Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Residual current fault type recognition based on S3VM and KNN cooperative training

  • Zhang, Xiangke (Department of Electrical and Electronic Engineering, Shandong University of Technology) ;
  • Wang, Yajing (Department of Electrical and Electronic Engineering, Shandong University of Technology) ;
  • Dou, Zhenhai (Department of Electrical and Electronic Engineering, Shandong University of Technology) ;
  • Wang, Wei (Department of Electrical and Electronic Engineering, Shandong University of Technology) ;
  • Bai, Yunpeng (Department of Electrical and Electronic Engineering, Shandong University of Technology)
  • Received : 2022.04.16
  • Accepted : 2022.06.30
  • Published : 2022.11.20
⟨ Previous Next ⟩

Abstract

It is difficult to detect the residual current of specific fault types in low-voltage distribution networks, which results in few labeled residual current samples. Thus, it is difficult to recognize the fault types of residual current. To solve this problem, a cooperative training classification model based on an improved squirrel search algorithm (ISSA) for a semi-supervised support vector machine (S3VM) and the k-nearest neighbor (KNN) is proposed (ISSA-S3VM-KNN). First, the residual current is decomposed into k intrinsic mode functions (IMFs) by variational mode decomposition (VMD), and the characteristic parameters of the IMFs are extracted to obtain a characteristic dataset for establishing a classification model. Second, to solve the problem where it is difficult to the select parameters (such as the penalty factors, slack variables and kernel function) of a S3VM, an ISSA parameter optimization method is proposed to self-adaptively select the optimal combination of parameters for the S3VM. Finally, the KNN is used to verify the classification results of an ISSA-S3VM through cooperative training, which further improves the classification accuracy of the S3VM for unlabeled residual current samples. Classification results of measured and simulation data show that the classification accuracy of the ISSA-S3VM-KNN is higher than that of the SVM-BPNN, WE-AE-BPNN, and PSO-SVM. The ISSA-S3VM-KNN provides a certain theoretical basis for achieving fast and accurate residual current fault type recognition.

Keywords

Acknowledgement

The authors wish to acknowledge Shandong Kehui Electric Co., Ltd. for providing the experimental space and experimental equipment contribution in Zibo, Shandong, China. The Project Supported by the Natural Science Foundation of Shandong Province (ZR2020MF124) and the Zibo City Integration Development (2019ZBXC011 and 2019ZBXC498).

