This paper focuses on bearing fault detection in induction machines based on stator currents analysis. The method for extracting and identifying bearing fault information of induction motor based on multitaper spectrum combined with support vector machine is proposed in this paper. This approach relies on two steps: the stator current of motor is preprocessed based on multitaper spectrum analysis in order to extract the fault information of motor bearing. Afterward, the support vector machine is employed. Five parameters including kurtosis, skewness, crest factor, clearance, and shape factor are extracted from the spectrum analysis and formed the support vector machine feature vector. By means of optimizing experimental parameters of the kernel function, the bearing fault is identified. The proposed method is used for bearing fault detection in induction motor under the condition of the bearing outer raceway damage. Experimental results show that the proposed method has relatively simple calculation complexity and better performance in identifying bearing fault of motor effectively.
Fault Diagnosis of Induction Motor Bearing Based on Multitaper Spectrum and Support Vector Machine
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2019 ; Qingdao, China October 25, 2019 - October 27, 2019
Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019 ; Kapitel : 20 ; 199-207
2020-04-08
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Condition Monitoring and Fault Diagnosis of Induction Motor Using Support Vector Machine
Online Contents | 2016
|Machine Learning based Early Fault Diagnosis of Induction Motor for Electric Vehicle Application
BASE | 2018
|