Identification method for power quality disturbances in distribution network based on transfer learning

• Autorzy: Heping Peng , Wenxiong Mo , Yong Wang , Le Luan , Zhong Xu

Identyfikatory

DOI

10.24425/aee.2022.141682

• Języki publikacji: EN

Abstrakty

EN

For a higher classification accuracy of disturbance signals of power quality, a disturbance classification method for power quality based on gram angle field and multiple transfer learning is proposed in this paper. Firstly, the one-dimensional disturbance signal of power quality is transformed into a Gramian angular field (GAF) coded image by using the gram angle field, and then three ResNet networks are constructed. The disturbance signals with representative signal-to-noise ratios of 0 dB, 20 dB and 40 dB are selected as the input of the sub-model to train the three sub-models, respectively. During this period, the training weights of the sub-models are transferred in turn by using the method of multiple transfer learning. The pre-training weight of the latter model is inherited from the training weight of the previous model, and the weight processing methods of partial freezing and partial fine-tuning are adopted to ensure the optimal training effect of the model. Finally, the features of the three sub-models are fused to train the classifier with a full connection layer, and a disturbance classification model for power quality is obtained. The simulation results show that the method has higher classification accuracy and better anti-noise performance, and the proposed model has good robustness and generalization.

Słowa kluczowe

EN

disturbance identification; distribution network; multiple transfer learning; power quality

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2022
• Tom: Vol. 71, nr 3
• Strony: 731--754
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wz.

Twórcy

autor

Heping Peng

• Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd.Guangdong, Guangzhou 510620, China

autor

Wenxiong Mo

• Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd.Guangdong, Guangzhou 510620, China

autor

Yong Wang

• Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd.Guangdong, Guangzhou 510620, China

autor

Le Luan

• Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd.Guangdong, Guangzhou 510620, China

autor

Zhong Xu

• Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd.Guangdong, Guangzhou 510620, China

