Study of GIS PD Defect Classification Based on Adaptive Affinity Propagation Clustering

Abstract:

In order to classify and identify different types of defects in GISs, this paper introduces a novel adaptive affinity propagation clustering (adAP) algorithm, which is used for classification of UHF signals of four kinds of typical defects. The algorithm has overcome the conventional affinity propagation (AP) algorithms defects, namely inability to acquire cluster number accurately and inability to cease oscillations, by technologies of adaptively scanning preference space to search for the number of clusters to find the optimal clustering results, adaptively adjusting the damping factor to eliminate oscillation and adaptively escaping oscillations. Finally, validity verification is performed over classification results using a variety of validity indexes. It is discovered that adAP algorithm can accurately tell the number of classes and realize classification of different types of defects. It is also superior to conventional AP algorithm in regards of the processing time and the number of loops.

• Periodical: Applied Mechanics and Materials (Volumes 448-453)
• Pages: 1963-1970
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.448-453.1963
• Online since: October 2013
• Authors: Da Peng Duan, Wei Qiang Qi, Hong Jing Liu, Xu Cheng, Yan Ran Li, Xiao Xin Chen, Hai Feng Ye
• Keywords: Adaptive Affinity Propagation Clustering, Adaptive Damping, Adaptive Escape, Adaptive Scanning, Clustering Validity Analysis, GIS, Partial Discharge (PD)

References

[1] RONG Lin, ZHENG Wen-dong, QIAN Yong, et al. Study of Ultrasonic Diagnosis Method for Partial Discharge in GIS Based on Signal Envelope Spectrum[J]. High Voltage Apparatus, 2011, 47(12): 39-43, 48.

[2] QIAN Yong, HUANG Cheng-jun, JIANG Xiu-chen, et al. Current Status and Development of PD Online Monitoring Technology in GIS[J]. Hign Voltage Apparatus, 2004, 40(6): 453-456.

[3] XIAO Yan, YU Wei-yong. Present status and prospect of research of online partial discharge monitoring system in GIS[J]. High Voltage Engineering, 2005, 31(1): 47-49.

[4] GUO Can-xin, ZHANG Li, QIAN Yong, et al. Current Status of Partial Discharge Detection and Location Techniques in XLPE Power Cable[J]. High Voltage Apparatus, 2009, 45(3): 56-60.

[5] LI Li-xue, HUANG Cheng-jun, ZENG Yi, et al. Noise Reduction Using Wavelet for Envelope Signal of Partial Discharge in GIS[J]. High Voltage Apparatus, 2009, 45(1): 33-35.

[6] Liu Junhua, Yao Ming, Huang Chengjun, et al. Experimental research on partial discharge localization in GIS using ultrasonic associated with electromagnetic wave method[J]. High Voltage Engineering, 2009, 33(10): 2458-2463.

[7] J.C. Bezdek. Pattern recognition with fuzzy objective function algorithms[M]. New York, 1981, Plenum Press.

[8] Wang Kaijun, Li Jian, Zhang Junying, et al. Semi-supervised affinity propagation clustering[J]. Computer Engineering, 2007, 33(23): 197-201.

[9] Wang Kaijun, Zhang Junying, Li Dan, et al. Adaptive affinity propagation clustering[J]. ACTA AUTOMATICA SINICA, 2007, 33(12): 1242-1246.

[10] Qian Yong, HUANG Chengjun, Chen Chen, et al. Analysis of the partial discharge in generator based on sk-ku plot[J]. Hign Voltage Apparatus, 2007, 43(3): 176-178, 182.

[11] Hu Wentang, Gao Shengyou, Yu Shaofeng, et al. Application of statistic parameters in recognition of partial discharge in transformers[J]. High Voltage Engineering, 2009, 35(2): 277-281.

[12] Gulski, E., Kreuger, F.H. Computer-aided recognition of discharge sources[J]. IEEE Transactions on Electrical Insulation, 1992, 27(1): 82-92.

DOI: 10.1109/14.123443

[13] B.J. Frey, D. Dueck. Clustering by passing messages between data points[J]. Science, 2007, 315(5814): 972-976.

DOI: 10.1126/science.1136800

[14] D.M. Tang, Q.X. Zhu, F. Yang. A Poisson-based adaptive affinity propagation clustering for SAGE data[J]. Computational Biology and Chemistry, 2010, 34(1): 63-70.

DOI: 10.1016/j.compbiolchem.2009.11.001

[15] S. Dudoit, J. Fridlyand. A prediction-based resampling method for estimating the number of clusters in a dataset[J]. Genome Biology, 2002, 3(7): 1-21.

[16] L. Kaufman, P. Rousseeuw. Finding groups in data: an introduction to clustering analysis[M]. New York, Wiley, (1990).

[17] E. Fowlkes, C. Mallows. A method for comparing two hierarchical clusterings[J]. Journal of American Statistical Society, 1983, 78(383): 553-569.

DOI: 10.1080/01621459.1983.10478008

[18] G.X. Chen, S.A. Jaradat, N. Banerjee. Evaluation and comparison of clustering algorithms in analyzing ES cell gene expression data[J]. Statistica Sinica, 2002, 12: 241-262.

[19] D.L. Davies, D.W. Bouldin. A cluster separation measure[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1979, 1(4): 224-227.

DOI: 10.1109/tpami.1979.4766909

[20] T. Calinski, J. Harabasz. A dendrite method for clustering analysis[J]. Communications in Statistics - Theory and Methods, 1974, 3(1): 1-27.

DOI: 10.1080/03610927408827101