Extreme Learning Machine in the Breaker Fault Diagnosis

Dan Jiang; Shu Tao Zhao; Jian Feng Ren; Yu Tao Xu

doi:10.4028/www.scientific.net/AMR.960-961.896

Paper Titles

Analytic Theory and PIC Simulation of Electron Beam Generation under High Voltage
p.877

Development of a Portable XLPE Cable Insulation Detection Device
p.881

Suppression of Stochastic Pulses Interference in XLPE Cables Based on Fuzzy Clustering
p.885

Impacts of UHV on Short Circuit Currents in China's Central 500kV Grid and Its Countermeasures
p.891

Extreme Learning Machine in the Breaker Fault Diagnosis
p.896

Based on EEMD and Multiclass Relevance Vector for High Voltage Circuit Breaker Mechanical Fault Diagnosis
p.900

The Role of Improved K-Means Clustering Algorithm in the Motion Parameters Determination of Breaker's Moving Contact
p.905

A Novel PWM Technology Based on High-Power Current Source Inverter
p.910

Study on High-Voltage DC Power Supply for Electron Beam Furnace Based on Series Resonance
p.916

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 960-961Extreme Learning Machine in the Breaker Fault...

Extreme Learning Machine in the Breaker Fault Diagnosis

Abstract:

In order to improve the diagnosis method of the existing high-voltage circuit breaker fault, demonstrated a new diagnosis methord of mechanical failure of high voltage circuit breaker based on vibration signal. According to the factors of high voltage circuit breaker failure and the features of Single-hidden Layer Feedforward Neural Network, SLFN, a method of high voltage circuit breaker fault diagnosis proposed based on Extreme Learning Machine (ELM). Finally, the experiment proves the effectiveness of this method for breaker fault diagnosis based on vibration signal analysis and ELM.

You might also be interested in these eBooks

Thermal, Power and Electrical Engineering III

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 960-961)

Pages:

896-899

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.960-961.896

Citation:

Cite this paper

Online since:

June 2014

Authors:

Dan Jiang*, Shu Tao Zhao, Jian Feng Ren, Yu Tao Xu

Keywords:

Extreme Learning Machine, Fault Diagnosis, High-Voltage Circuit Breakers (HVCBs), Vibration Signal

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] CHEN Weigen, DENG Bangfei, YANG Bin. Fault recognition for high voltage circuit breaker based on EMD of vibration signal and energy entropy characteristic[J]. High Voltage Apparatus, 2009, 45(2): 90-96, in Chinese.

Google Scholar

[2] WU Zhensheng，WANG Wei，HUANG Mei，et al. Analysis of characteristics of vibration signals in high-voltage circuit breakers based on phase space reconstruction [J]. Modern Electric Power，2006，23(1)：10-14 , in Chinese.

Google Scholar

[3] MA Qiang, RONG Mingzhe, JIA Shenli. Study of switching synchronization of high voltage breakers based on the wavelet packets extraction algorithm and short time analysis method [J]. Proceeding of the CSEE, 2005, 25(13): 149-154, in Chinese.

Google Scholar

[4] SHU Juan, GAN Lei. Research on cost estimation of power lines construction projects based on extreme learning machine method [J]. Modern Electric Power, 2011, 28(04): 78-83, in Chinese.

Google Scholar

[5] CHANG Guang, ZHANG Zhenqian, WANG Yi. Review on Mechanical Fault Diagnosis of High-voltage Circuit Breakers Based on Vibration Diagnosis[J]. High Voltage Apparatus, 2011, 8(8): 85-89, in Chinese.

Google Scholar