Articles
A Novel Framework for Classifying Power System Disturbances Using Wavelet Scattering Transform-Derived Feature Matrices
Downloads
Keywords
Power system disturbances
wavelet scattering transform
feature matrix
machine learning
Article Usage Statistics
Live Metrics
Abstract Views
225
File Views
78
PDF
0
HTML
0
Other
78
Total
303
Article Usage Chart
Abstract
File Views
PDF
HTML
Other
Total
Abstract
Accurate classification of power system disturbances is pivotal for the reliability, stability, and operational efficiency of modern electrical grids. Traditional signal processing approaches often struggle with the non-stationary and multi-scale nature of disturbance signals, limiting their diagnostic precision. This research introduces a novel framework leveraging wavelet scattering transform-derived feature matrices for the classification of diverse power system disturbances. By integrating multi-scale convolutional scattering representations with machine learning classifiers, the proposed framework enhances robustness against signal variability, preserves discriminative features, and facilitates accurate disturbance categorization. Experimental validation using benchmark datasets demonstrates significant improvements in classification accuracy compared to conventional methodologies, highlighting the framework’s potential for real-world implementation in power system monitoring and automated fault detection. The results underscore the theoretical and practical advantages of wavelet scattering-based feature extraction for high-dimensional and non-linear signal analysis in complex power systems.
Downloads
Download data is not yet available.
References
1. A. Sami Al-Itbi, A. Bahaaulddin A. Alwahhab, and A. M. Sahan, “X-Ray Covid-19 detection based on scatter wavelet transform and dense deep neural network,” Computer Systems Science and Engineering, vol. 41, no. 3, pp. 1255–1271, 2022, doi: 10.32604/csse.2022.021980.
2. H. A. Agboola and J. E. Zaccheus, “Wavelet image scattering based glaucoma detection,” BMC Biomedical Engineering, vol. 5, no. 1, Mar. 2023, doi: 10.1186/s42490-023-00067-5.
3. J. Andén and S. Mallat, “Deep scattering spectrum,” IEEE Transactions on Signal Processing, vol. 62, no. 16, pp. 4114–4128, Aug. 2014, doi: 10.1109/TSP.2014.2326991.
4. J. Andén and S. Mallat, “Multiscale scattering for audio classification,” International Society for Music Information Retrieval, pp. 657–662, 2011.
5. M. AlBader and H. A. Toliyat, “Wavelet scattering transform based induction motor current signature analysisa,” in 2020 International Conference on Electrical Machines (ICEM), Aug. 2020, pp. 1452–1457, doi: 10.1109/ICEM49940.2020.9270810.
6. T. Bourgana, R. Brijder, T. Ooijevaar, and A. P. Ompusunggu, “Wavelet scattering network based bearing fault detection,” PHM Society European Conference, vol. 6, no. 1, Jun. 2021, doi: 10.36001/phme.2021.v6i1.2875.
7. J. Bruna and S. Mallat, “Classification with scattering operators,” in CVPR 2011, Jun. 2011, pp. 1561–1566, doi: 10.1109/CVPR.2011.5995635.
8. J. Bruna and S. Mallat, “Invariant scattering convolution networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1872–1886, Aug. 2013, doi: 10.1109/TPAMI.2012.230.
9. N. W. Branco, M. S. M. Cavalca, S. F. Stefenon, and V. R. Q. Leithardt, “Wavelet LSTM for fault forecasting in electrical power grids,” Sensors, vol. 22, no. 21, Oct. 2022, doi: 10.3390/s22218323.
10. E. de Aguiar, A. Lazzaretti, B. Mulinari, and D. Pipa, “Scattering transform for classification in non-intrusive load monitoring,” Energies, vol. 14, no. 20, Oct. 2021, doi: 10.3390/en14206796.
11. O. Cortes-Robles, E. Barocio, E. Beltran, and R. D. Rodríguez-Soto, “Events classification in power systems with distributed generation sources using an LSTM-based method with multi-input tensor approach,” Electricity, vol. 4, no. 4, pp. 410–426, Dec. 2023, doi: 10.3390/electricity4040022.
12. W. Ghezaiel, L. Brun, and O. Lezoray, “Wavelet scattering transform and CNN for closed set speaker identification,” in 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), Sep. 2020, pp. 1–6, doi: 10.1109/MMSP48831.2020.9287061.
