Power quality disturbance classification based on time-frequency domain multi-feature and decision tree
Tóm tắt
Accurate classification of power quality disturbance is the premise and basis for improving and governing power quality. A method for power quality disturbance classification based on time-frequency domain multi-feature and decision tree is presented. Wavelet transform and S-transform are used to extract the feature quantity of each power quality disturbance signal, and a decision tree with classification rules is then constructed for classification and recognition based on the extracted feature quantity. The classification rules and decision tree classifier are established by combining the energy spectrum feature quantity extracted by wavelet transform and other seven time-frequency domain feature quantities extracted by S-transform. Simulation results show that the proposed method can effectively identify six types of common single disturbance signals and two mixed disturbance signals, with fast classification speed and adequate noise resistance. Its classification accuracy is also higher than those of support vector machine (SVM) and k-nearest neighbor (KNN) algorithms. Compared with the method that only uses S-transform, the proposed feature extraction method has more abundant features and higher classification accuracy for power quality disturbance.
Tài liệu tham khảo
Xiao, X.N. (2010). Analysis and control of power quality [M]. Beijing: China Electric Power Press, 124–128.
Zhang, Y., & Liu., Z.G. (2012). A new power quality hybrid disturbance classification method based on time-frequency domain multi-characteristic quantities [J]. Proceedings of the CSEE, 32(34), 83–90.
Zhang, B. (2010). Power quality analysis method based on Mallat algorithm and fast Fourier transform [C]. Power Quality Seminar, 35–40.
Jurado, F., & Saenz, J. R. (2002). Comparison between discrete STFT and wavelets for the analysis of power quality events[J]. Electr Power Syst Res, 62(3), 183–190.
Huang, J.M, Qu, H.Z, & Li, X.M. (2016). Classification of mixed disturbance of power quality based on short-time Fourier transform and spectral kurdiness [J]. Power System Technology, 40(10), 3184–3191.
Qu, H.Z, Liu, H., Li, X.M, et al. (2017). A feature combination optimization method for multi-disturbance classification of power quality [J]. Electric Powcr Automation Equipment, 37(3), 146–152.
Luciano C.M. Andrade, Mário Oleskovicz, & Ricardo A.S. Fernandes. (2016). Adaptive threshold based on wavelet transform applied to the segmentation of single and combined power quality disturbances[J]. Neurocomputing, 38, 967–977.
Wu, Y., Tang, Q., Teng Z.S, et al. (2016). Power quality disturbance signal feature extraction method based on improved S transform [J]. Proceedings of the CSEE, 36(10), 2682–2689.
Huang, N.T, Peng, H., Cai, G.W, et al. (2017). Composite disturbance feature selection and optimal decision tree construction of power quality [J]. Proceedings of the CSEE, 37(3), 776–786.
LI, X.N. (2017). Power quality disturbance detection and recognition based on hilbert-huang transformation [D], China University of Mining and Technology.
Anamika Yadav, Yajnaseni Dash & V. Ashok. (2016). ANN based directional relaying scheme for protection of Korba-Bhilai transmission line of Chhattisgarh state[J]. Protection and Control of Modern Power Systems, 1(1), 15.
He, J.L, Wang, G.P, Liu, D., et al. (2017). Location and identification of power quality disturbance in distribution network system based on lifting wavelet and improving BP neural network [J]. Power System Protection and Control, 45(10), 69–76.
Ren, Z.H, & Wang, Q. (2008). Power quality disturbance identification based on optimal DDAGSVM multi-class classification strategy [J]. Power System Protection and Control, 46(5), 82–88.
Panigrahi B.K., Pandi V.R. optimal feature selection for classification of power quality disturbances using wavelet packet-based fuzzy k-nearest neighbour algorithm[J]. Neurocomputing, 2009, 3(3): 296–306.
Biswal, M., & Dash, P.K. (2013). Measurement and classification of simultaneous power signal patterns with an S-transform variant and fuzzy decision tree[J]. IEEE Transactions on Industrial Informatics, 9(4), 1819–1827.
Zhou, Z.N. (2017). Research on power quality disturbance identification algorithm based on S transform [D]. Harbin Institute of Technology.
Han, G., Zhao, J.W, Zhu, X., et al. (2015). Power quality disturbance identification based on multi-feature combination [J]. Proceedings of the CSU-EPSA, 27(8), 71–77.