RBFNN for fault diagnosis of rotor windings inter-turn short circuit in turbine-Generator

Author

Yan-jun, Zhao ; Yong-gang, Li ; Ji-wei, Hu

Author_Institution

Sch. of Electr. Eng., North China Electr. Power Univ., Baoding

fYear

2008

fDate

21-24 April 2008

Firstpage

1331

Lastpage

1334

Abstract

The electromagnetic characteristic and rotor vibration characteristic of turbine-generator are analyzed when rotor windings inter-turn short circuit fault has happened. This paper also gets relevant characteristic parameters. Based on characteristic parameters, RBFNN (radial basis function neural network) can be adequately trained and diagnosis rotor windings inter-turn short circuit. RBFNN is independent on mathematic models and parameters of turbine-generator. Finally practically acquired dynamic experiment data of the MJF-30-6 generator, the results of verification show that the theory analysis is right and the RBFNN can diagnosis rotor fault and estimate fault turns ratio.

Keywords

fault diagnosis; mathematical analysis; power engineering computing; radial basis function networks; rotors; turbogenerators; MJF-30-6 generator; RBFNN; electromagnetic characteristics; fault diagnosis; fault estimation; mathematic models; radial basis function neural network; rotor vibration characteristic; rotor windings inter-turn short circuit; turbine-generator; Circuits; Condition monitoring; Corona; Electrodes; Fault diagnosis; Partial discharges; Power cables; Principal component analysis; Substations; Testing; RBFNN; Turbine-Generator; fault diagnosis; rotor windings inter-turn short circuit fault; vibration;

fLanguage

English

Publisher

ieee

Conference_Titel

Condition Monitoring and Diagnosis, 2008. CMD 2008. International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-1621-9

Electronic_ISBN

978-1-4244-1622-6

Type

conf

DOI

10.1109/CMD.2008.4580222

Filename

4580222