Bibliografia

• [1] Huang J.M., Qu H.Z., Li X.M., Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis, Power System Technology, vol. 40, no. 10, pp. 3184–3191 (2016), DOI: 10.13335/j.1000-3673.pst.2016.10.036.
• [2] Yin B.Q., He Y.G., Zhu Y.Q., Detection and classification of power quality multi-disturbances based on generalized S-transform and fuzzy SOM neural network, Proceedings of the CSEE, vol. 35, no. 4, pp. 866–872 (2015), DOI: 10.13334/j.0258-8013.pcsee.2015.04.013.
• [3] Chandrasekarp K., Detection and classification of power quality disturbance waveform using MRA based modified wavelet transform and neural networks, Journal of Electrical Engineering, vol. 61, no. 4, pp. 235–240 (2010), DOI: 10.2478/v10187-010-0033-4.
• [4] Li T.Y., Zhao Y., Li N. et al., A new method for power quality detection based on HHT, Proceedings of the CSEE, vol. 25, no. 17, pp. 52–56 (2005), DOI: 10.13334/j.0258-8013.pcsee.2005.17.011.
• [5] Wei L., Zhang F.S., Geng Z.X. et al., Detection, location and identification of power quality disturbance based on instantaneous reactive power theory, Power System Technology, vol. 28, no. 6, pp. 53–58 (2004), DOI: 10.13335/j.1000-3673.pst.2004.06.012.
• [6] Yongd D., Bhowmiks M., An effective power quality classifier using wavelet transform and support vector machines, Expert Systems with Applications, vol. 15, no. 1, pp. 6075–6081 (2015), DOI: 10.1016/j.eswa.2015.04.002.
• [7] Tan H.F., Liu Z.Y., Multi-label K nearest neighbor algorithm by exploiting label correlation, Journal of Computer Applications, vol. 35, no. 10, pp. 2761–2765 (2015), DOI: 10.11772/j.issn.1001-9081.2015.10.2761.
• [8] Lee I.W.C., Dash P.K., S-transform-based intelligent system for classification of disturbance signals of power quality, IEEE Transactions on Industrial Electronics, vol. 50, no. 4, pp. 800–805 (2003), DOI: 10.1109/TIE.2015.2449780.
• [9] Dehghanih V., Naghiza D. et al., Power quality disturbance classification using a statistical and wavelet-based hidden Markov model with Dempster Shafer algorithm, International Journal of Electrical Power and Energy Systems, vol. 47, no. 5, pp. 368–377 (2013), DOI: 10.1016/j.ijepes.2012.11.005.
• [10] Zhao W.J., Shang L.Q., Sun J.F., Power quality disturbance classification based on time-frequency domain multi-feature and decision tree, Protection and Control of Modern Power Systems, vol. 4,no. 4, pp. 337–342 (2019), DOI: 10.1186/s41601-019-0139-z.
• [11] Yu Z.Y., Zhang W.H., Wang X.K., Huang N.T., Huang X.W., Feature selection method for power quality disturbance identification based on GA and ELM, Electrical measurement and instrumentation, vol. 53, no. 23, pp. 62–66 (2016), DOI: 10.3969/j.issn.1001-1390.2016.23.01.
• [12] Qu H.Z., Liu H., Li X.M., Huang J.M., Power quality composite disturbance classification method based on multi label random forest, Power System Protection and Control, vol. 45, no. 11, pp. 1–7 (2017), DOI: 10.7667/PSPC160899.
• [13] Xing J.P., Research on power quality composite disturbance identification method based on multi feature quantity, Shandong Electric Power Technology, vol. 44, no. 4, pp. 16–21 (2017).
• [14] Qiu X.Y., Li F.L., Power quality disturbance analysis and identification based on ITD and Kmeans clustering, Journal of Power System and Automation, vol. 27, no. 8, pp. 54–59 (2015), DOI: 10.3969/j.issn.1003-8930.2015.08.10.
• [15] Hinton G.E., Osindero S., Yee-Whye T., A Fast Learning Algorithm for Deep Belief Nets, Neural Computation, vol. 18, no. 7, pp. 1527–1554 (2006), DOI: 10.1162/neco.2006.18.7.1527.
• [16] Xiao K., He J.J., Liu C., Chen S.Y., Electronic circuit classification algorithm based on stack self coding network, Computer Application Research, vol. 35, no. 9, pp. 2853–2855 (2018), DOI: 10.3969/j.issn.1001-3695.2018.09.069.
• [17] Fang R., Meng X., Wang C.Q., Zhong Y.D., ECG recognition and classification method based on cyclic neural network, Industrial control computer, vol. 34, no. 7, pp. 122–123 (2021).
• [18] Yang W., Yin K.Y., Bao Y.Y., Yin X.G., Xu B., Power grid fault type identification based on deep confidence network, Power Engineering Technology, vol. 40, no. 2, pp. 169–177 (2021), DOI: 10.12158/j.2096-3203.2021.02.024.
• [19] Wang H., Yang D.S., Zhou B.W., Gao X.T., Pang Y.H., Fault diagnosis of multi terminal DC transmission line based on parallel convolutional neural network, Power System Automation, vol. 44, no. 12, pp. 84–92 (2020), DOI: 10.7500/AEPS20191124003.
• [20] Jiang H., Zheng Y.H., Wang Z.Z., Chen L., Peng J.C., Classification of transient power quality disturbances based on digital image processing technology, Power system protection and control, vol. 43, no. 13, pp. 72–78 (2015), DOI: JournalArticle/5b3bd991c095d70f00940a69.
