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

https://doi.org/10.1016/j.eswa.2009.11.015Get rights and content

Abstract

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.

Introduction

Recently, power quality (PQ) has become one of the most important issues in modern power industry. The origin of events affected quality of power is mainly electromagnetic transients, which are common phenomena in every electric power systems. A number of causes of transients can be identified: lightning strokes, planned switching actions in the distribution or transmission system, self-clearing faults or faults cleared by current-limiting fuses, and the switching of end-user equipment. Transient phenomena are extremely critical since they can cause over voltages leading to insulation breakdown or flashover. These failures might trip any protection device initiating a short interruption to the supplied power. Excess current produced by transients may lead to complete damage to system equipment during the transient period. Moreover, if such disturbances are not mitigated, they can lead to failures or malfunctions of various sensitive loads in power systems and may be very costly. Therefore, there is a growing need to develop PQ monitoring techniques that can classify the potential sources of disturbances (El-Saadany et al., 2004, Gaing, 2004, Gargoom et al., 2007). The classification or recognition topic is an important issue for the development of the next generation of PQ monitoring equipment. Basically, it refers to the use of signal processing techniques to extract as few as possible and representative features from disturbance signals, followed by the use of a powerful and a simple technique to classify the detected disturbances. In the literature, the signal processing techniques are available for analyzing PQ disturbance. However, the most important of those are Fourier transform (FT), short-time Fourier transform (STFT) and wavelet transform (WT) for useful feature extraction from signals.

Traditionally, the FT has been extensively used for analyzing the frequency contents of the signals. Besides, the FT is not an efficient analyzing tool for extracting the transient information of the non-stationary signals. Although the STFT divides the full-time interval into a number of small/equal-time intervals, can partly alleviate the problem, the STFT still has the limitation of a fixed window width. It is difficult to detect the occurrence times for very-short-duration and high-frequency signals. In order to avoid the disadvantages of both FT and STFT, the WT has been widely used for analyzing the PQ problems. The WT approach prepares a window that automatically adjusts to give proper resolutions of both the time and the frequency. In the approach, a larger resolution of time is provided to high-frequency components of a signal, and a larger resolution of frequency to low-frequency components. These features make the WT well suited for the analysis of the power system transients caused by various disturbances.

A number of papers on automatic classification of PQ problems have been published during the last several years. These can be roughly divided into two groups as classification of disturbance waveforms and classification of events based on their origin. In first group of the classification usually called disturbance classification, the detected disturbances are classified in a number of typical classes such as voltage sags, voltage swells, and interruptions, etc. In several studies (Gaing, 2004, He and Starzyk, 2006, Huang et al., 2002, Uyar et al., 2008) based on WT, the feature vectors representing the disturbance signals are obtained by using different feature extraction techniques to WT coefficients. Resulting feature vectors are applied as inputs to artificial intelligent techniques such as artificial neural network (ANN), fuzzy systems and support vector machine (SVM). They are showed that typical PQ disturbances are correctly classified. In second group of the classification called event classification, the underlying causes of disturbances such as faults, capacitor switching, and transformer energizing are classified. In the literature papers (Axelberg et al., 2007, Bollen et al., 2007, Hong and Wang, 2005, Santoso et al., 2000, Silva et al., 2006, Styvaktakis et al., 2002) about event classification, it can be generally seen that three feature vectors representing an event are obtained by applying several feature extracting techniques to three phase voltage signals of detected event. In these papers, feature vectors are created using total harmonic distortion values, harmonic magnitudes, root mean square (RMS) values, energy values of WT coefficients, and WT coefficients obtained from event signals. As the classifier, SVM, ANN, self-organizing mapping neural network, and expert system are used.

In this paper, an automatic event classification algorithm is proposed for identifying the PQ events. Firstly, the wavelet multi-resolution analysis (WMRA) technique is employed to extract the features of the three phase event signals. Single feature vector for each event is obtained from another feature extraction technique applied three phase signal features. Secondly, the SVM is used to classify event types. Finally, event signals generated by the ATP/EMTP are applied to the proposed algorithm for both noiseless and noisy environments. The experimental results showed that the proposed method could analyze and classify the event signals efficiently.

The novelty presented in this paper can be summarized as follows:

An effective single feature vector representing a three-phase event signal is offered for automatic PQ event classification. Moreover, proposed algorithm has the advantage of monitoring all phases of the three-phase signal simultaneously and the great potential because of practical implementation and high classification accuracy.

