GIS partial discharge pattern recognition based on the chaos theory

Partial discharge (PD) is a key parameter which describes insulation condition of gas-insulated switchgear GIS, GIS internal defects can be discovered in time with the interferences such as corona discharge from the power system using Ultra-high frequency (UHF) method. Traditional method based on statistical characteristics is limited to the analysis of image features that describe the PD pattern plot, causing low recognition rate of some kinds of PD. In this paper, the acquisition of the PD characteristics caused by four typical insulation defects forms φ-v-n 3D PRPD pattern plots sample matrix. The largest Lyapunov exponent of each column of matrix is calculated. A 36-dimension vector is then obtained as the chaotic characteristics of the PD in different voltage phases. The experimental results show that the recognition method based on the chaotic characteristics performs well on all four kinds of insulation defects and can satisfy the recognition order. The method based on the chaotic characteristics has a strong recognition ability for the discharge physical models of gas gap, which is an advantage over the traditional method. The two recognition methods have a good complementary property. Combining the complementary chaotic and statistical characteristics in a decision-making level by using the Dempster-Shafer evidence theory results in an accuracy of above 98%.

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[2]  Ja-Yoon Koo,et al.  Chaotic analysis of partial discharge (CAPD) as a novel approach to investigate insulation degradation caused by the various defects , 2001, ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No.01TH8570).

[3]  J. Yorke,et al.  Final state sensitivity: An obstruction to predictability , 1983 .

[4]  Gian Carlo Montanari,et al.  A new approach to the diagnosis of solid insulation systems based on PD signal inference , 2003 .

[5]  L. Hao,et al.  Partial discharge source discrimination using a support vector machine , 2010, IEEE Transactions on Dielectrics and Electrical Insulation.

[6]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[7]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[8]  Kimura Takashi,et al.  Diagnostic Methods for GIS Insulating Systems Using External Antenna , 1995 .

[9]  Caixin Sun,et al.  Kernel statistical uncorrelated optimum discriminant vectors algorithm for GIS PD recognition , 2009 .

[10]  Xiaoxing Zhang,et al.  Kernel statistical uncorrelated optimum discriminant vectors algorithm for GIS PD recognition , 2009, IEEE Transactions on Dielectrics and Electrical Insulation.

[11]  B. F. Hampton,et al.  The excitation of UHF signals by partial discharges in GIS , 1996 .

[12]  D. L. Hall,et al.  Mathematical Techniques in Multisensor Data Fusion , 1992 .

[13]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and an Introduction to Chaos , 2003 .

[14]  E. Gulski.  Discharge pattern recognition in high voltage equipment , 1995 .

[15]  G. Wahba.  Support vector machines, reproducing kernel Hilbert spaces, and randomized GACV , 1999 .

[16]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[17]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  L. Satish,et al.  Can fractal features be used for recognizing 3-d partial discharge patterns , 1995 .

[20]  Ja-Yoon Koo,et al.  Chaotic analysis of partial discharge (CAPD)-a novel approach to identify the nature of PD source , 2001, 2001 Annual Report Conference on Electrical Insulation and Dielectric Phenomena (Cat. No.01CH37225).

[21]  Xiaoxing Zhang,et al.  Partial discharge pattern recognition based on optimal uncorrelated discriminant vectors in GIS , 2009 .

[22]  B. F. Hampton,et al.  A continuous UHF monitor for gas-insulated substations , 1991 .

[23]  Susanto Rahardja,et al.  Object Recognition by Discriminative Combinations of Line Segments, Ellipses, and Appearance Features , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.