A hybrid intelligence approach for power quality disturbances detection and classification

SUMMARY This paper presents a new synthetic methodology for detection and classification of different Power Quality Disturbances (PQDs). Gabor Transform (GT) integrated by a Probabilistic Neural Network (PNN) model is designed for implementation of a pattern recognition system. The approach uses features extracted from the output Matrix of GT as an input vector of a PNN classifier. The key attribute of GT is that it yields good time-frequency resolution with low computation burden. The PNN learner without any iteration for tuning weights classifies nine types of the most common PQDs including simultaneous events. The performance of the algorithm based on the combination of the GT and PNN (GT-PNN) is evaluated by generated data using parametric equations and a simulated network in the PSCAD/EMTDC software environment. The obtained numerical results confirm the effectiveness of GT-PNN approach for recognition of the different PQDs. Moreover, the classification accuracy is evaluated in the noisy conditions. Copyright © 2012 John Wiley & Sons, Ltd.

[1]  G. Jang,et al.  Time-Frequency Analysis of Power-Quality Disturbances via the Gabor–Wigner Transform , 2010, IEEE Transactions on Power Delivery.

[2]  S. J. Huang,et al.  Application of Gabor transform technique to supervise power system transient harmonics , 1996 .

[3]  Wee Ser,et al.  Probabilistic neural-network structure determination for pattern classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Jovitha Jerome,et al.  Pattern recognition of power signal disturbances using S Transform and TT Transform , 2010 .

[5]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[6]  Zahra Moravej,et al.  Detection and Classification of Power Quality Disturbances Using Wavelet Transform and Support Vector Machines , 2009 .

[7]  Shie Qian,et al.  Discrete Gabor transform , 1993, IEEE Trans. Signal Process..

[8]  M. Uyar,et al.  An effective wavelet-based feature extraction method for classification of power quality disturbance signals , 2008 .

[9]  Rajiv Kapoor,et al.  Hybrid demodulation concept and harmonic analysis for single/multiple power quality events detection and classification , 2011 .

[10]  Salvatore Nuccio,et al.  A chirp-z transform-based synchronizer for power system measurements , 2005, IEEE Transactions on Instrumentation and Measurement.

[11]  Rashid Alammari,et al.  Power quality analysis based on fuzzy estimation algorithm : Voltage flicker measurements , 2006 .

[12]  Zahra Moravej,et al.  Wavelet transform and multi‐class relevance vector machines based recognition and classification of power quality disturbances , 2011 .

[13]  Zahra Moravej,et al.  New Combined S-transform and Logistic Model Tree Technique for Recognition and Classification of Power Quality Disturbances , 2011 .

[14]  Thanatchai Kulworawanichpong,et al.  Recognition of power quality events by using multiwavelet-based neural networks , 2008 .

[15]  Math Bollen,et al.  Time-frequency and time-scale domain analysis of voltage disturbances , 2000 .

[16]  Gerald T. Heydt,et al.  Applications of the windowed FFT to electric power quality assessment , 1999 .

[17]  Carlos A. Duque,et al.  Power quality events recognition using a SVM-based method , 2008 .

[18]  R. Sukanesh,et al.  Power quality disturbance classification using Hilbert transform and RBF networks , 2010, Neurocomputing.

[19]  S. Mishra,et al.  Detection and Classification of Power Quality Disturbances Using S-Transform and Probabilistic Neural Network , 2008, IEEE Transactions on Power Delivery.

[20]  Jong-Beom Lee,et al.  A fuzzy-expert system for classifying power quality disturbances , 2004 .

[21]  Whei-Min Lin,et al.  Detection and Classification of Multiple Power-Quality Disturbances With Wavelet Multiclass SVM , 2008, IEEE Transactions on Power Delivery.

[22]  E.F. El-Saadany,et al.  Power quality disturbance classification using the inductive inference approach , 2004, IEEE Transactions on Power Delivery.

[23]  Mario Oleskovicz,et al.  Power quality analysis applying a hybrid methodology with wavelet transforms and neural networks , 2009 .

[24]  H. He,et al.  A self-organizing learning array system for power quality classification based on wavelet transform , 2006, IEEE Transactions on Power Delivery.

[25]  Zhen Ren,et al.  Power quality disturbance identification using wavelet packet energy entropy and weighted support vector machines , 2008, Expert Syst. Appl..