The remaining part of the paper is organized as follows. In Section 2, it is given several brief definitions of WT and WMRA. A short review to SVM classifiers is presented in Section 3. Section 4 contains the proposed automatic classification algorithm. Simulations and discussion for proposed algorithm are given in Section 5. Finally, conclusions are discussed in Section 6.

Section snippets

Wavelet transform theory

Due to its ability to extract time and frequency information of signal simultaneously, the WT is an attractive technique for analyzing PQ waveform. It is particularly attractive for studying disturbance or transient waveform, where it is necessary to examine different frequency components separately. WT can be continuous or discrete. Discrete WT (DWT) can be viewed as a subset of Continuous WT (CWT). In practical applications, the DWT is commonly used. The DWT is normally implemented by

Support vector machines for classification

SVM is a powerful tool for solving pattern classification problems (Cortes and Vapnik, 1995, Vapnik, 1998). Given the training data (x1, y1), …, (x, y), x ϵ RM, yi ϵ {−1, +1} for two class problem, SVM constructs the decision functions of form sgn((wTxi) + w0) by the maximum margin, where w is the normal vector of the separating hyperplane in the canonical form and wo is a bias term (Vapnik, 1998). The distances of the point closest to the hyperplanes of both −1 and +1 are calculated as 1/||w||. The

Automatic power quality event classification algorithm

The proposed algorithm for PQ event classification is divided into the three stages: pre-processing, feature extraction, and classification shown as Fig. 2. In this algorithm, the segmentation and normalization processes are applied to PQ event signals. A distinctive feature vector for per event is extracted by using the WMRA. PQ events are classified by using feature vectors obtained from feature extraction stage. Then, proposed algorithm is tested for both the noisy and noiseless PQ event

PQ events

In this paper, in order to evaluate the proposed algorithm, seven classes of PQ events are considered as the classification problem. These events are divided into two main groups: fault-induced events and switching events. Besides, normal class (C1) named undisturbed sinusoid is selected for non-event case. For fault-induced events, three major event types of faults which are phase-to-ground fault (C2), phase-to-phase fault (C3) and three-phase fault (C4) are chosen. The load switching event

Conclusions

The large number of PQ events occurs in the power systems. Hence, there is a need for a new technique that can be used for automated classification of PQ events. This paper introduced a new algorithm to distinguish the types of PQ events. The technique is based on the WMRA and SVM classifier. Unlike most of the literature studies for automatic PQ event classification having three feature vectors for an event or based on single-phase analysis techniques, the proposed technique has single feature

Acknowledgments

This work is supported by Firat University Scientific Research Unit (FUBAP) (Project No. FUBAP-1605).

References (24)

  • M. Uyar et al.

    An effective wavelet-based feature extraction method for classification of power quality disturbance signals

    Electric Power Systems Research

    (2008)
  • N. Zhang et al.

    A real time fault analysis tool for monitoring operation of transmission line protective relay

    Electric Power Systems Research

    (2007)
  • S. Abe

    Support vector machines for pattern classification

    (2005)
  • P.G.V. Axelberg et al.

    Support vector machine for classification of voltage disturbances

    IEEE Transactions on Power Delivery

    (2007)
  • D.P. Bertsekas

    Nonlinear programming

    (1999)
  • Bollen, H. J., Gu, I. Y. H., Axelberg, P. G. V., & Styvaktakis, E. (2007). Classification of underlying causes of power...
  • M.H.J. Bollen et al.

    Signal processing of power quality disturbances

    (2006)
  • CanAm EMTP User Group. (1992). Alternative transient program (ATP) rule book,...
  • Chang, C. C., & Lin, C. J. (2001). LIBSVM: A library for support vector machines. Available from...
  • Chen, S., & Zhu, H. Y. (2007). Wavelet transform for processing power quality disturbances. EURASIP Journal on Advances...
  • C. Cortes et al.

    Support vector networks

    Machine Learning

    (1995)
  • P.K. Dash et al.

    Hybrid S-transform and Kalman filtering approach for detection and measurement of short duration disturbances in power networks

    IEEE Transactions on Institutions and Measurements

    (2004)
  • Cited by (91)

    • Research challenges in real-time classification of power quality disturbances applicable to microgrids: A systematic review

      2020, Renewable and Sustainable Energy Reviews
      Citation Excerpt :

      For the PQ distortions considered in the previous studies, it was determined that 49% of works considered combined distortions while 33% modeled simple distortions exclusively. The remaining 18% of studies not only classified PQ distortions, but also events that cause PQ distortions [38–40,94,110,115,120,128,129,133–135,137,149,152,156,157]. A little more than half of the works considered the study of the effect of noise on classification performance.

    View all citing articles on Scopus
    View full text