Self-Organizing Feature Extraction Method for the High-Voltage Discharge Fault in Ultraviolet Imaging Detection System

Wei Wang; Li Xin Ma; Da Hai Huang

doi:10.4028/www.scientific.net/AMM.494-495.1731

Paper Titles

Multi-Objective Optimal Load Distribution Based on Sub Goals Multiplication and Division in Power Plants
p.1715

Dynamic Characteristic Analysis of Transmission Tower
p.1719

A Feasibility Urban Power Network Black-Start Scheme Based on Gas-Steam CCPP
p.1723

Planning of Terminal Unit Amount in Distribution Automation Systems
p.1727

Self-Organizing Feature Extraction Method for the High-Voltage Discharge Fault in Ultraviolet Imaging Detection System
p.1731

Research of Multi-Objective Power Network Planning Based on Improved Fish Swarm Algorithm
p.1735

Online Method for Location of Single Phase to Ground Fault through Cement Pole in Distribution Network
p.1739

Study on the User-Side Risk of Smart Grid System in Big Data Age
p.1743

Study on Technological Evaluation Modeling of Smart Grid
p.1747

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 494-495Self-Organizing Feature Extraction Method for the...

Self-Organizing Feature Extraction Method for the High-Voltage Discharge Fault in Ultraviolet Imaging Detection System

Abstract:

An ultraviolet detecting system for electrical faults is designed and built to locate the fault precisely and classify its pattern level as few studies have been done on. Self-organizing feature extraction method devotes itself to fault state recognition approach in high-voltage discharge. The established system including the filter system, image collection system, image preprocessing system, feature extraction, and pattern recognition could identify and classify device faults and operation conditions accurately tested by simulation.

You might also be interested in these eBooks

Current Development of Mechanical Engineering and Energy

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 494-495)

Pages:

1731-1734

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.494-495.1731

Citation:

Cite this paper

Online since:

February 2014

Authors:

Wei Wang, Li Xin Ma*, Da Hai Huang

Keywords:

Artificial Neural Network (ANN), Image Processing, Self-Organizing Feature Extraction, Status Recognition, UV Imaging Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Liu Tie, Lu Tiecheng, Li Jiansheng, He Qing, Tian Kan, Song Zhiguo. An Information Management and Evaluating System for High Voltage Electric Equipment Test Data, Automation of Electric Power Systems 31(12), 100-104(2007).

Google Scholar

[2] Chi Dianlin, Ceng Qingli, Sun Lishi. Detecting insulator by UV imaging, High Voltage Engine. 32 (2), 115 (2006).

Google Scholar

[3] An American National Standard, IEEE Standard Definitions of Terms Relating to overhead -Power -Line Corona and Ratio Noise, IEEE Std. 539-(1979).

DOI: 10.1109/ieeestd.1979.120962

Google Scholar

[4] Hu Jianping, Xin Zhou, Shugang Li, Zhicao Liu. Image processing method for laser damage probability measurement by single-shot of laser pulse, Opt. Express, Vol. 19 Issue 11, pp.10625-10631 (2011).

DOI: 10.1364/oe.19.010625

Google Scholar

[5] Xu Rujun, Lixin Ma, Bo Hu. Intelligent High-voltage Discharge Fault Detection and Its Diagnosis Methods Based on ANN, IPTC, 119-122(2011).

Google Scholar

[6] Shinya Fukumoto, Noritaka Shigei, Michiharu Maeda and Hiromi Miyajima. A Hybrid Learning Approach to Self-Organizing Neural Network for Vector Quantization,. IEICE Trans. Fundamentals. Vol. E86-A, No. 9: 2280-2286(2003).

DOI: 10.1109/isccsp.2008.4537249

Google Scholar