Fault Diagnosis of Power Transformer Based on DDAG-SVM

Wei Guo Zhao; Li Ying Wang

doi:10.4028/www.scientific.net/AMR.121-122.819

Paper Titles

Research on Color Control for Color Scanner
p.797

A Replica Selection Decision in Cloud Computing Environment
p.801

Research of Machine Vision System about Robot Soccer Based on the HSV
p.807

Rolling Bearing Fault Diagnosis Based on Wavelet Packet Feature Entropy-MFSVM
p.813

Fault Diagnosis of Power Transformer Based on DDAG-SVM
p.819

Modeling Knowledge Employee’s Turnover Based on P-SVM
p.825

Modal Analysis of the Cable-Stayed Space Truss Combining ANSYS and MSC.ADAMS
p.832

Research on Robot Pose Control System Based on MMA7455
p.838

Booth Array Multiplier Based on Adiabatic Computing
p.843

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 121-122Fault Diagnosis of Power Transformer Based on...

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.