A new algorithm for automatic classification of power quality events based on wavelet transform and SVM

被引:73
作者
Eristi, Hueseyin [1 ]
Demir, Yakup [2 ]
机构
[1] Tunceli Univ, Tunceli Vocat Sch, Tunceli, Turkey
[2] Firat Univ, Fac Engn, Dept Elect & Elect Engn, TR-23169 Elazig, Turkey
关键词
Automatic classification; Power quality events; Feature extraction; Wavelet transform; Support vector machines; RECOGNITION; SYSTEM;
D O I
10.1016/j.eswa.2009.11.015
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a new approach for automatic classification of power quality events, which is based on the wavelet transform and support vector machines. In the proposed approach, an effective single feature vector representing three phase event signals is extracted after signals are applied normalization and segmentation process. The kernel and penalty parameters of the support vector machine (SVM) are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. ATP/EMTP model for six types of power system events, namely phase-to-ground fault, phase-to-phase fault, three-phase fault, load switching, capacitor switching and transformer energizing, are constructed. Both the noisy and noiseless event signals are applied to the proposed algorithm. Obtained results indicate that the proposed automatic event classification algorithm is robust and has ability to distinguish different power quality event classes easily. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:4094 / 4102
页数:9
相关论文
共 24 条
[11]  
Daubechies I., 1992, Ten lectures on wavelets, DOI DOI 10.1137/1.9781611970104
[12]  
ELSAADANY EF, 2004, CANADIAN C ELECT COM, V2, P869
[13]   Wavelet-based neural network for power disturbance recognition and classification [J].
Gaing, ZL .
IEEE TRANSACTIONS ON POWER DELIVERY, 2004, 19 (04) :1560-1568
[14]   Investigation of effective automatic recognition systems of power-quality events [J].
Gargoom, Ameen A. ;
Ertugrul, Nesirni ;
Soong, Wen. L. .
IEEE TRANSACTIONS ON POWER DELIVERY, 2007, 22 (04) :2319-2326
[15]   A self-organizing learning array system for power quality classification based on wavelet transform [J].
He, HB ;
Starzyk, JA .
IEEE TRANSACTIONS ON POWER DELIVERY, 2006, 21 (01) :286-295
[16]   Switching detection/classification using discrete wavelet transform and self-organizing mapping network [J].
Hong, YY ;
Wang, CW .
IEEE TRANSACTIONS ON POWER DELIVERY, 2005, 20 (02) :1662-1668
[17]   A neural-fuzzy classifier for recognition of power quality disturbances [J].
Huang, JS ;
Negnevitsky, M ;
Nguyen, DT .
IEEE TRANSACTIONS ON POWER DELIVERY, 2002, 17 (02) :609-616
[18]   A THEORY FOR MULTIRESOLUTION SIGNAL DECOMPOSITION - THE WAVELET REPRESENTATION [J].
MALLAT, SG .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (07) :674-693
[19]   A scalable PQ event identification system [J].
Santoso, S ;
Lamoree, J ;
Grady, WM ;
Powers, EJ ;
Bhatt, SC .
IEEE TRANSACTIONS ON POWER DELIVERY, 2000, 15 (02) :738-743
[20]   Fault detection and classification in transmission lines-based on wavelet transform and ANN [J].
Silva, K. M. ;
Souza, B. A. ;
Brito, N. S. D. .
IEEE TRANSACTIONS ON POWER DELIVERY, 2006, 21 (04) :2058-2063