Power Transformer Fault Diagnosis Based on Least Squares Support Vector Machine and Particle Swarm Optimization

Xin Ma

doi:10.4028/www.scientific.net/AMM.50-51.624

Paper Titles

A New Heuristic Attribute Reduction Method Based on Boolean Matrix
p.605

The Prediction Research on Ports of Coasts Based on Grey Theory in Fangcheng Port
p.610

Finite Element Simulation of Springback in Sheet Metal Forming
p.615

Visual Simulation of Straight-Racket-Hit Skill of Table Tennis Based on MD2 Model
p.619

Power Transformer Fault Diagnosis Based on Least Squares Support Vector Machine and Particle Swarm Optimization
p.624

Control of Stochastic Energetic Resonance in a Bistable System
p.629

Robust Intrusion Detection Algorithm Based on K-Means and BP
p.634

Divergence Color Histogram for Content-Based Image Retrieval
p.639

A Kind of Web Database Classification Based on Machine Learning
p.644

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 50-51Power Transformer Fault Diagnosis Based on Least...

Power Transformer Fault Diagnosis Based on Least Squares Support Vector Machine and Particle Swarm Optimization

Abstract:

Dissolved gas analysis (DGA) is an important method to diagnose the fault of power t ransformer. Least squares support vector machine (LS-SVM) has excellent learning, classification ability and generalization ability, which use structural risk minimization instead of traditional empirical risk minimization based on large sample. LS-SVM is widely used in pattern recognition and function fitting. Kernel parameter selection is very important and decides the precision of power transformer fault diagnosis. In order to enhance fault diagnosis precision, a new fault diagnosis method is proposed by combining particle swarm optimization (PSO) and LS-SVM algorithm. It is presented to choose σ parameter of kernel function on dynamic, which enhances precision rate of fault diagnosis and efficiency. The experiments show that the algorithm can efficiently find the suitable kernel parameters which result in good classification purpose.

You might also be interested in these eBooks

Intelligent Structure and Vibration Control

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 50-51)

Pages:

624-628

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.50-51.624

Citation:

Cite this paper

Online since:

February 2011

Authors:

Xin Ma

Keywords:

Dissolved Gas Analysis, Fault Diagnosis, Least Squares Support Vector Machines (Ls-SVM), Particle Swarm Optimization Algorithm (PSO), Power Transformer

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Z. Zhang.: Application of Genetic Programming Based Discriminate Functions in the Insulation Fault Diagnosis of Power Transformers. Journal of Shanghai Jiaotong University, Vol. 40(2008), pp.558-562.

Google Scholar

[2] Z. Wang: An Artificial Neural Network Approach to Transformer Faults Diagnosis. High Voltage Research, Vol. 13 (2009), pp.1224-1229.

Google Scholar

[3] Fu Y.: Power Transformer Fault Diagnosis Using Weighted Fuzzy Kernel Clustering. High Voltage Engineering, Vol. 36(2010), pp.371-374.

Google Scholar

[4] H. Xiong: Study on Kernel Based Possibility Clustering and Dissolved Gas Analysis for Fault Diagnosis of Power Transformer. Proceedings of the CSEE, Vol. 25(2005), pp.162-166.

Google Scholar

[5] H.T. Yang: Intelligent Decision Support for Diagnosis of Incipient Transformers Faults using Self-organizing Polynomial Networks, IEEE Trans. on Power System, Vol. 13(1998), pp.946-952.

DOI: 10.1109/59.708845

Google Scholar