z-logo
open-access-imgOpen Access
Application of oscillatory time frequency manifold for extraction of rolling element bearing fault signature
Author(s) -
Lei Li,
Khandaker Noman,
Yongbo Li,
Fang Hao,
Zichen Deng
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2252/1/012039
Subject(s) - time–frequency analysis , short time fourier transform , signature (topology) , bearing (navigation) , fault (geology) , feature extraction , fourier transform , constant q transform , rolling element bearing , manifold (fluid mechanics) , noise (video) , pattern recognition (psychology) , oscillation (cell signaling) , fault detection and isolation , signal (programming language) , computer science , algorithm , artificial intelligence , vibration , acoustics , engineering , mathematics , physics , fourier analysis , mathematical analysis , computer vision , filter (signal processing) , actuator , image (mathematics) , genetics , biology , geometry , programming language , mechanical engineering , seismology , geology
To overcome the problem that traditional feature extraction algorithms are sensitive to noise, a bearing fault signature extraction scheme is proposed in this paper with the help of oscillation-based signal decomposition and time frequency manifold (TFM) learning. Firstly, an oscillation-based signal component separation method based on tunable Q factor wavelet transform (TQWT) is utilized to separate the low oscillatory component from vibration signals. Then, concept of TFM is utilized on the separated low oscillatory component to generate the low oscillatory time frequency manifold signature. The proposed method is termed as oscillatory time frequency manifold (OTFM). Compared to that of traditional short time Fourier transform (STFT) and original TFM algorithm, results of experiment show that the proposed algorithm has better time frequency characterization ability for bearing fault signature.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here