File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TNNLS.2023.3274290
- Scopus: eid_2-s2.0-85161082788
- WOS: WOS:001005882100001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: PeriodNet: Noise-Robust Fault Diagnosis Method under Varying Speed Conditions
Title | PeriodNet: Noise-Robust Fault Diagnosis Method under Varying Speed Conditions |
---|---|
Authors | |
Keywords | Bearing fault diagnosis complex operating conditions Convolution deep learning (DL) Fault diagnosis Feature extraction Kernel Noise measurement noise resist correlation periodic convolutional module (PeriodConv) Signal to noise ratio Vibrations |
Issue Date | 22-May-2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Citation | IEEE Transactions on Neural Networks and Learning Systems, 2023, p. 1-15 How to Cite? |
Abstract | Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments. |
Persistent Identifier | http://hdl.handle.net/10722/340000 |
ISSN | 2022 Impact Factor: 10.4 2020 SCImago Journal Rankings: 2.882 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, R | - |
dc.contributor.author | Wu, J | - |
dc.contributor.author | Li, Y | - |
dc.contributor.author | Cheng, Y | - |
dc.date.accessioned | 2024-03-11T10:40:55Z | - |
dc.date.available | 2024-03-11T10:40:55Z | - |
dc.date.issued | 2023-05-22 | - |
dc.identifier.citation | IEEE Transactions on Neural Networks and Learning Systems, 2023, p. 1-15 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | http://hdl.handle.net/10722/340000 | - |
dc.description.abstract | <p>Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments.</p> | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.ispartof | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.subject | Bearing fault diagnosis | - |
dc.subject | complex operating conditions | - |
dc.subject | Convolution | - |
dc.subject | deep learning (DL) | - |
dc.subject | Fault diagnosis | - |
dc.subject | Feature extraction | - |
dc.subject | Kernel | - |
dc.subject | Noise measurement | - |
dc.subject | noise resist correlation | - |
dc.subject | periodic convolutional module (PeriodConv) | - |
dc.subject | Signal to noise ratio | - |
dc.subject | Vibrations | - |
dc.title | PeriodNet: Noise-Robust Fault Diagnosis Method under Varying Speed Conditions | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TNNLS.2023.3274290 | - |
dc.identifier.scopus | eid_2-s2.0-85161082788 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 15 | - |
dc.identifier.eissn | 2162-2388 | - |
dc.identifier.isi | WOS:001005882100001 | - |
dc.identifier.issnl | 2162-237X | - |