Research on Intelligent Identification of PD Patterns Based on the Fingerprint Features
- 1 Instrumentation Technology & Economy Institute, Beijing, China
- 2 Harbin University of Science and Technology, Harbin, China
- 3 Harbin University of Science and Technology, Harbin, China
- 4 Harbin University of Science and Technology, Harbin, China
- 5 Harbin University of Science and Technology, Harbin, China
- 6 Harbin University of Science and Technology, Harbin, China
- 7 Harbin University of Science and Technology, Harbin, China
Abstract
Five-electrode configurations were designed to simulate the distribution inhomogeneity of electric field intensities in the air-insulating medium, and the characteristic data waveforms of partial discharge generated by different electrode configurations under the excitation of power frequency AC voltage were carefully collected in this paper. Furthermore, the feature vectors of the corresponding fingerprint, contained in partial discharge data, were extracted by rigorous mathematical algorithms, and the artificial neural network was employed to realize the pattern recognition of partial discharge caused by the inhomogeneity of electric field intensity with different electrode configurations. The results indicate that the J 4 value in the space of 7 feature quantities is 1905.6, and the recognition rate is 100% when the hidden layer neuron of the network is 19. However, the J 5 value of 9 feature quantities is 1589.9, and the purpose of recognition has been achieved when the number of hidden layer neurons of the network is 6. Increasing the number of hidden layer neurons will only waste computing resources. Of course, PD information collection mode, feature quantity selection, optimal feature space composition, network structure and classification algorithm are the key to realizing PD fault intelligence identification.
- Yazici, B. (2004) Statistical Pattern Analysis of Partial Discharge Measurements for Quality Assessment of Insulation Systems in High-Voltage Electrical Machinery. IEEE Transactions on Industry Applications, 40, 1579-1594. https://doi.org/10.1109/TIA.2004.836174
- Fwenando, F.G., Jacinto, T.J., Ruben, J.V., et al. (2017) Analysis of Insulating Material of XLPE Cables Considering Innovative Patterns of Partial Discharges. Mathematical Problems in Engineering, 2017, Article ID: 23794118. https://doi.org/10.1155/2017/2379418
- Zheng, D.C. (2019) Dielectric Characteristics and Application of the SF6(M). Science Press, Beijing.
- Firuzi, K., Vakilian, M. and Phung, B.T. (2019) Partial Discharges Pattern Recognition of Transformer Defect Model by LBP & HOG Features. IEEE Transactions on Power Delivery, 34, 542-550. https://doi.org/10.1109/TPWRD.2018.2872820
- Gao, K. Tan, K.X., Li, F.Q., et al. (2002) PD Pattern Recognition for Stator Bar Models with Six Kinds of Characteristic Vectors Using BP Network. IEEE Transactions on Dielectrics and Electrical Insulation, 9, 381-389. https://doi.org/10.1109/TDEI.2002.1007700
- Wong, J.K.R., Hazlee, A., Ab, H.A., et al. (2015) Partial Discharge Classifications: Review of Recent Progress. Measurement, 68, 164-181. https://doi.org/10.1016/j.measurement.2015.02.032
- Si, W.R., Li, J.H., Yuan, P., et al. (2008) Digital Detection, Grouping and Classification of Partial Discharge Signals at DC Voltage. IEEE Transactions on Dielectrics and Electrical Insulation, 15, 1663-1674. https://doi.org/10.1109/TDEI.2008.4712671
- Callender, G. (2018) Modelling Partial Discharge in Gaseous Voids. University of Southampton, Southampton.
- Lu, C.B. (2002) Dry-Type Power Transformer Theory and Calculation. Liaoning Science and Technology Press (China), Shenyang.
- Yan, Z. and Zhu, D.H. (2007) High Voltage Insulation Technology. China Electric Power Press (China), Beijing.
- Krivda, A. (1995) Automated Recognition of Partial Discharge. IEEE Transactions on Dielectrics and Electrical Insulation, 2, 796-821. https://doi.org/10.1109/94.469976
- Pearson, J.S., Farish, O., Hampton, B.F., et al. (2002) Partial Discharge Diagnostics for Gas Insulated Substations. IEEE Transactions on Dielectrics and Electrical Insulation, 5, 893-905. https://doi.org/10.1109/94.469984
- Zheng, D.C. (2005) PD Pattern Recognition Based on BP Network. Ph.D. Dissertation, Harbin University of Science and Technology, Harbin.