Energy and entropy-based feature extraction for locating fault on transmission lines by using neural network and wavelet packet decomposition

The aim of this paper is to estimate the fault location on transmission lines quickly and accurately. The faulty current and voltage signals obtained from a simulation are decomposed by wavelet packet transform (WPT). The extracted features are applied to artificial neural network (ANN) for estimating fault location. As data sets increase in size, their analysis become more complicated and time consuming. The energy and entropy criterion are applied to wavelet packet coefficients to decrease the size of feature vectors. The test results of ANN demonstrate that the applying of energy criterion to current signals after WPT is a very powerful and reliable method for reducing data sets in size and hence estimating fault locations on transmission lines quickly and accurately.

[1]  M. Fikri,et al.  New algorithm for distance protection of high voltage transmission lines , 1988 .

[2]  Hiroyuki Mori,et al.  A fault detection technique with preconditioned ANN in power systems , 2002, IEEE/PES Transmission and Distribution Conference and Exhibition.

[3]  Mohamed A. H. El-Sayed,et al.  Artificial neural network for reactive power optimization , 1998, Neurocomputing.

[4]  M. M. Morcos,et al.  A fault locator for transmission lines based on Prony method , 1999, 1999 IEEE Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.99CH36364).

[5]  Subir Ray,et al.  Electrical Power Systems , 2007 .

[6]  Mladen Kezunovic,et al.  Locating faults in the transmission network using sparse field measurements, simulation data and genetic algorithm , 2004 .

[7]  M. Joorabian.  Artificial intelligent based fault location technique for EHV series-compensated lines , 1998, Proceedings of EMPD '98. 1998 International Conference on Energy Management and Power Delivery (Cat. No.98EX137).

[8]  Chen Xiangxun,et al.  Travelling wave fault location of transmission line using wavelet transform , 1998, POWERCON '98. 1998 International Conference on Power System Technology. Proceedings (Cat. No.98EX151).

[9]  Eugeniusz Rosolowski,et al.  A new accurate fault locating algorithm for series compensated lines , 1999 .

[10]  Jie Liang,et al.  Application of wavelet transform in travelling wave protection , 2000 .

[11]  In-Keun Yu,et al.  Wavelet analysis and neural network based adaptive single-pole autoreclosure scheme for EHV transmission systems , 1998 .

[12]  Tuan Van Pham,et al.  DWT-based classification of acoustic-phonetic classes and phonetic units , 2004, INTERSPEECH.

[13]  A. Elhaffar,et al.  Travelling waves based earth fault location in 400 kV transmission network using single end measurement , 2004, 2004 Large Engineering Systems Conference on Power Engineering (IEEE Cat. No.04EX819).

[14]  Matti Lehtonen,et al.  Earth fault distance computation with fundamental frequency signals based on measurements in substation supply bay , 2002 .

[15]  Ronald R. Coifman,et al.  Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.

[16]  F. Mörchen.  Time series feature extraction for data mining using DWT and DFT , 2003 .

[17]  CHENG HONG,et al.  WAVELET PACKETS ANALYSIS AND ARTIFICIAL INTELLIGENCE BASED ADAPTIVE FAULT DIAGNOSIS , 1999 .

[18]  E. E. Dungan.  Electrical power systems studies at MSFC , 1965 .

[19]  Zhikun Hou,et al.  A Wavelet Packet Based Sifting Process and its Application for Structural Health Monitoring , 2005, Proceedings of the 2004 American Control Conference.

[20]  Ampol Tungkanawanich,et al.  Ground Fault Discrimination based on Wavelet Transform using Artificial Neural Networks , 2000 .

[21]  Loi Lei Lai,et al.  Fault location of a teed-network with wavelet transform and neural networks , 2000, DRPT2000. International Conference on Electric Utility Deregulation and Restructuring and Power Technologies. Proceedings (Cat. No.00EX382).

[22]  Alan S. Willsky,et al.  A Wavelet Packet Approach to Transient Signal Classification , 1995 .