Bearing fault detection via Park´s vector approach based on ANFIS

Author

Saeidi, Majid ; Zarei, Jafar ; Hassani, Hossein ; Zamani, Ali

Author_Institution

Fac. of Eng., Islamic Azad Univ., Dehdasht, Iran

fYear

2014

Firstpage

2436

Lastpage

2441

Abstract

In this paper, Park´s vector transformation and frequency domain analysis for fault detection of induction motors are introduced. Then a smart approach based on Adaptive Nuero Fuzzy Inference System (ANFIS) that uses time domain features obtained from the Park´s transformation of stator currents is proposed for fault detection. By the proposed method, a 1 mm hole on the inner race and two faults including 1 mm and 3 mm hole on the outer race, using experimental data is investigated. It is shown that using features derived from Park´s vector modulus results in better performance compared to the features obtained from a single phase current.

Keywords

fault diagnosis; frequency-domain analysis; fuzzy reasoning; induction motors; machine bearings; mechanical engineering computing; neural nets; stators; time-domain analysis; ANFIS; Park vector approach; Park vector modulus; Park vector transformation; adaptive neuro fuzzy inference system; bearing fault detection; frequency domain analysis; induction motors; inner race; outer race; single phase current; stator currents; time domain features; Fault detection; Fuzzy logic; Harmonic analysis; Resonant frequency; Stators; Training; Vibrations; ANFIS; Bearing; Fault diagnosis; Park´s vector;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Control (ICMC), 2014 International Conference on

Print_ISBN

978-1-4799-2537-7

Type

conf

DOI

10.1109/ICMC.2014.7232006

Filename

7232006