Abstract
Recently, condition monitoring of power transformer has become global due to the potential advantages to be gained from reduced maintenance costs, improved productivity and increased machine availability. In this paper, a novel fault measuring method base on relevance vector machine (RVM) is proposed for power transformer condition monitoring. Empirical results demonstrated that using, using similar training time, the RVM model has shown comparable generalization performance to the popular and state-of-the-art support vector machine (SVM), while the RVM requires dramatically fewer kernel functions and needs much less testing time. The results lead us to believe that the RVM is more powerful tool for on-line fault measuring method than the SVM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Moulin, L.S.: Support vector machines for transient stability analysis of large-scale power systems. IEEE Transactions on Power Systems 19(2), 818–825 (2004)
Kaplowicz, N.: Learning from imbalanced data sets: a comparison of various strategies. In: Proceeding of Learning from Imbalanced Data Sets, pp. 10–15. AAAI Press, Menlo Park (2000), Tech.Rep. WS-00-05
Browne, M.W.: Cross-validation methods. Journal of the Mathematical Psychology 44, 108–132 (2000)
Kaplowicz, N.: Learning from imbalanced data sets: a comparison of various strategies. In: Proceeding of Learning from Imbalanced Data Sets, pp. 10–15. AAAI Press, Menlo Park (2000), Tech.Rep. WS-00-05
Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. Mach. Learning 1, 211–244 (2001)
Shang, Y.: Synthetic insulation fault diagnose model of oil-immersed power transformers utilizing information fusion. Elec. Eng. (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, K. (2012). Design of Power Transformer Fault Measuring Model Based on Relevance Vector Machine. In: Jin, D., Lin, S. (eds) Advances in Mechanical and Electronic Engineering. Lecture Notes in Electrical Engineering, vol 177. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31516-9_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-31516-9_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31515-2
Online ISBN: 978-3-642-31516-9
eBook Packages: EngineeringEngineering (R0)