Extraction of induction motor fault characteristics in frequency domain and fuzzy entropy

Author

Lee, Sang-Hyuk ; Kim, Sungshin ; Kim, Jang Mok ; Choi, Changho ; Kim, Jaesig ; Lee, Sanghoon ; Oh, Yongmin

Author_Institution

Sch. of Electr. Eng., Pusan Nat. Univ., Busan

fYear

2005

fDate

15-15 May 2005

Firstpage

35

Lastpage

40

Abstract

Feature extraction for fault detection of an induction motor is carried out using the information of stator current. After preprocessing actual data, Fourier and wavelet transforms are applied to detect characteristics under the healthy and various faulted conditions. The most reliable phase current among 3-phase currents is selected by the fuzzy entropy. The fuzzy membership function is also required to obtain the fuzzy entropy. The membership function is designed by the bootstrap method and central limit theorem. PCA (principal component analysis) and LDA (linear discriminant analysis) is finally applied to obtain characteristics of the healthy and faulted motors

Keywords

Fourier transforms; entropy; fault diagnosis; frequency-domain analysis; induction motors; principal component analysis; wavelet transforms; 3-phase currents; Fourier transforms; PCA; bootstrap method; central limit theorem; fault detection; fault extraction; feature extraction; frequency domain; fuzzy entropy; fuzzy membership function; induction motor fault; linear discriminant analysis; principal component analysis; stator current; wavelet transforms; Data mining; Entropy; Fault detection; Feature extraction; Fourier transforms; Frequency domain analysis; Induction motors; Linear discriminant analysis; Principal component analysis; Stators;

fLanguage

English

Publisher

ieee

Conference_Titel

Electric Machines and Drives, 2005 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-8987-5

Electronic_ISBN

0-7803-8988-3

Type

conf

DOI

10.1109/IEMDC.2005.195698

Filename

1531316