13. K. Gu, Y. Zhang, X. Liu, H. Li, and M. Ren, “DWT-LSTM-based fault diagnosis of rolling bearings with multi-sensors,” Electronics, vol. 10, no. 17, Aug. 2021, doi: 10.3390/electronics10172076.
14. M. Hirn, S. Mallat, and N. Poilvert, “Wavelet scattering regression of quantum chemical energies,” Multiscale Modeling & Simulation, vol. 15, no. 2, pp. 827–863, Jan. 2017, doi: 10.1137/16M1075454.
15. Y. Jin and Y. Duan, “Wavelet scattering network-based machine learning for ground penetrating radar imaging: application in pipeline identification,” Remote Sensing, vol. 12, no. 21, Nov. 2020, doi: 10.3390/rs12213655.
16. W.-H. Lai, S.-T. Tsai, D.-L. Cheng, and Y.-R. Liang, “Application of wavelet scattering and machine learning on structural health diagnosis for quadcopter,” Applied Sciences, vol. 11, no. 21, Nov. 2021, doi: 10.3390/app112110297.
17. F. Liu et al., “Wearable electrocardiogram quality assessment using wavelet scattering and LSTM,” Frontiers in Physiology, vol. 13, Jun. 2022, doi: 10.3389/fphys.2022.905447.
18. V. Lostanlen, G. Lafay, J. Andén, and M. Lagrange, “Relevance-based quantization of scattering features for unsupervised mining of environmental audio,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2018, no. 1, Dec. 2018, doi: 10.1186/s13636-018-0138-4.
19. L. Sifre, J. Anden, M. Kapoko, E. Oyallon, and V. Lostanlen, “ScatNet: a MATLAB toolbox for scattering networks,” DIENS, 2013.
20. P. K. Shukla and K. Deepa, “Deep learning techniques for transmission line fault classification –a comparative study,” Ain Shams Engineering Journal, vol. 15, no. 2, Feb. 2024, doi: 10.1016/j.asej.2023.102427.
21. A. Sherstinsky, “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network,” Physica D: Nonlinear Phenomena, vol. 404, Mar. 2020, doi: 10.1016/j.physd.2019.132306.
22. B. Soro and C. Lee, “A wavelet scattering feature extraction approach for deep neural network based indoor fingerprinting localization,” Sensors, vol. 19, no. 8, Apr. 2019, doi: 10.3390/s19081790.
23. S. Karan and H.-G. Yeh, “Fault classification in microgrids using deep learning,” in 2020 IEEE Green Energy and Smart Systems Conference (IGESSC), Nov. 2020, pp. 1–7, doi: 10.1109/IGESSC50231.2020.9285101.
24. S. Mallat, “Group invariant scattering,” Communications on Pure and Applied Mathematics, vol. 65, no. 10, pp. 1331–1398, Oct. 2012, doi: 10.1002/cpa.21413.
25. N. Qu, Z. Li, J. Zuo, and J. Chen, “Fault detection on insulated overhead conductors based on DWT-LSTM and partial discharge,” IEEE Access, vol. 8, pp. 87060–87070, 2020, doi: 10.1109/ACCESS.2020.2992790.
26. A. Rohan, “Deep scattering spectrum germaneness to fault detection and diagnosis for component-level prognostics and health management (PHM),” Sensors, vol. 22, no. 23, Nov. 2022, doi: 10.3390/s22239064.
27. V. Veerasamy et al., “LSTM recurrent neural network classifier for high impedance fault detection in solar PV integrated power system,” IEEE Access, vol. 9, pp. 32672–32687, 2021, doi: 10.1109/ACCESS.2021.3060800.
28. A. A. Susu, H. A. Agboola, C. Solebo, F. E. A. Lesi, and D. S. Aribike, “Wavelet time scattering based classification of interictal and preictal EEG signals,” Brain Res, vol. 3, no. 115, 2020.
29. J. Zarka, L. Thiry, T. Angles, and S. Mallat, “Deep network classification by scattering and homotopy dictionary learning,” arXiv preprint arXiv:1910.03561, 2019.
30. “Wavelet scattering,” MathWorks, 2024.