Classification of Stockwell Transform Based Power Quality Disturbance with Support Vector Machine and Artificial Neural Networks

Öz

The detection and classification of power quality events that disturb the voltage and/or current waveforms in the electrical power distribution networks is very important to generate electrical energy and to deliver this energy to the end-user equipment at an acceptable voltage. Various property extraction methods are used to determine the type of disturbances in the electrical signal. In this study, seven power distortions including voltage sag, voltage swell, voltage harmonics, voltage sag with harmonics, voltage swell with harmonics, flicker, transient signals and pure sine as a reference signal is used. Synthetic data are produced in MATLAB using parametric equations based on TS EN 50160 standard. Four kinds of feature extraction as frequency-amplitude, time-amplitude, geometric mean and standard deviation is made with Stockwell Transform (ST), which is one of the methods used for the feature extraction of the determined GKB. Detection of voltage distortions is interpreted through these properties. 640 simulation data is entered into the classifier by using Support Vector Machines (SVM) and Artificial Neural Networks (ANN) and their classification performance is compared.

Anahtar Kelimeler

• Power Quality Disturbance
• Stockwell Transform
• Support Vector Machine
• Artificial Neural Network.

Stockwell Dönüşümü Tabanlı Güç Kalitesi Bozunumlarının Destek Vektör Makinası ve Yapay Sinir Ağları ile Sınıflandırılması

Öz

Elektrik enerjisi hizmetlerinin kesintisiz bir biçimde tüketiciye ulaştırılması büyük önem taşımaktadır. Sistemdeki bozulmaların tespiti ve alınması gereken önlemler bu açıdan önemlidir. Elektrik sinyalindekini bozulmaların türünün belirlenmesi için çeşitli özellik çıkarım yöntemleri kullanılmaktadır. Bu çalışmada, elektrik güç sistemlerinde meydana gelen Güç Kalitesi Bozunumlarından(GKB) gerilim yükselmesi, gerilim çökmesi, harmonikli gerilim, harmonikli gerilim düşmesi, harmonikli gerilim yükselmesi, flicker ve transient ile referans sinyali olarak saf sinüs sinyallerini içeren sekiz işaret toplam on dönem sürecek şekilde TS EN 50160 standartlarına göre MATLAB ortamında oluşturulmuştur. Belirlenen GKB’na ait özellik çıkarımı için kullanılan yöntemlerden biri olan Stockwell-Dönüşümü ile frekans-genlik, zaman-genlik, geometrik ortalama ve standart sapma olmak üzere 4 çeşit özellik çıkarımı yapılmıştır. Bu özellikler üzerinden gerilim bozulmalarının tespiti yorumlanmıştır. Toplam 640 benzetim verisi Destek Vektör Makinaları (DVM) ve Yapay Sinir Ağları(YSA) ile sınıflandırıcıya sokularak sınıflandırma başarımları karşılaştırılmıştır.

Anahtar Kelimeler

• Güç Kalitesi Bozunumları
• Stockwell dönüşümü
• Destek Vektör Makinaları
• Yapay Sinir Ağları.

Kaynakça

1. Agarwal, R. K., Hussain, I., Singh, B., 2017. Application of LMS-based NN structure for power quality enhancement in a distribution network under abnormal conditions. IEEE transactions on neural networks and learning systems, 29(5), pp. 1598-1607.
2. Azam, M. S., Tu, F., Pattipati, K. R., Karanam, R., 2004. A dependency model-based approach for identifying and evaluating power quality problems. IEEE Transactions on power delivery, 19(3), pp. 1154-1166.
3. Chilukuri MV, Dash PK., 2004. Multiresolution S-transform-based fuzzy recognition system for power quality events. IEEE Trans Power Delivery. 19(1), pp. 323-330.
4. Choudhary, B., 2021. An advanced genetic algorithm with improved support vector machine for multi-class classification of real power quality events. Electric Power Systems Research, 191, 106879.
5. Cortes, C., Vapnik, V., 1995. Support-vector networks. Machine learning, 20(3), pp. 273-297.
6. Dharavath, R., Raglend, I. J., Manmohan, A., 2017. Implementation of solar PV—Battery storage with DVR for power quality improvement. In 2017 Innovations in Power and Advanced Computing Technologies (i-PACT), pp. 1-5.
7. Elango, M. K., Loganathan,K., 2016.Classification of power quality disturbances using Stockwell Transform and Back Propagation algorithm. Emerging Technological Trends (ICETT), International Conference on. IEEE.
8. Gaing, Z. L., 2004. Wavelet-based neural network for power disturbance recognition and classification. IEEE transactions on power delivery, 19(4), pp. 1560-1568.

