Study on Fault Diagnosis of Power Transformer with Reduction Method of Attribute Significance

Hong Li Lv

doi:10.4028/www.scientific.net/AMR.1049-1050.665

Paper Titles

A Bandgap Reference with High Order Temperature Compensation
p.649

A Low Noise CMOS Digital Output Interface Circuit
p.653

Design of Isolated Flyback LED Driver Based on LYT4326E
p.657

Automatic Navigation of Intelligent Vehicle Control System Based on Laser Sensor
p.661

Study on Fault Diagnosis of Power Transformer with Reduction Method of Attribute Significance
p.665

Virtual Reactance Implementation Method for Droop-Controlled Three-Phase Microgrid Inverters Using SOGI Scheme
p.669

Design of Excitation Source for Ultrasonic Guided Waves Based on DDS Technology
p.674

Design of an Analog Control Circuit for the Automatic Sun-Tracking PV Bracket System
p.678

A Novel Circuit Design of the Wideband VGA in CMOS
p.682

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 1049-1050Study on Fault Diagnosis of Power Transformer with...

Study on Fault Diagnosis of Power Transformer with Reduction Method of Attribute Significance

Abstract:

This paper studies the power transformer fault quality diagnosis using rough sets theory and neural network. It is rough sets reduction as the pre-unit of neural network based on reduction algorithm with the attribute significance. The paper describes the reduction algorithm and implementation method detailed. Through the training and testing results with practical data, it is proved that the reduction algorithm with the attribute significance can make the number of input samples shorter, the training speed faster and the diagnostic accuracy higher. The algorithm is feasible and effective for applying to the fault diagnosis system of power transformer.

You might also be interested in these eBooks

Modern Technologies in Materials, Mechanics and Intelligent Systems

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 1049-1050)

Pages:

665-668

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1049-1050.665

Citation:

Cite this paper

Online since:

October 2014

Authors:

Hong Li Lv*

Keywords:

Attribute Reduction, Attribute Significance, Fault Diagnosis, Neural Network (NN), Rough Sets

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Pawlak Z. Rough set. International Journal of Computer and Information Science. 1982, 11 (5): 341-356.

Google Scholar

[2] Salvatore Greco, Benedetto Matarazzo, Roman Slowinski. Rough Sets Theory for Multicriteria Decision Analysis. European Journal of Operational Research 129(2001): 1-47.

DOI: 10.1016/s0377-2217(00)00167-3

Google Scholar

[3] Hu Xiaohua. Knowledge Discovery in Databases: An attribute-oriented rough set approach. Doctorial Dissertation. University of Regina, Canada, (1995).

Google Scholar

[4] Zhou Xianzhong. Rough Sets-based Theory and Approaches for Knowledge Acquisition in Incomplete Information Systems. Nanjing: Nanjing University Press, 2010. 12.

Google Scholar

[5] Liao Qiming. Research on Algorithm for Attribute Reduct & Core Computation Based on Rough Sets Theory. Changsha Univiersity of Science & Technology, 2012. 3.

Google Scholar

[6] Wang Xiaoying. Power Transformer Fault and Monitor . Beijing: China Machine Press, (2004).

Google Scholar

[7] Li Jian. Study on the Models of Fault Diagnosis about Power Transformer Based on Dissilved Gases Analysis . Chongqing University, (2001).

Google Scholar