DocumentCode :
1819280
Title :
Genetic programming for partial discharge feature construction in large generator diagnosis
Author :
Ruihua, Li ; Hengkun, Xie ; Naikui, Gao ; Weixiang, Shi
Author_Institution :
State Key Lab. of Electr. Insulation for Power Equip., Xi´´an Jiaotong Univ., China
Volume :
1
fYear :
2003
fDate :
1-5 June 2003
Firstpage :
258
Abstract :
In this paper, the standpoint of feature construction is employed into partial discharge defects identification of large generators by another emerging simulated evolution technique- genetic programming (GP). Genetic programming can discover relationships among observed data and express them mathematically. The architecture of partial discharge feature construction is proposed. GP is applied to extract and construct effective features from raw dataset. In addition, in order to eliminate the bottleneck of insufficient sample size, a kind of statistical resampling technique called bootstrap is incorporated as a preprocessing step into genetic programming. The experimental results show the good ability in partial discharge defects identification.
Keywords :
electric generators; machine insulation; partial discharges; generator diagnosis; genetic programming; partial discharge defects; partial discharge feature construction; Artificial neural networks; Data mining; Dielectrics and electrical insulation; Feature extraction; Genetic programming; Genomics; Partial discharges; Pattern recognition; Stator windings; Thermal stresses;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Properties and Applications of Dielectric Materials, 2003. Proceedings of the 7th International Conference on
ISSN :
1081-7735
Print_ISBN :
0-7803-7725-7
Type :
conf
DOI :
10.1109/ICPADM.2003.1218401
Filename :
1218401
Link To Document :
بازگشت