References

  1. Li, K., Lin, J.-Y., Niu, F., Wang, Y.: A novel fault leakage current detection method with protection deadzone elimination. IEEE Trans. Instrum. Meas. 70, 1-9 (2021). https://doi.org/10.1109/TIM.2020.3035257
  2. Shopov, Y., Petrakieva, S. Filipova., Boychev, B.: Investigation of residual current devices in high frequencies. In: 10th Electrical Engineering Faculty Conference, pp. 1-3 (2018). Doi: https://doi.org/10.1109/BULEF. 2018.8646945
  3. Wu, S., Lin, S.-Y., Guo, M.-F.: Application of WE-AE-BP method to electric shock faults identification in the low-voltage distribution network. In: 2020 IEEE 1st China International Youth Conference on Electrical Engineering (CIYCEE). Pp. 1-6 (2020). https://doi.org/10.1109/ciycee49808.2020.9332673
  4. Han, X.-H., Du, H.-S., Su, J., Liu, G.-G.: Fault transient feature extraction and fault type identification for electrical shock signals. Power Syst. Technol. 40(11), 3591-3596 (2016). https://doi.org/10.13335/j.1000-3673.pst.2016.11.046
  5. Liu, Y.-Y., Du, H.-S., Sheng, W.-X.: Prediction method of electric shock current based on SVM and neural network fusion feedback. Power Syst.m Technol. 44(05), 1972-1977 (2020). https://doi.org/10.13335/j.1000-3673.pst.2018.2977
  6. Fu, Y., Wang, X., Zhou, D.-Q., Fan, X.-Y., Zhou, Y.-P.: Recognition method of radar signal based on SVD of ambiguity function and improved S3VM algorithm. Comput. Eng. Appl. 53(06), 264-270 (2017). https://doi.org/10.3778/j.issn.1002-8331.1608-0192
  7. Wei, L.-F., Feng, X.-Q., Li, D.-D.: Classification of hyperspectral remote sensing image based on S3VM model. Bull. Surv. Mapp. 12, 43-47 (2017). https://doi.org/10.13474/j.cnki.11-2246.2017.0376
  8. Wang, A.-N., Li, Y.-L., Zhao, F.-Y.: Novel semi-supervised classification algorithm based on TSVM. Chin. J. Sci. Instrum. 32(07), 1546-1550 (2011). https://doi.org/10.19650/j.cnki.cjsi.2011.07.016
  9. Xie, J.-L., Yao, T.-Q.: Quantified assessment of internal shortcircuit state for 18650 batteries using an extreme learning machine based pseudo-distributed model. IEEE Trans. Transport. Electr. 7(3), 1303-1313 (2021). https://doi.org/10.1109/TTE.2021.3052579
  10. Chen, L., Li, M., Su, W., Wu, M., Hirota, K., Pedrycz, W.: Adaptive feature selection-based adaboost-KNN with direct optimization for dynamic emotion recognition in human-robot interaction. IEEE Trans. Emerg. Top. Comput. Intell. 5(2), 205-213 (2021). https://doi.org/10.1109/TETCI.2019.2909930
  11. Montague, P., Kim, J.: An efficient semi-supervised SVM for anomaly detection. 2017 International Joint Conference on Neural Networks. 2843-2850 (2017). https://doi.org/10.1109/IJCNN.2017.7966207
  12. Chen, S.-Y., Wang, G.-P., Dong, S.-H.: A progressive transductive inference algorithm based on support vector machine. J. Softw. 14(3), 451-459 (2003). https://doi.org/10.1177/009524403031094
  13. Li, X.-Y., Meng, H.-F., Peng, X.-L.: Semi-supervised learning for fault identification in electricity distribution networks. Twelfth International Conference on Signal Processing Systems. 33, (2021). https://doi.org/10.1117/12.2589229
  14. Drucker, H., Wu, D.-H., Vapnik, V.N.: Support vector machines for spam categorization. IEEE Trans. Neural Netw. 10(5), 1048-1054 (1999). https://doi.org/10.1109/72.788645
  15. Scholkopf, B., Sung, K.-K., Burges, C.-J.-C., et al.: Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Trans. Signal Process. 45(11), 2758-2765 (1997). https://doi.org/10.1109/78.650102
  16. Vapnik, V.: An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988-999 (1999). https://doi.org/10.1109/72.788640
  17. Jain, M., Singh, V., Rani, A.: A novel nature-inspired algorithm for optimization: squirrel search algorithm. Swarm Evol. Comput. 44, 148-175 (2018). https://doi.org/10.1016/j. swevo. 2018. 02. 013
  18. Li, L., Wang, G.-W., Zhang, J.: Coupled simulated annealing semi-supervised SVM for credit prediction. Comput. Eng. Des. 42(01), 196-205 (2021). https://doi.org/10.16208/j.issn1000-7024.2021.01.029
  19. Chen, Y.-H., Pan, T.-H., Chen, S.: Development of co-training support vector machine model for semi-supervised classification. In: 2017 36th Chinese Control Conference (CCC). 11077-11080, (2017). https://doi.org/10.23919/ChiCC.2017.8029125
  20. Fabian, G., Antti, A., Tapio, P.: Fast and Simple gradient-based optimization for semi-supervised support vector machines. Neurocomputing 123, 23-32 (2014). https://doi.org/10.1016/j.neucom.2012.12.056
  21. Zhang, S., Li, X., Zong, M., Zhu, X., Wang, R.: Efficient KNN classification with different numbers of nearest neighbors. IEEE Trans. Neural Netw. Learn. Syst. 29(5), 1774-1785 (2018). https://doi.org/10.1109/TNNNS.2017.2673241
  22. Li, C.-L., Lou, J., Wang, C.-Y.: Electric shock recognition method based on cyclic spectrum features and cluster analysis. Trans. China Electrotech. Soc. 32(22), 4677-4687 (2022). https://doi.org/10.19595/j.cnki.1000-6753.tces.201468
  23. Zhang, W.-C., Shi, P.-X., Liu, W.: Research on deformation prediction of diaphragm wall based on improved knn and parameters of subway deep excavation. J. Huazhong Univ. Sci.Technol. 49(09), 101-106 (2021). https://doi.org/10.13245/j. hust. 210918
  24. Dragomiretskiy, K., Zosso, D.: Variational mode decomposition. IEEE Trans. Signal Process. 62(3), 531-544 (2014). https://doi.org/10.1109/TSP.2013.2288675
  25. Huang, N.-E., Zheng, S., Steven, R.: The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. A. 454, 903-995 (1998). https://doi.org/10.1098/rspa.1998.0193
  26. Lei, Y.-G., He, Z.-J., Zi, Y.-Y.: Fault diagnosis based on novel hybrid intelligent model. J. Mech. Eng. 07, 112-117 (2008). https://doi.org/10.3901/JME.2008.07.112
  27. Cao, L., Chua, K., Chong, W.: A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine. Neurocomputing 55(1), 321-336 (2003). https://doi.org/10.1016/S0925-2312(03)00433-8
  28. Tang, Y.-B., Gui, W.-H., Peng, T.: Transformer fault diagnosis model based on PCA and KICA feature extraction. High Volt. Eng. 55(1), 321-336 (2014). https://doi.org/10.13336/j.1003-6520.hve.2014.02.031