authors: Fa Ming Wang, Hao Sun, Yuan Chao Hu, Qi Jia Xie, Wen Dai
Chapter 4: Sensors, Measurement, Monitoring and Detection
Abstract:The development of smart grid puts higher requirement on the intelligentization of high-voltage equipment including transformers. At present,...
1005