Using improved self-organizing map for partial discharge diagnosis of large turbogenerators

Partial discharge (PD) classification is a powerful way to predict insulation problems of the windings of rotating machinery. While online PD tests have been carried out for over 40 years, effective diagnostic methods are still under development. In this paper, a practical diagnostic method is proposed based on an improved self-organizing map (SOM) with improved clustering indications. Three feature extraction methods are employed for the SOM implementation, including Weibull analysis, statistical operators, and fractal parameters. Experimental PD data of industrial model bars are used to validate the efficiency of using SOM for PD classification. The method is applied to investigate the turbine generator analyzer (TGA) data obtained from a power plant of British Nuclear Fuels Ltd. Diagnostic results are included to demonstrate that the relationship between the new PD measurement and historical data can be visualized and more confidential diagnostic information can be provided, especially when small-size database, new class of data, and doubtful measurements are involved in a practical environment.

[1]  Michael J. Kurtz,et al.  Experience with PDA diagnostic testing on hydraulic generators , 1988 .

[2]  E. Gulski,et al.  Computer-aided measurement of partial discharges in HV equipment , 1993 .

[3]  E. Gulski,et al.  Neural networks as a tool for recognition of partial discharges , 1993 .

[4]  E. Gulski,et al.  Classification of partial discharges , 1993 .

[5]  W. McDermid,et al.  Practical online partial discharge tests for turbine generators and motors , 1994, IEEE Power Engineering Review.

[6]  Anil K. Jain,et al.  A nonlinear projection method based on Kohonen's topology preserving maps , 1992, IEEE Trans. Neural Networks.

[7]  A. Krivda.  Automated recognition of partial discharges , 1995 .

[8]  E. Gulski.  Digital analysis of partial discharges , 1995 .

[9]  Alfredo Contin,et al.  Use of a mixed-Weibull distribution for the identification of PD phenomena [corrected version] , 1995 .

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

[11]  A. T. Johns,et al.  Power system voltage stability assessment using a self-organizing neural network classifier , 1996 .

[12]  E. M. Lalitha,et al.  Fractal image compression for classification of PD sources , 1998 .

[13]  G. C. Stone,et al.  Partial discharge. XXV. Calibration of PD measurements for motor and generator windings-why it can't be done , 1998 .

[14]  Marek Reformat,et al.  Application of genetic algorithms to pattern recognition of defects in GIS , 2000 .

[15]  R. Candela,et al.  PD recognition by means of statistical and fractal parameters and a neural network , 2000 .

[16]  Guangning Wu.  A neural network used for PD pattern recognition in large turbine generators with genetic algorithm , 2000, Conference Record of the 2000 IEEE International Symposium on Electrical Insulation (Cat. No.00CH37075).

[17]  G. Montanari,et al.  PD source recognition by Weibull processing of pulse height distributions , 2000 .

[18]  Gao Kai,et al.  The use of moment features for recognition of partial discharges in generator stator winding models , 2000, Proceedings of the 6th International Conference on Properties and Applications of Dielectric Materials (Cat. No.00CH36347).