PD pattern recognition based on multi-fractal dimension in GIS

Abstract

This paper designs four types of gas insulated substation (GIS) defect models based on partial discharge (PD) characteristics and its defections. The GIS gray intensity images are constructed based on the mass specimens gathered by the ultra-high frequency and high-speed sampling systems. The multi-fractal dimension is founded on the box-counting dimension and multi-fractal theories. The GIS gray intensity images distillation methods, based on multi-fractal characteristics, is put forward. The box-counting dimension, multi-fractal dimension, and discharge centrobaric characteristics of the PD images are also extracted. The characteristic variables are then classified by the radial basis function (RBF) network. Identified results show that the methods can effectively elevate the discrimination of the four types of defects in GIS.

References

1. Tang Ju Zhu Wei Sun Caixin et al.Study of the uhf shield resonance loop antenna appliedto detect PD in GISChinese Journal of ScientificInstrument 2005 26(7)705709
2. Contin A Montanari G C Ferraro C PD source recognition by weibull processing of pulse heightdistributionIEEE Transaction on Dielectricsand Electrical Insulation 2000 7(1)4858. doi:10.1109/94.839341
3. Gao Kai Tan Kexiong Li Fuqi et al.Pattern recognition of partial discharges basedon fractal features of the scatter setProceedingof the CSEE 2002 22(5)2226
4. Li Jian Sun Caixin Du Lin et al.Study on fractal dimension of PD intensity imageProceedings of the CSEE 2002 22(8)123127
5. Sun Caixin Xu Gaofeng Tang Ju et al.PD pattern recognition method using box dimensionand information dimension as discrimination features in GISProceeding of the CSEE 2005 25(3)100104
6. Dan Wengang Chen Xiangxun Zheng Jianchao Classification of partial discharge distribution usingwavelet transform and neural networkProceedingsof the CSEE 2002 22(9)15
7. Sun Caixin Li Xin Li Jian et al.Research on complementarity between wavelet andfractal theory and relevant application in PD pattern recognitionProceedings of the CSEE 2001 21(12)7376
8. Gao Kai Tan Kexiong Li Fuqi et al.Partial discharge pattern recognition of electricalmachine insulation models using moment featuresTransaction of China Electrotechnical Society 2001 16(4)6164
9. Liu Zhuofu Sang Enfang Sonar image recognition byWavelet Decomposition and fractal dimensionJournal Of Computer Aided Design & Computer Graphics 2004 16(10)13291334
10. Zhang Jizhong FractalTsinghua University Press 1995
11. Sarkar N Chaudhuri B B An efficient approach to estimatefractal dimension of textural imagesPatternRecognition 1992 25(9)10351041. doi:10.1016/0031‐3203(92)90066‐R
12. Chaudhuri B B Sarkar N Texture segmentation throughfractal dimensionIEEE Pattern Analysisand Machine Intelligence 1995 17(1)7277. doi:10.1109/34.368149
13. Tang Ju Shi Haijun Xu Gaofeng et al.Capacitive couplers used for partial discharge inGISIn: Proc 2nd Intern Conf Insul. ConditionMonitoring of Electrical Plants 2003 190194
14. Gao Kai Tan Kexiong Li Fuqi et al.The use of moment features of partial dischargesin generator stator winding modelsIn: Proceedingsof the 6th ICPADMXi'an 2000
15. Yuan Zengren Artifical Nerual Networks and its ApplicationBeijingTsinghua University Press 1999