Online fault detection of induction motors using frequency domain independent components analysis

• Main Authors: WANG, Zhaoxia, CHANG, C. S.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2011
• Subjects: Fast Fourier Transform (FFT); Fault detection; Features of the frequency signatures (FS features); Independent Component Analysis (ICA); Induction Motor; Numerical Analysis and Scientific Computing; Operations Research, Systems Engineering and Industrial Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5560; https://ink.library.smu.edu.sg/context/sis_research/article/6563/viewcontent/2011_OnlineFaultDetection_Induction_Motors_av.pdf
• Institution: Singapore Management University

This paper proposes an online fault detection method for induction motors using frequency-domain independent component analysis. Frequency-domain results, which are obtained by applying Fast Fourier Transform (FFT) to measured stator current time-domain waveforms, are analyzed with the aim of extracting frequency signatures of healthy and faulty motors with broken rotor-bar or bearing problem. Independent components analysis (ICA) is applied for such an aim to the FFT results. The obtained independent components as well as the FFT results are then used to obtain the combined fault signatures. The proposed method overcomes problems occurring in many existing FFT-based methods. Results using laboratory-collected data demonstrate the robustness of the proposed method, as well as its immunity against measurement noises and motor parameters.