9. Greche, L., Es-Sbai, N., Lavendelis, E., 2017. Histogram of oriented gradient and multi-layer feed forward neural network for facial expression identification. In 2017 International Conference on Control, Automation and Diagnosis (ICCAD), pp. 333-337.
10. Ingale, R., 2014. Harmonic analysis using FFT and STFT. International Journal of Signal Processing, Image Processing and Pattern Recognition, 7(4), pp. 345-362.
11. Karasu, S., Başkan, S., 2016. Classification of power quality disturbances by using ensemble technique. In 2016 24th Signal Processing and Communication Application Conference (SIU), pp. 529-532.
12. Liang, C., Teng, Z., Li, J., Yao, W., Wang, L., He, Q., Hu, S., 2021. Improved S-Transform for Time-Frequency Analysis for Power Quality Disturbances. IEEE Transactions on Power Delivery.
13. Mahela, O. P., Shaik, A. G., 2016. Recognition of power quality disturbances using S-transform and rule-based decision tree. In 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), pp. 1-6.
14. Mishra, A. K., Ray, P. K., Mallick, R. K., Mohanty, A., & Das, S. R., 2021. Adaptive fuzzy controlled hybrid shunt active power filter for power quality enhancement. Neural Computing and Applications, 33(5), pp. 1435-1452.
15. Ozgonenel, O., Yalcin, T., Guney, I., Kurt, U., 2013. A new classification for power quality events in distribution systems. Electric Power Systems Research, 95, pp. 192-199.
16. Poisson, O., Rioual, P., Meunier, M., 2000. Detection and measurement of power quality disturbances using wavelet transform. IEEE transactions on Power Delivery, 15(3), pp. 1039-1044.
17. Raj, S., Phani, T. K., Dalei, J., 2016. Power quality analysis using modified S-transform on ARM processor. In 2016 Sixth International Symposium on Embedded Computing and System Design (ISED) (pp. 166-170). IEEE.
18. Ruder, S., 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747.
19. Saxena, D., Singh, S. N., Verma, K. S., Singh, S. K., 2014. HHT-based classification of composite power quality events. International Journal of Energy Sector Management.
20. Shamachurn, H., 2019. Assessing the performance of a modified S-transform with probabilistic neural network, support vector machine and nearest neighbour classifiers for single and multiple power quality disturbances identification. Neural Computing and Applications, 31(4), pp. 1041-1060. Sindi, H., Nour, M., Rawa, M., Öztürk, Ş., Polat, K., 2021. An adaptive deep learning framework to classify unknown composite power quality event using known single power quality events. Expert Systems with Applications, 178, 115023.
21. Singh, B., Al-Haddad, K., Chandra, A., 1999. A review of active filters for power quality improvement. IEEE transactions on industrial electronics, 46(5), pp. 960-971.
22. Singh, U., Singh, S. N., 2017. Application of fractional Fourier transform for classification of power quality disturbances. IET Science, Measurement & Technology, 11(1), pp. 67-76.
23. Tao, W., Yin, S., Ding, M., Li, C., Yu, N., Bao, X., Guo, J., 2013. Classification of power quality disturbance signals based on S-transform and HHT. In Proceedings of the 32nd Chinese Control Conference, pp. 3639-3644.
24. Thirumala, K., Prasad, M. S., Jain, T., Umarikar, A. C., 2016. Tunable-Q wavelet transform and dual multiclass SVM for online automatic detection of power quality disturbances. IEEE Transactions on Smart Grid, 9(4), pp. 3018-3028.
25. Wang, S., Chen, H., 2019. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network. Applied energy, 235, pp. 1126-1140.
26. Yoo, J. H., Shin, S. K., Park, J. Y., Cho, S. H., 2015. Advanced railway power quality detecting algorithm using a combined TEO and STFT method. Journal of Electrical Engineering and Technology, 10(6), pp. 2442-2447.
27. Zhao, Z., Wang, S., Zhang, W., Xie, Y., 2016. A novel automatic modulation classification method based on Stockwell-transform and energy entropy for underwater acoustic signals. In 2016 IEEE international conference on signal processing, communications and computing (ICSPCC), pp. 1-6.