DocumentCode
2106076
Title
Notice of Retraction
Gaussian Research of Turbine Faults Diagnosis Base on Mixture Models
Author
Chen Xiufeng ; Liang Ping
Author_Institution
Coll. of Electr. Power, South China Univ. of Technol., Guangzhou, China
fYear
2010
fDate
28-31 March 2010
Firstpage
1
Lastpage
5
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
The Gaussian Mixture Models and the wavelet packet analysis is used to the turbine vibration faults diagnosis. Decompounded firstly the vibration faults signal and delete the disturbed component. Then, distill the frequency segment that includes the faults character which seen as the faults characteristic vector. Set up the Gaussian Mixture Models with the vectors, and identify different faults with the built model. It used the experimentation data that measured in Benlty experiment table, to set up the model and identify faults. From the result, when the modulus equal to twelve , the faults diagnosis right rate of the Gaussian Mixture Models equal to approximately 80%~90%. It indicates that the means can acquire a good effect, which uses the Gaussian Mixture Models and the wavelet packet analysis to diagnose the turbine libration fault.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
The Gaussian Mixture Models and the wavelet packet analysis is used to the turbine vibration faults diagnosis. Decompounded firstly the vibration faults signal and delete the disturbed component. Then, distill the frequency segment that includes the faults character which seen as the faults characteristic vector. Set up the Gaussian Mixture Models with the vectors, and identify different faults with the built model. It used the experimentation data that measured in Benlty experiment table, to set up the model and identify faults. From the result, when the modulus equal to twelve , the faults diagnosis right rate of the Gaussian Mixture Models equal to approximately 80%~90%. It indicates that the means can acquire a good effect, which uses the Gaussian Mixture Models and the wavelet packet analysis to diagnose the turbine libration fault.
Keywords
Gaussian processes; acoustic signal processing; fault diagnosis; turbines; turbogenerators; vectors; vibrations; wavelet transforms; Gaussian mixture models; turbine fault diagnosis; turbine libration fault; turbine vibration faults diagnosis; vectors; wavelet packet analysis; Clustering algorithms; Equations; Fault diagnosis; Frequency; Probability; Signal analysis; Stochastic processes; Turbines; Wavelet analysis; Wavelet packets;
fLanguage
English
Publisher
ieee
Conference_Titel
Power and Energy Engineering Conference (APPEEC), 2010 Asia-Pacific
Conference_Location
Chengdu
Print_ISBN
978-1-4244-4812-8
Type
conf
DOI
10.1109/APPEEC.2010.5448942
Filename
5448942
Link To Document