DocumentCode :
2474545
Title :
Rough set neural network based fault line detection for neutral non-effectively grounded system
Author :
Pang, Qingle
Author_Institution :
Sch. of Inf. & Electron. Eng., Shandong Inst. of Bus. & Technol., Yantai
fYear :
2008
fDate :
25-27 June 2008
Firstpage :
6550
Lastpage :
6554
Abstract :
A novel fault line detection method based on rough set neural network is proposed to avoid the longtime training and the complicated model structure for the neural network based fault line detection model. Through performing single-phase-to-earth fault experiments by means of the ATP-EMTP simulation program, the zero sequence currents of every line are obtained. The fault features are extracted from zero sequence currents by using wavelet transform method, the fifth harmonic current method, zero sequence current active component method and fundamental current component amplitude comparison. These fault features are transformed into fault measures according to properties of each fault feature. The fault measures of lines make up of the original data table and these discretized data construct decision table. Then the decision table is reduced through attribute reduction and rule reduction. The reduced condition attributes are regarded as inputs of the neural network and the reduced samples are used to training neural network. The neural network model trained can realize fault line detection. The simulation results show that the method reaches higher training speed and lower error rate.
Keywords :
EMTP; decision tables; earthing; fault currents; fault diagnosis; feature extraction; neural nets; power system harmonics; rough set theory; signal detection; wavelet transforms; ATP-EMTP simulation program; attribute reduction; data discretization; data table; decision table; fault feature extraction; fault line detection; fault measure; fifth harmonic current method; fundamental current component amplitude comparison; neutral noneffectively grounded system; rough set neural network; rule reduction; single-phase-to-earth fault experiment; wavelet transform; zero sequence current active component method; Automation; Clustering algorithms; Data mining; Fault detection; Feature extraction; Intelligent control; Load forecasting; Neural networks; Set theory; Wavelet transforms; Fault line detection; Neural network; Neutral non-effectively grounded system; Rough set theory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
Type :
conf
DOI :
10.1109/WCICA.2008.4592892
Filename :
4592892
Link To Document :
بازگشت