Rotor faults diagnosis in synchronous generators using feature selection and nearest neighbors rule
Authors:
- 1 September 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 300-306
Abstract
Feature selection and nearest neighbors rule technique is used to diagnose large-generator rotor faults. Thus, a specific experimental setup has been designed to perform the methodology of rotor faults detection. This experimental setup is a small scale prototype of a nuclear plant turbo-generator, which is actually DC excited synchronous machine. In this generator, electrical (turn-to-turn failures) and mechanical faults (eccentricities) can be carried out. Sixteen functional states have been performed for five operating points. Stator current, voltage and flux density in the air-gap have been recorded. A list of features is then extracted from these records. To reduce their number, the SBS algorithm is used and the classification is performed by using the k-NN rule. As a result, the classification accuracy is 77.4% and the rotor faults accuracy reaches 85.1% which prove the efficiency of the method.Keywords
This publication has 8 references indexed in Scilit:
- Induction motor fault diagnosis based on thek-NN and optimal feature selectionInternational Journal of Electronics, 2010
- FDI based on pattern recognition using Kalman prediction: Application to an induction machineEngineering Applications of Artificial Intelligence, 2008
- An innovative inductive air-gap monitoring for large low speed hydro-generators2008
- Methods for diagnosing static eccentricity in a synchronous 2 pole generator2007
- The use of features selection and nearest neighbors rule for faults diagnostic in induction motorsEngineering Applications of Artificial Intelligence, 2006
- Analysis of shaft voltages in large synchronous generators2003
- Circulating current analysis in the parallel-connected windings of synchronous generators under abnormal operating conditions2003
- Comparison of algorithms that select features for pattern classifiersPattern Recognition, 2000