• [21] Chen W., He J.H., Pei X.P., Classification for power quality disturbance classification based on phase space reconstruction and convolution neural network, Power System Protection and Control, vol. 46, no. 14, pp. 87–93 (2018), DOI: 10.7667/PSPC171080.
• [22] Wang Z., Oates T., Encoding time series as images for visual inspection and classification using tiled convolutional neural networks, Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, Texas, USA, pp. 1–7 (2015).
• [23] Wang Z., Oates T., Imaging time-series to improve classification and imputation, Twenty-Fourth International Joint Conference on Artificial Intelligence, Michael Wooldridge Buenos Aires, Argentina, pp. 3939–3945 (2015).
• [24] Simonyan K., Zisserman A., Very Deep Convolutional Networks for Large-Scale Image Recognition, The 3th International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA, pp. 1–9 (2015), DOI: 10.48550/arXiv.1409.1556.
• [25] Szegedy C., Liu W., Jia Y. et al., Going Deeper with Convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 1–9 (2015), DOI: 10.1109/CVPR.2015.7298594.
• [26] Lecun Y., Bottou L., Bengio Y., Haffner P., Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324 (2019), DOI: 10.1109/jproc.2003.813577.
• [27] Krizhevsky A., Sutskever I., Hinton G., ImageNet Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems, vol. 25, no. 2, pp. 1–9 (2019), DOI: 10.1016/s0898-1221(96)90463-0.
• [28] He K., Zhang X., Ren S. et al., Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770–778 (2016), DOI: 10.1109/CVPR.2016.90.
• [29] Tan C., Sun F., Kong T. et al., A Survey on Deep Transfer Learning, The 27th International Conference on Artificial Neural Networks, Rhodes, Greece, pp. 270–279 (2018), DOI: 10.48550/arXiv.1808.01974.
• [30] Schmidhuber J., Deep learning in neural networks: an overview, Neural Networks, vol. 61, pp. 85–117 (2015), DOI: 10.1016/j.neunet.2014.09.003.
• [31] Ma P., Fan Y.F., Power equipment component detection of small sample intelligent substation based on deep transfer learning, Power Grid Technology, vol. 44, no. 3, pp. 1148–1159 (2020), DOI: 10.13335/j.1000-3673.pst.2018.2793.
• [32] He Q., Zhao J.Y., Jiang G.Q., Jia Ch.L., Xie P., Gearbox fault diagnosis method based on sparse filtering feature fusion of current signal, Power Grid Technology, vol. 44, no. 5, pp. 1964–1971 (2020), DOI: 10.13335/j.1000-3673.pst.2019.1314.
• 33] Lu J.L., Guo L.Y., Power system transient stability assessment based on improved deep residual shrinkage network, Journal of Electrotechnics, vol. 36, no. 11, pp. 2233–2244 (2021), DOI: 10.19595/ j.cnki.1000-6753.tces.200437.
• [34] Wenge C., Guo H., Roehrig C., Measurement-based harmonic current modeling of mobile storage for power quality study in the distribution system, Archives of Electrical Engineering, vol. 66, no. 4, pp. 801–814 (2017), DOI: 10.1515/aee-2017-0061.
• [35] Khoa N.M., Dai L.V., Detection and Classification of Power Quality Disturbances in Power System Using Modified-Combination between the Stockwell Transform and Decision Tree Methods, Energies, vol. 13, no. 14, 3623 (2020), DOI: 10.3390/en13143623.
• [36] Velazquez L.M., Troncoso R.J.R., Ruiz G.H., Sotelo D.M., Rios R.A.O., Smart sensor network for power quality monitoring in electrical installations, Measurement, vol. 103, pp. 133–142 (2017), DOI: 10.1016/j.measurement.2017.02.032.
• [37] Laurens V.D.M., Hinton G., Visualizing Data using t-SNE, Journal of Machine Learning Research, vol. 9, pp. 2579−2605 (2008).
• [38] Hoang D.T., Kang H.J., Convolutional Neural Network Based Bearing Fault Diagnosis, Proceedings of the thirteenth International Conference on Intelligent Computing: Intelligent Computing Theories and Application, Liverpool, UK, pp. 105–111 (2017), DOI: 10.1007/978-3-319-63312-1_9.
• [39] Wu A.D., Zhong J.W., Qin M. et al., Research on Power Quality Disturbance Recognition Based on Convolutional Neural Network, Journal of Hubei Minzu University (Natural Science Edition), vol. 38, no. 3, 318–321 (2020), DOI: 10.13501/j.cnki.42-1908/n.2020.09.015.
• [40] Mohammed Y.S., Mahmood T.A., High impedance fault detection in radial distribution network using discrete wavelet transform technique, Archives of Electrical Engineering, vol. 70, no. 4, pp. 873–886 (2021), DOI: 10.24425/aee.2021.138267.
• [41] Ma J.X., Xu W.N., He F.X. et al., A Novel Power Quality Classification and Identification Method Based on WT and SVM, Smart Power, vol. 47, no. 3, pp. 16–22 + 37 (2019), DOI: CNKI:SUN:XBDJ.0.2019-03-004.
• [42] IEEE Power Engineering Society, IEEE PES working group P1433 Power Quality Definitions (2001).
• [43] IEEE Power Engineering Society, IEEE PES working group P3139 Power Quality Data Analytics (2020)

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).